diff --git a/.github/workflows/integration-tests.yml b/.github/workflows/integration-tests.yml index 36b8d18..f09af43 100644 --- a/.github/workflows/integration-tests.yml +++ b/.github/workflows/integration-tests.yml @@ -39,5 +39,6 @@ jobs: TAVILY_API_KEY: ${{ secrets.TAVILY_API_KEY }} LANGSMITH_API_KEY: ${{ secrets.LANGSMITH_API_KEY }} LANGSMITH_TRACING: true + LANGSMITH_TEST_CACHE: tests/cassettes run: | uv run pytest tests/integration_tests diff --git a/src/react_agent/graph.py b/src/react_agent/graph.py index 5940fd7..4614895 100644 --- a/src/react_agent/graph.py +++ b/src/react_agent/graph.py @@ -7,7 +7,6 @@ from typing import Dict, List, Literal, cast from langchain_core.messages import AIMessage -from langchain_core.prompts import ChatPromptTemplate from langchain_core.runnables import RunnableConfig from langgraph.graph import StateGraph from langgraph.prebuilt import ToolNode @@ -36,25 +35,21 @@ async def call_model( """ configuration = Configuration.from_runnable_config(config) - # Create a prompt template. Customize this to change the agent's behavior. - prompt = ChatPromptTemplate.from_messages( - [("system", configuration.system_prompt), ("placeholder", "{messages}")] - ) - # Initialize the model with tool binding. Change the model or add more tools here. model = load_chat_model(configuration.model).bind_tools(TOOLS) - # Prepare the input for the model, including the current system time - message_value = await prompt.ainvoke( - { - "messages": state.messages, - "system_time": datetime.now(tz=timezone.utc).isoformat(), - }, - config, + # Format the system prompt. Customize this to change the agent's behavior. + system_message = configuration.system_prompt.format( + system_time=datetime.now(tz=timezone.utc).isoformat() ) # Get the model's response - response = cast(AIMessage, await model.ainvoke(message_value, config)) + response = cast( + AIMessage, + await model.ainvoke( + [{"role": "system", "content": system_message}, *state.messages], config + ), + ) # Handle the case when it's the last step and the model still wants to use a tool if state.is_last_step and response.tool_calls: diff --git a/tests/casettes/103fe67e-a040-4e4e-aadb-b20a7057f904.yaml b/tests/casettes/103fe67e-a040-4e4e-aadb-b20a7057f904.yaml deleted file mode 100644 index 0ea32e3..0000000 --- a/tests/casettes/103fe67e-a040-4e4e-aadb-b20a7057f904.yaml +++ /dev/null @@ -1,464 +0,0 @@ -interactions: -- request: - body: '{"max_tokens": 1024, "messages": [{"role": "user", "content": "Who is the - founder of LangChain?"}], "model": "claude-3-5-sonnet-20240620", "system": "You - are a helpful AI assistant.\n\nSystem time: 2024-09-16T12:24:33.011280+00:00", - "tools": [{"name": "scrape_webpage", "description": "Scrape the given webpage - and return a summary of text based on the instructions.", "input_schema": {"type": - "object", "properties": {"url": {"description": "The URL of the webpage to scrape.", - "type": "string"}, "instructions": {"description": "The instructions to give - to the scraper. An LLM will be used to respond using the instructions and the - scraped text.", "type": "string"}, "config": {"type": "object", "properties": - {"tags": {"type": "array", "items": {"type": "string"}}, "metadata": {"type": - "object"}, "callbacks": {"anyOf": [{"type": "array", "items": {}}, {}]}, "run_name": - {"type": "string"}, "max_concurrency": {"type": "integer"}, "recursion_limit": - {"type": "integer"}, "configurable": {"type": "object"}, "run_id": {"type": - "string", "format": "uuid"}}}}, "required": ["url", "instructions", "config"]}}, - {"name": "search", "description": "Search for general web results. This function - performs a search using the Tavily search engine, which is designed\nto provide - comprehensive, accurate, and trusted results. It''s particularly useful\nfor - answering questions about current events.", "input_schema": {"type": "object", - "properties": {"query": {"type": "string"}}, "required": ["query"]}}]}' - headers: {} - method: POST - uri: https://api.anthropic.com/v1/messages - response: - body: - string: !!binary | - H4sIAAAAAAAAA3RRwY7TQAz9FcsXLtNVtpSKzgV1ewC63UqLVruoCEVD4jSBxG7HHtFS5d9XyQoB - B06Wn/3s9+wLNiV67HSfZ9dzXq/Xnz8lXt53y9Pm4Xa5vdut0aGdDzR0kWrYEzqM0g5AUG3UAhs6 - 7KSkFj0WbUglTV5P3kxUmMkm02w6y+bTDB0WwkZs6L9cfg81Og30MXh8EAisPymC1Y3CMZFaIwzh - myQDqwkqSVxSBKlgE3i/qkPDDj6+altgohJMQCnEooZKIhQpRmKDwCWEokgxGEHDlcQuDIOvYEMG - HUEpYHWwkXSWdIW9+yNRpM2TDsbHaw15yrPr1Wq12374VTy9vT3d8M32fbV4/B7RIYdu4L3oGFh8 - SIb+gsdE8Ywen2qBRv/r5x32/VeHanLIIwUV/lfFWFA6JuKC0HNqW4dp/I2/vGzLTX4QK/r5YuZQ - kv2NLaZ9/wwAAP//AwAoDYjV+gEAAA== - headers: - CF-Cache-Status: - - DYNAMIC - CF-RAY: - - 8c40d5f83851985e-SJC - Connection: - - keep-alive - Content-Encoding: - - gzip - Content-Type: - - application/json - Date: - - Mon, 16 Sep 2024 12:24:53 GMT - Server: - - cloudflare - Transfer-Encoding: - - chunked - X-Robots-Tag: - - none - anthropic-ratelimit-requests-limit: - - '4000' - anthropic-ratelimit-requests-remaining: - - '3999' - anthropic-ratelimit-requests-reset: - - '2024-09-16T12:24:54Z' - anthropic-ratelimit-tokens-limit: - - '400000' - anthropic-ratelimit-tokens-remaining: - - '400000' - anthropic-ratelimit-tokens-reset: - - '2024-09-16T12:24:53Z' - request-id: - - req_01Dz6cSGBZ25kTSQUUSNk2zs - via: - - 1.1 google - x-cloud-trace-context: - - ada7375721ba3518afe0c80850b9daaa - status: - code: 200 - message: OK -- request: - body: null - headers: {} - method: POST - uri: https://api.tavily.com/search - response: - body: - string: "{\"query\":\"Who is the founder of LangChain?\",\"follow_up_questions\":null,\"answer\":null,\"images\":[],\"results\":[{\"title\":\"LangChain - Company Profile 2024: Valuation, Funding & Investors - PitchBook\",\"url\":\"https://pitchbook.com/profiles/company/522935-92\",\"content\":\"LangChain - was founded in 2022. Who is the founder of LangChain? Harrison Chase and Ankush - Gola are the founders of LangChain. Who is the CEO of LangChain? Harrison - Chase is the CEO of LangChain. Where is LangChain headquartered? LangChain - is headquartered in San Francisco, CA. What is the size of LangChain? LangChain - has 43 total employees ...\",\"score\":0.9997695,\"raw_content\":null},{\"title\":\"Harrison - Chase - The AI Conference\",\"url\":\"https://aiconference.com/speakers/harrison-chase/\",\"content\":\"Harrison - Chase is the co-founder and CEO of LangChain, a company formed around the - open-source Python/Typescript packages that aim to make it easy to develop - Language Model applications. Prior to starting LangChain, he led the ML team - at Robust Intelligence (an MLOps company focused on testing and validation - of machine learning models), led the ...\",\"score\":0.99951214,\"raw_content\":null},{\"title\":\"Harrison - Chase - Forbes\",\"url\":\"https://www.forbes.com/profile/harrison-chase/\",\"content\":\"Cofounder, - LangChain. Harrison Chase only cofounded LangChain in late 2022, but the company - caught instant attention for enabling anyone to build apps powered by large - language models like GPT-4 ...\",\"score\":0.99924165,\"raw_content\":null},{\"title\":\"LangChain - - Wikipedia\",\"url\":\"https://en.wikipedia.org/wiki/LangChain\",\"content\":\"In - October 2023 LangChain introduced LangServe, a deployment tool designed to - facilitate the transition from LCEL (LangChain Expression Language) prototypes - to production-ready applications.[5]\\nIntegrations[edit]\\nAs of March 2023, - LangChain included integrations with systems including Amazon, Google, and - Microsoft Azure cloud storage; API wrappers for news, movie information, and - weather; Bash for summarization, syntax and semantics checking, and execution - of shell scripts; multiple web scraping subsystems and templates; few-shot - learning prompt generation support; finding and summarizing \\\"todo\\\" tasks - in code; Google Drive documents, spreadsheets, and presentations summarization, - extraction, and creation; Google Search and Microsoft Bing web search; OpenAI, - Anthropic, and Hugging Face language models; iFixit repair guides and wikis - search and summarization; MapReduce for question answering, combining documents, - and question generation; N-gram overlap scoring; PyPDF, pdfminer, fitz, and - pymupdf for PDF file text extraction and manipulation; Python and JavaScript - code generation, analysis, and debugging; Milvus vector database[6] to store - and retrieve vector embeddings; Weaviate vector database[7] to cache embedding - and data objects; Redis cache database storage; Python RequestsWrapper and - other methods for API requests; SQL and NoSQL databases including JSON support; - Streamlit, including for logging; text mapping for k-nearest neighbors search; - time zone conversion and calendar operations; tracing and recording stack - symbols in threaded and asynchronous subprocess runs; and the Wolfram Alpha - website and SDK.[8] As a language model integration framework, LangChain's - use-cases largely overlap with those of language models in general, including - document analysis and summarization, chatbots, and code analysis.[2]\\nHistory[edit]\\nLangChain - was launched in October 2022 as an open source project by Harrison Chase, - while working at machine learning startup Robust Intelligence. In April 2023, - LangChain had incorporated and the new startup raised over $20 million in - funding at a valuation of at least $200 million from venture firm Sequoia - Capital, a week after announcing a $10 million seed investment from Benchmark.[3][4]\\n - The project quickly garnered popularity, with improvements from hundreds of - contributors on GitHub, trending discussions on Twitter, lively activity on - the project's Discord server, many YouTube tutorials, and meetups in San Francisco - and London. As of April 2023, it can read from more than 50 document types - and data sources.[9]\\nReferences[edit]\\nExternal links[edit]\",\"score\":0.9964204,\"raw_content\":null},{\"title\":\"LangChain - | Company Overview & News - Forbes\",\"url\":\"https://www.forbes.com/companies/langchain/\",\"content\":\"LangChain. - Founded in late 2022, LangChain was an instant hit in Silicon Valley for its - software that enables anyone to build apps powered by large language models - like GPT-4 in as little as two ...\",\"score\":0.9964204,\"raw_content\":null},{\"title\":\"Harrison - Chase - Co-Founder and CEO @ LangChain - Crunchbase\",\"url\":\"https://www.crunchbase.com/person/harrison-chase\",\"content\":\"Number - of Current Jobs 1. Number of Past Jobs 1. Harrison Chase is the Co-Founder - and CEO at LangChain. Additionally, Harrison Chase has had 1 past job as the - Machine Learning Engineer at Robust Intelligence. LangChain Co-Founder and - CEO Jan 2023. Organization Name.\",\"score\":0.99505633,\"raw_content\":null},{\"title\":\"Key - Insights from Harrison Chase's Talk on Building Next-Level AI Agents\",\"url\":\"https://www.turingpost.com/p/harrison-chase-langchain-ai-agents\",\"content\":\"Harrison - Chase, founder of LangChain, shared insights on the evolution of AI agents - and their applications during Sequoia Capital's AI Ascent. ... Saves you a - lot of research time, plus gives a flashback to ML history and insights into - the future. Stay ahead alongside over 65,000 professionals from top AI labs, - ML startups, and enterprises ...\",\"score\":0.99392605,\"raw_content\":null},{\"title\":\"What - Is LangChain? - IBM\",\"url\":\"https://www.ibm.com/topics/langchain\",\"content\":\"Applications - made with LangChain provide great utility for a variety of use cases, from - straightforward question-answering and text generation tasks to more complex - solutions that use an LLM as a \u201Creasoning engine.\u201D\\nTrain, validate, - tune and deploy generative AI, foundation models and machine learning capabilities - with ease and build AI applications in a fraction of the time with a fraction - of the data.\\n When building a chain for an agent, inputs include:\\nDespite - their heralded power and versatility, LLMs have important limitations: namely, - a lack of up-to-date information, a lack of domain-specific expertise and - a general difficulty with math.\\nLangChain tools\_(link resides outside ibm.com) - are a set of functions that empower LangChain agents to interact with real-world - information in order to expand or improve the services it can provide. Launched - by Harrison Chase in October 2022, LangChain enjoyed a meteoric rise to prominence: - as of June 2023, it was the single fastest-growing open source project on - Github.1 Coinciding with the momentous launch of OpenAI\u2019s ChatGPT the - following month, LangChain has played a significant role in making generative - AI more accessible to enthusiasts in the wake of its widespread popularity.\\n - Reimagine how you work with\_AI: our diverse, global team of more than 20,000 - AI\_experts can help you quickly and confidently\_design and scale AI and - automation across your\_business, working across our own IBM\_watsonx\_technology\_and - an open ecosystem of partners to deliver any\_AI model, on any cloud, guided - by ethics and trust.\\n While it\u2019s the GPT model that interprets the - user\u2019s input and composes a natural language response, it\u2019s the - application that (among other things) provides an interface for the user to - type and read and a UX design that governs the chatbot experience.\",\"score\":0.99306935,\"raw_content\":null},{\"title\":\"LangChain's - origin story | Basedash\",\"url\":\"https://www.basedash.com/blog/langchains-origin-story\",\"content\":\"USER - CRM\\nADMIN PANEL\\nSQL COMPOSER WITH AI\\nRelated posts\\nRelated posts\\nRelated - posts\\nMy 9 core Mac apps and utilities\\nTom Johnson\\nHow Supabase became - this generation\u2019s database\\nMax Musing\\nReport: The 2023 State of Databases\\nMax - Musing\\nBasedash on the main stage at Collision 2023\\nMax Musing\\nBasedash - raises $4.5M led by Matrix\\nMax Musing\\n6 Retool Alternatives for 2023 - - A Comprehensive Guide\\nJordan Chavis\\nSOC IIType 2 Certified\\nCompany\\nAbout\\nCareers\\nTerms - of service\\nPrivacy policy\\nContact us\\nBlog\\nBrand\\nSlack community\\nSitemap\\nProduct\\nPricing\\nIntegrations\\nFeedback\\nChangelog\\nDocs\\nDownload - app\\nStatus\\nFeatures\\nViews\\nQueries\\nActions\\nSecurity\\nPower features\\n\xA9 - 2023 BaseDash Inc.\\nProudly carbon-neutral.\\n SOC IIType 2 Certified\\nCompany\\nAbout\\nCareers\\nTerms - of service\\nPrivacy policy\\nContact us\\nBlog\\nBrand\\nSlack community\\nSitemap\\nProduct\\nPricing\\nIntegrations\\nFeedback\\nChangelog\\nDocs\\nDownload - app\\nStatus\\nFeatures\\nViews\\nQueries\\nActions\\nSecurity\\nPower features\\n\xA9 - 2023 BaseDash Inc.\\nProudly carbon-neutral.\\n SOC IIType 2 Certified\\nCompany\\nAbout\\nCareers\\nTerms - of service\\nPrivacy policy\\nContact us\\nBlog\\nBrand\\nSlack community\\nSitemap\\nProduct\\nPricing\\nIntegrations\\nFeedback\\nChangelog\\nDocs\\nDownload - app\\nStatus\\nFeatures\\nViews\\nQueries\\nActions\\nSecurity\\nPower features\\n\xA9 - 2023 BaseDash Inc.\\nProudly carbon-neutral. About\\nFeatures\\nPricing\\nChangelog\\nBlog\\nDocs\\nLog - in\\nSign up\\nAbout\\nFeatures\\nPricing\\nLog in\\nSign up\\nLog in\\nSign - up\\nLangChain's origin story\\nMax Musing\\nFounder\\nThe admin panel that - you'll actually want to use. To do this, the LangSmith product allows developers - to see the inputs and outputs at each step of a model run and the exact sequence - of runs (debug), write tests to check if the response was intended behavior - (test), collect input/output examples to further refine the model (evaluate), - and log latency, token usage, and feedback (monitor).\\n\",\"score\":0.98208266,\"raw_content\":null},{\"title\":\"The - Point of LangChain \u2014 with Harrison Chase of LangChain\",\"url\":\"https://www.latent.space/p/langchain\",\"content\":\"And - so you can do a lot of things like reflection and kind of like making sure - that you're on the right track and really put more safeguards and thinking - about these agents as opposed to relying on like chas and interface, like - the bot we have that's on GitHub answering questions on the issues, I think - probably gives better answers than the bots that we have that are on chat - on the website. [00:50:32]\\nHarrison: And then between kind of like allowing - for, I think one helpful thing that we did in terms of like distinguishing - between basically the base interfaces and then more complex stuff is part - of the separation around the docs is there's like the components piece, which - has the model IO, the retrieval, the agents, the callbacks, things like that. - And then like, I know a lot of people are doing this, but like a personal - assistant for like managing like email calendar, basic stuff, which I think - is, I think that's like a fantastic application for these like agent like - things, because if you think about personal assistants today, you usually - interact, I don't have one, but I'm told you interact with them over email. - Show Notes\\nLangChain\\nLangChain\u2019s Berkshire Hathaway Homepage\\nAbstractions - tweet\\nLangSmith\\nLangSmith Cookbooks repo\\nLangChain Retrieval blog\\nEvaluating - CSV Question/Answering blog and YouTube\\nMultiOn Partner blog\\nHarvard Sports - Analytics Collective\\nEvaluating RAG Webinar\\nawesome-langchain:\\nLLM Math - Chain\\nSelf-Ask\\nLangChain Hub UI\\n\u201CLangChain is Pointless\u201D\\nHarrison\u2019s - links\\nsports - estimating player compatibility in the NBA\\nearly interest - in prompt injections\\nGitHub\\nTwitter\\nTimestamps\\n[00:00:00] Introduction\\n[00:00:48] - Harrison's background and how sports led him into ML\\n[00:04:54] Memory (for - long running chats, whether a simple Buffer, Knowledge Graph, Summary, or - Vector Store)\\nUse-Cases: compositions of Components\\nChains: combining - a PromptTemplate, LLM Model and optional OutputParser\\nwith Router, Sequential, - and Transform Chains for advanced usecases\\nsavable, sharable schemas that - can be loaded from LangChainHub\\nAgents: a chain that has access to a suite - of tools, of nondeterministic8 length because the LLM is used as a reasoning - engine to determine which actions to take and in which order.\",\"score\":0.8589554,\"raw_content\":null}],\"response_time\":1.84}" - headers: - Connection: - - keep-alive - Content-Length: - - '12187' - Content-Type: - - application/json - Date: - - Mon, 16 Sep 2024 12:24:55 GMT - Server: - - nginx - status: - code: 200 - message: OK -- request: - body: '{"max_tokens": 1024, "messages": [{"role": "user", "content": "Who is the - founder of LangChain?"}, {"role": "assistant", "content": [{"text": "To answer - this question about the founder of LangChain, I''ll need to search for current - and accurate information. Let me do that for you.", "type": "text"}, {"type": - "tool_use", "name": "search", "input": {"query": "Who is the founder of LangChain?"}, - "id": "toolu_01CCCZNHzcW8KxBnBNGf9Vjr"}]}, {"role": "user", "content": [{"type": - "tool_result", "content": "[{\"url\": \"https://pitchbook.com/profiles/company/522935-92\", - \"content\": \"LangChain was founded in 2022. Who is the founder of LangChain? - Harrison Chase and Ankush Gola are the founders of LangChain. Who is the CEO - of LangChain? Harrison Chase is the CEO of LangChain. Where is LangChain headquartered? - LangChain is headquartered in San Francisco, CA. What is the size of LangChain? - LangChain has 43 total employees ...\"}, {\"url\": \"https://aiconference.com/speakers/harrison-chase/\", - \"content\": \"Harrison Chase is the co-founder and CEO of LangChain, a company - formed around the open-source Python/Typescript packages that aim to make it - easy to develop Language Model applications. Prior to starting LangChain, he - led the ML team at Robust Intelligence (an MLOps company focused on testing - and validation of machine learning models), led the ...\"}, {\"url\": \"https://www.forbes.com/profile/harrison-chase/\", - \"content\": \"Cofounder, LangChain. Harrison Chase only cofounded LangChain - in late 2022, but the company caught instant attention for enabling anyone to - build apps powered by large language models like GPT-4 ...\"}, {\"url\": \"https://en.wikipedia.org/wiki/LangChain\", - \"content\": \"In October 2023 LangChain introduced LangServe, a deployment - tool designed to facilitate the transition from LCEL (LangChain Expression Language) - prototypes to production-ready applications.[5]\\nIntegrations[edit]\\nAs of - March 2023, LangChain included integrations with systems including Amazon, Google, - and Microsoft Azure cloud storage; API wrappers for news, movie information, - and weather; Bash for summarization, syntax and semantics checking, and execution - of shell scripts; multiple web scraping subsystems and templates; few-shot learning - prompt generation support; finding and summarizing \\\"todo\\\" tasks in code; - Google Drive documents, spreadsheets, and presentations summarization, extraction, - and creation; Google Search and Microsoft Bing web search; OpenAI, Anthropic, - and Hugging Face language models; iFixit repair guides and wikis search and - summarization; MapReduce for question answering, combining documents, and question - generation; N-gram overlap scoring; PyPDF, pdfminer, fitz, and pymupdf for PDF - file text extraction and manipulation; Python and JavaScript code generation, - analysis, and debugging; Milvus vector database[6] to store and retrieve vector - embeddings; Weaviate vector database[7] to cache embedding and data objects; - Redis cache database storage; Python RequestsWrapper and other methods for API - requests; SQL and NoSQL databases including JSON support; Streamlit, including - for logging; text mapping for k-nearest neighbors search; time zone conversion - and calendar operations; tracing and recording stack symbols in threaded and - asynchronous subprocess runs; and the Wolfram Alpha website and SDK.[8] As a - language model integration framework, LangChain''s use-cases largely overlap - with those of language models in general, including document analysis and summarization, - chatbots, and code analysis.[2]\\nHistory[edit]\\nLangChain was launched in - October 2022 as an open source project by Harrison Chase, while working at machine - learning startup Robust Intelligence. In April 2023, LangChain had incorporated - and the new startup raised over $20 million in funding at a valuation of at - least $200 million from venture firm Sequoia Capital, a week after announcing - a $10 million seed investment from Benchmark.[3][4]\\n The project quickly garnered - popularity, with improvements from hundreds of contributors on GitHub, trending - discussions on Twitter, lively activity on the project''s Discord server, many - YouTube tutorials, and meetups in San Francisco and London. As of April 2023, - it can read from more than 50 document types and data sources.[9]\\nReferences[edit]\\nExternal - links[edit]\"}, {\"url\": \"https://www.forbes.com/companies/langchain/\", \"content\": - \"LangChain. Founded in late 2022, LangChain was an instant hit in Silicon Valley - for its software that enables anyone to build apps powered by large language - models like GPT-4 in as little as two ...\"}, {\"url\": \"https://www.crunchbase.com/person/harrison-chase\", - \"content\": \"Number of Current Jobs 1. Number of Past Jobs 1. Harrison Chase - is the Co-Founder and CEO at LangChain. Additionally, Harrison Chase has had - 1 past job as the Machine Learning Engineer at Robust Intelligence. LangChain - Co-Founder and CEO Jan 2023. Organization Name.\"}, {\"url\": \"https://www.turingpost.com/p/harrison-chase-langchain-ai-agents\", - \"content\": \"Harrison Chase, founder of LangChain, shared insights on the - evolution of AI agents and their applications during Sequoia Capital''s AI Ascent. - ... Saves you a lot of research time, plus gives a flashback to ML history and - insights into the future. Stay ahead alongside over 65,000 professionals from - top AI labs, ML startups, and enterprises ...\"}, {\"url\": \"https://www.ibm.com/topics/langchain\", - \"content\": \"Applications made with LangChain provide great utility for a - variety of use cases, from straightforward question-answering and text generation - tasks to more complex solutions that use an LLM as a \u201creasoning engine.\u201d\\nTrain, - validate, tune and deploy generative AI, foundation models and machine learning - capabilities with ease and build AI applications in a fraction of the time with - a fraction of the data.\\n When building a chain for an agent, inputs include:\\nDespite - their heralded power and versatility, LLMs have important limitations: namely, - a lack of up-to-date information, a lack of domain-specific expertise and a - general difficulty with math.\\nLangChain tools\u00a0(link resides outside ibm.com) - are a set of functions that empower LangChain agents to interact with real-world - information in order to expand or improve the services it can provide. Launched - by Harrison Chase in October 2022, LangChain enjoyed a meteoric rise to prominence: - as of June 2023, it was the single fastest-growing open source project on Github.1 - Coinciding with the momentous launch of OpenAI\u2019s ChatGPT the following - month, LangChain has played a significant role in making generative AI more - accessible to enthusiasts in the wake of its widespread popularity.\\n Reimagine - how you work with\u00a0AI: our diverse, global team of more than 20,000 AI\u00a0experts - can help you quickly and confidently\u00a0design and scale AI and automation - across your\u00a0business, working across our own IBM\u00a0watsonx\u00a0technology\u00a0and - an open ecosystem of partners to deliver any\u00a0AI model, on any cloud, guided - by ethics and trust.\\n While it\u2019s the GPT model that interprets the user\u2019s - input and composes a natural language response, it\u2019s the application that - (among other things) provides an interface for the user to type and read and - a UX design that governs the chatbot experience.\"}, {\"url\": \"https://www.basedash.com/blog/langchains-origin-story\", - \"content\": \"USER CRM\\nADMIN PANEL\\nSQL COMPOSER WITH AI\\nRelated posts\\nRelated - posts\\nRelated posts\\nMy 9 core Mac apps and utilities\\nTom Johnson\\nHow - Supabase became this generation\u2019s database\\nMax Musing\\nReport: The 2023 - State of Databases\\nMax Musing\\nBasedash on the main stage at Collision 2023\\nMax - Musing\\nBasedash raises $4.5M led by Matrix\\nMax Musing\\n6 Retool Alternatives - for 2023 - A Comprehensive Guide\\nJordan Chavis\\nSOC IIType 2 Certified\\nCompany\\nAbout\\nCareers\\nTerms - of service\\nPrivacy policy\\nContact us\\nBlog\\nBrand\\nSlack community\\nSitemap\\nProduct\\nPricing\\nIntegrations\\nFeedback\\nChangelog\\nDocs\\nDownload - app\\nStatus\\nFeatures\\nViews\\nQueries\\nActions\\nSecurity\\nPower features\\n\u00a9 - 2023 BaseDash Inc.\\nProudly carbon-neutral.\\n SOC IIType 2 Certified\\nCompany\\nAbout\\nCareers\\nTerms - of service\\nPrivacy policy\\nContact us\\nBlog\\nBrand\\nSlack community\\nSitemap\\nProduct\\nPricing\\nIntegrations\\nFeedback\\nChangelog\\nDocs\\nDownload - app\\nStatus\\nFeatures\\nViews\\nQueries\\nActions\\nSecurity\\nPower features\\n\u00a9 - 2023 BaseDash Inc.\\nProudly carbon-neutral.\\n SOC IIType 2 Certified\\nCompany\\nAbout\\nCareers\\nTerms - of service\\nPrivacy policy\\nContact us\\nBlog\\nBrand\\nSlack community\\nSitemap\\nProduct\\nPricing\\nIntegrations\\nFeedback\\nChangelog\\nDocs\\nDownload - app\\nStatus\\nFeatures\\nViews\\nQueries\\nActions\\nSecurity\\nPower features\\n\u00a9 - 2023 BaseDash Inc.\\nProudly carbon-neutral. About\\nFeatures\\nPricing\\nChangelog\\nBlog\\nDocs\\nLog - in\\nSign up\\nAbout\\nFeatures\\nPricing\\nLog in\\nSign up\\nLog in\\nSign - up\\nLangChain''s origin story\\nMax Musing\\nFounder\\nThe admin panel that - you''ll actually want to use. To do this, the LangSmith product allows developers - to see the inputs and outputs at each step of a model run and the exact sequence - of runs (debug), write tests to check if the response was intended behavior - (test), collect input/output examples to further refine the model (evaluate), - and log latency, token usage, and feedback (monitor).\\n\"}, {\"url\": \"https://www.latent.space/p/langchain\", - \"content\": \"And so you can do a lot of things like reflection and kind of - like making sure that you''re on the right track and really put more safeguards - and thinking about these agents as opposed to relying on like chas and interface, - like the bot we have that''s on GitHub answering questions on the issues, I - think probably gives better answers than the bots that we have that are on chat - on the website. [00:50:32]\\nHarrison: And then between kind of like allowing - for, I think one helpful thing that we did in terms of like distinguishing between - basically the base interfaces and then more complex stuff is part of the separation - around the docs is there''s like the components piece, which has the model IO, - the retrieval, the agents, the callbacks, things like that. And then like, I - know a lot of people are doing this, but like a personal assistant for like - managing like email calendar, basic stuff, which I think is, I think that''s - like a fantastic application for these like agent like things, because if you - think about personal assistants today, you usually interact, I don''t have one, - but I''m told you interact with them over email. Show Notes\\nLangChain\\nLangChain\u2019s - Berkshire Hathaway Homepage\\nAbstractions tweet\\nLangSmith\\nLangSmith Cookbooks - repo\\nLangChain Retrieval blog\\nEvaluating CSV Question/Answering blog and - YouTube\\nMultiOn Partner blog\\nHarvard Sports Analytics Collective\\nEvaluating - RAG Webinar\\nawesome-langchain:\\nLLM Math Chain\\nSelf-Ask\\nLangChain Hub - UI\\n\u201cLangChain is Pointless\u201d\\nHarrison\u2019s links\\nsports - estimating - player compatibility in the NBA\\nearly interest in prompt injections\\nGitHub\\nTwitter\\nTimestamps\\n[00:00:00] - Introduction\\n[00:00:48] Harrison''s background and how sports led him into - ML\\n[00:04:54] Memory (for long running chats, whether a simple Buffer, Knowledge - Graph, Summary, or Vector Store)\\nUse-Cases: compositions of Components\\nChains: - combining a PromptTemplate, LLM Model and optional OutputParser\\nwith Router, - Sequential, and Transform Chains for advanced usecases\\nsavable, sharable schemas - that can be loaded from LangChainHub\\nAgents: a chain that has access to a - suite of tools, of nondeterministic8 length because the LLM is used as a reasoning - engine to determine which actions to take and in which order.\"}]", "tool_use_id": - "toolu_01CCCZNHzcW8KxBnBNGf9Vjr", "is_error": false}]}], "model": "claude-3-5-sonnet-20240620", - "system": "You are a helpful AI assistant.\n\nSystem time: 2024-09-16T12:24:37.857496+00:00", - "tools": [{"name": "scrape_webpage", "description": "Scrape the given webpage - and return a summary of text based on the instructions.", "input_schema": {"type": - "object", "properties": {"url": {"description": "The URL of the webpage to scrape.", - "type": "string"}, "instructions": {"description": "The instructions to give - to the scraper. An LLM will be used to respond using the instructions and the - scraped text.", "type": "string"}, "config": {"type": "object", "properties": - {"tags": {"type": "array", "items": {"type": "string"}}, "metadata": {"type": - "object"}, "callbacks": {"anyOf": [{"type": "array", "items": {}}, {}]}, "run_name": - {"type": "string"}, "max_concurrency": {"type": "integer"}, "recursion_limit": - {"type": "integer"}, "configurable": {"type": "object"}, "run_id": {"type": - "string", "format": "uuid"}}}}, "required": ["url", "instructions", "config"]}}, - {"name": "search", "description": "Search for general web results. This function - performs a search using the Tavily search engine, which is designed\nto provide - comprehensive, accurate, and trusted results. It''s particularly useful\nfor - answering questions about current events.", "input_schema": {"type": "object", - "properties": {"query": {"type": "string"}}, "required": ["query"]}}]}' - headers: {} - method: POST - uri: https://api.anthropic.com/v1/messages - response: - body: - string: !!binary | - H4sIAAAAAAAAA2xVUW/cNgz+K4SefYfLJe0KvyXB2gZI0K5r97B1CHgybWsnk65EXeoF+e+D5Lv0 - bs2TIZv6+PEjP/rRuMbUZojd/ersD/r8Z+ovRLrfvuy+NP9+f3M59IOpjE4j5SiKETsylQni8wuM - 0UVFVlOZQRrypjbWY2pocb54tYjCTLpYr9YXq9frlamMFVZiNfVfjwdQpe/5ennU5gojNSAM2hNE - wmB7CBST11jBDVhkGIPsXEMwSYIHpz04biUMqE4YcCNJy+VWEjcUQFq4Re6ue3Rcf+Wv/HyCB4z7 - sAY2E7zHEFwUhuseI4Fj+GBVNhRgvVqvl/CeAgEGgigDwZYmGMWxxheSIjflbGUYkaeS92wJb+fP - 9U+p4j56cQxw/euHE/bLjLJewvVzWA2/ZypRUrAUAX0UGIiLEpe8TbGHd+IRMAIeoVegvaSuf4HG - IIGywoNjYvUTtISaAjVZjszxROwdOo8bT4XZ+b4+xx00qFTDqdIeE9t+RjoWtrBjkJF4MVeSCfxD - VgvsxRKu0G67kLFruKI2U4yKQXOm5xzV/6vxNPfgDm3vmOCWMHC+ooQDoMIn2aSocMNK3ruO2FKV - mdzdfhjjoXXQik2HmaRYcubm7NC7ZpZBWhj2OfwhR3FDLAW8yh2bsbogD9ofC/MtObv1E3TomBoY - ZUweg9PpoPflTUnX0I68jBQyryGx02kJVxNcjsH5LON5dTxw0GPW2UoYJaBSU0ACulxJdB271llk - hXZuWCH6egkfUxglnrQO3RBBBQbcEjgFwjjl855RiUzYEdzlkgHH0TtbhIlLuNGDXfMEtgEHepCw - hVYCbJLzZViOr8AoDxRmP3oMHYE/4M+SgndbgncfPy8uCulflvCJrHTs8v2fnJXL/lFLjzuCQJbc - LkuiuvfKXmslm7dJk6KGqZqXywyzoUz02Atj2vwgXTi9lbChWErrXYRS536RjR4122Z5un96jLAh - my2MwKLZSjl2onDU/r3Q2dcQR8xDOmtaZlnEx1Lls7h5l6ACcYF7HpzSRBsIlU4VTzEDvSx2WQfU - ts66sg6W5unvykSV8T4QRmFTG+LmXlNgs/8Q6VvKXjI1J+8rk8o/o340jsek9ypb4mjq8zers8pI - 0pOXZxdPT/8BAAD//wMA8UBANZQGAAA= - headers: - CF-Cache-Status: - - DYNAMIC - CF-RAY: - - 8c40d61569facfc0-SJC - Connection: - - keep-alive - Content-Encoding: - - gzip - Content-Type: - - application/json - Date: - - Mon, 16 Sep 2024 12:25:03 GMT - Server: - - cloudflare - Transfer-Encoding: - - chunked - X-Robots-Tag: - - none - anthropic-ratelimit-requests-limit: - - '4000' - anthropic-ratelimit-requests-remaining: - - '3999' - anthropic-ratelimit-requests-reset: - - '2024-09-16T12:25:54Z' - anthropic-ratelimit-tokens-limit: - - '400000' - anthropic-ratelimit-tokens-remaining: - - '400000' - anthropic-ratelimit-tokens-reset: - - '2024-09-16T12:25:03Z' - request-id: - - req_018pAJZyzb11i66uT7AZPk7R - via: - - 1.1 google - x-cloud-trace-context: - - c2803397a8cc610b16de02a6c63f2dfe - status: - code: 200 - message: OK -version: 1 diff --git a/tests/cassettes/103fe67e-a040-4e4e-aadb-b20a7057f904.yaml b/tests/cassettes/103fe67e-a040-4e4e-aadb-b20a7057f904.yaml new file mode 100644 index 0000000..1d80331 --- /dev/null +++ b/tests/cassettes/103fe67e-a040-4e4e-aadb-b20a7057f904.yaml @@ -0,0 +1,2053 @@ +interactions: +- request: + body: '{"max_tokens": 1024, "messages": [{"role": "user", "content": "Who is the + founder of LangChain?"}], "model": "claude-3-5-sonnet-20240620", "system": "You + are a helpful AI assistant.\n\nSystem time: 2024-11-13T23:50:53.832822+00:00", + "tools": [{"name": "search", "description": "Search for general web results. + This function performs a search using the Tavily search engine, which is designed\nto + provide comprehensive, accurate, and trusted results. It''s particularly useful\nfor + answering questions about current events.", "input_schema": {"properties": {"query": + {"type": "string"}}, "required": ["query"], "type": "object"}}]}' + headers: {} + method: POST + uri: https://api.anthropic.com/v1/messages + response: + body: + string: !!binary | + H4sIAAAAAAAAA2yRS0vEQAzHv0rIxctUuqurOEdXXRQPooIvpIzb9KFtsjuTUevS7y6tiAqeQh6/ + /PPYYJ2jxTaUWTrZf32Wp9Jf3h2+Fa/z+4/F1dFiskCD2q1oqKIQXElo0EszBFwIdVDHigZbyalB + i8vGxZySnWSWBGEmTabpdDfdm6ZocCmsxIr2YfPdVOl9wEdj8VrAcXgjD51ED+tIQWthcE8SFbQi + KCRyTh6kgHPH5bxyNRs43WoaYKIcVCCQ88sKCvEj0UpQiKtEJcmdEtRciG/d0HcbzkmhJcgFtHI6 + Mp3EbezNz4QiTRbDsPd4rMGPWTo5XB/NbiYXz2fkZrfHxye+q9pFiQbZtQP3NcZA8Soq2g2uI/kO + Lf63A/b9o8Ggsso8uSD8V3lMBFpH4iWh5dg0BuP4Drv5UshUXogD2t2dPYMS9XfsYNr3nwAAAP// + AwCzkxon7QEAAA== + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 8e22ab88f99c4cb1-PHL + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 13 Nov 2024 23:51:31 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + X-Robots-Tag: + - none + anthropic-ratelimit-requests-limit: + - '4000' + anthropic-ratelimit-requests-remaining: + - '3999' + anthropic-ratelimit-requests-reset: + - '2024-11-13T23:51:29Z' + anthropic-ratelimit-tokens-limit: + - '400000' + anthropic-ratelimit-tokens-remaining: + - '400000' + anthropic-ratelimit-tokens-reset: + - '2024-11-13T23:51:31Z' + request-id: + - req_019JrRXeYjgQXtSjyp85fdHe + via: + - 1.1 google + status: + code: 200 + message: OK +- request: + body: null + headers: {} + method: POST + uri: https://api.tavily.com/search + response: + body: + string: '{"query":"founder of LangChain","follow_up_questions":null,"answer":null,"images":[],"results":[{"title":"Speaker + Harrison Chase - ELC","url":"https://sfelc.com/speaker/harrison-chase","content":"Harrison + Chase is the CEO and co-founder of LangChain, a company formed around the + open source Python/Typescript packages that aim to make it easy to develop + Language Model applications. Prior to starting LangChain, he led the ML team + at Robust Intelligence (an MLOps company focused on testing and validation + of machine learning models), led the","score":0.99967754,"raw_content":null},{"title":"Harrison + Chase - The AI Conference","url":"https://aiconference.com/speakers/harrison-chase/","content":"Harrison + Chase is the co-founder and CEO of LangChain, a company formed around the + open-source Python/Typescript packages that aim to make it easy to develop + Language Model applications. Prior to starting LangChain, he led the ML team + at Robust Intelligence (an MLOps company focused on testing and validation + of machine learning models), led the","score":0.9995908,"raw_content":null},{"title":"Harrison + Chase | TEDAI San Francisco","url":"https://tedai-sanfrancisco.ted.com/speakers-1/harrison-chase-/co-founder-and-ceo,-langchain/","content":"Harrison + Chase, a Harvard graduate in statistics and computer science, co-founded LangChain + to streamline the development of Language Model applications with open-source + Python/Typescript packages. Chase''s experience includes heading the Machine + Learning team at Robust Intelligence, focusing on the testing and validation + of machine learning models, and leading the entity linking team at Kensho","score":0.9994746,"raw_content":null},{"title":"Harrison + Chase, Author at TechCrunch","url":"https://techcrunch.com/author/harrison-chase/","content":"Harrison + Chase is the CEO and co-founder of LangChain, a company formed around the + open source Python/Typescript packages that aim to make it easy to develop + Language Model applications","score":0.9994185,"raw_content":null},{"title":"LangChain''s + Harrison Chase on Building the Orchestration Layer for AI ...","url":"https://www.sequoiacap.com/podcast/training-data-harrison-chase/","content":"Sonya + Huang: Hi, and welcome to training data. We have with us today Harrison Chase, + founder and CEO of LangChain. Harrison is a legend in the agent ecosystem, + as the product visionary who first connected LLMs with tools and actions. + And LangChain is the most popular agent building framework in the AI space.","score":0.99876,"raw_content":null},{"title":"Harrison + Chase, LangChain CEO - Interview - YouTube","url":"https://www.youtube.com/watch?v=7D8bw_4hTdo","content":"Join + us for an insightful interview with Harrison Chase, the CEO and co-founder + of Langchain, as he provides a comprehensive overview of Langchain''s innovati","score":0.99854493,"raw_content":null},{"title":"Harrison + Chase - Forbes","url":"https://www.forbes.com/profile/harrison-chase/","content":"Harrison + Chase only cofounded LangChain in late 2022, but the company caught instant + attention for enabling anyone to build apps powered by large language models + like GPT-4 in as little as two","score":0.9977743,"raw_content":null},{"title":"LangChain + - Wikipedia","url":"https://en.wikipedia.org/wiki/LangChain","content":"In + October 2023 LangChain introduced LangServe, a deployment tool designed to + facilitate the transition from LCEL (LangChain Expression Language) prototypes + to production-ready applications.[5]\nIntegrations[edit]\nAs of March 2023, + LangChain included integrations with systems including Amazon, Google, and + Microsoft Azure cloud storage; API wrappers for news, movie information, and + weather; Bash for summarization, syntax and semantics checking, and execution + of shell scripts; multiple web scraping subsystems and templates; few-shot + learning prompt generation support; finding and summarizing \"todo\" tasks + in code; Google Drive documents, spreadsheets, and presentations summarization, + extraction, and creation; Google Search and Microsoft Bing web search; OpenAI, + Anthropic, and Hugging Face language models; iFixit repair guides and wikis + search and summarization; MapReduce for question answering, combining documents, + and question generation; N-gram overlap scoring; PyPDF, pdfminer, fitz, and + pymupdf for PDF file text extraction and manipulation; Python and JavaScript + code generation, analysis, and debugging; Milvus vector database[6] to store + and retrieve vector embeddings; Weaviate vector database[7] to cache embedding + and data objects; Redis cache database storage; Python RequestsWrapper and + other methods for API requests; SQL and NoSQL databases including JSON support; + Streamlit, including for logging; text mapping for k-nearest neighbors search; + time zone conversion and calendar operations; tracing and recording stack + symbols in threaded and asynchronous subprocess runs; and the Wolfram Alpha + website and SDK.[8] As a language model integration framework, LangChain''s + use-cases largely overlap with those of language models in general, including + document analysis and summarization, chatbots, and code analysis.[2]\nHistory[edit]\nLangChain + was launched in October 2022 as an open source project by Harrison Chase, + while working at machine learning startup Robust Intelligence. In April 2023, + LangChain had incorporated and the new startup raised over $20 million in + funding at a valuation of at least $200 million from venture firm Sequoia + Capital, a week after announcing a $10 million seed investment from Benchmark.[3][4]\n + The project quickly garnered popularity, with improvements from hundreds of + contributors on GitHub, trending discussions on Twitter, lively activity on + the project''s Discord server, many YouTube tutorials, and meetups in San + Francisco and London. As of April 2023, it can read from more than 50 document + types and data sources.[9]\nReferences[edit]\nExternal links[edit]","score":0.99694854,"raw_content":null},{"title":"Harrison + Chase - CEO of LangChain - Analytics India Magazine","url":"https://analyticsindiamag.com/people/harrison-chase/","content":"By + AIM The dynamic co-founder and CEO of LangChain, Harrison Chase is simplifying + the creation of applications powered by LLMs. With a background in statistics + and computer science from Harvard University, Chase has carved a niche in + the AI landscape. AIM Brand Solutions, a marketing division within AIM, specializes + in creating diverse content such as documentaries, public artworks, podcasts, + videos, articles, and more to effectively tell compelling stories. AIM Research + produces a series of annual reports on AI & Data Science covering every aspect + of the industry. Discover how Cypher 2024 expands to the USA, bridging AI + innovation gaps and tackling the challenges of enterprise AI adoption AIM + India AIM Research AIM Leaders Council 50 Best Data Science Firms","score":0.99491996,"raw_content":null},{"title":"Key + Insights from Harrison Chase''s Talk on Building Next-Level AI Agents","url":"https://www.turingpost.com/p/harrison-chase-langchain-ai-agents","content":"Harrison + Chase, founder of LangChain, shared insights on the evolution of AI agents + and their applications during Sequoia Capital''s AI Ascent. ... Saves you + a lot of research time, plus gives a flashback to ML history and insights + into the future. Stay ahead alongside over 73,000 professionals from top AI + labs, ML startups, and enterprises","score":0.9941801,"raw_content":null}],"response_time":2.54}' + headers: + Connection: + - keep-alive + Content-Length: + - '7474' + Content-Type: + - application/json + Date: + - Wed, 13 Nov 2024 23:51:34 GMT + Server: + - nginx + status: + code: 200 + message: OK +- request: + body: '{"max_tokens": 1024, "messages": [{"role": "user", "content": "Who is the + founder of LangChain?"}, {"role": "assistant", "content": [{"text": "To answer + your question about the founder of LangChain, I''ll need to search for the most + up-to-date information. Let me do that for you.", "type": "text"}, {"type": + "tool_use", "name": "search", "input": {"query": "founder of LangChain"}, "id": + "toolu_01BqD5W1PjJea5XEEFryhmGg"}]}, {"role": "user", "content": [{"type": "tool_result", + "content": "[{\"url\": \"https://sfelc.com/speaker/harrison-chase\", \"content\": + \"Harrison Chase is the CEO and co-founder of LangChain, a company formed around + the open source Python/Typescript packages that aim to make it easy to develop + Language Model applications. Prior to starting LangChain, he led the ML team + at Robust Intelligence (an MLOps company focused on testing and validation of + machine learning models), led the\"}, {\"url\": \"https://aiconference.com/speakers/harrison-chase/\", + \"content\": \"Harrison Chase is the co-founder and CEO of LangChain, a company + formed around the open-source Python/Typescript packages that aim to make it + easy to develop Language Model applications. Prior to starting LangChain, he + led the ML team at Robust Intelligence (an MLOps company focused on testing + and validation of machine learning models), led the\"}, {\"url\": \"https://tedai-sanfrancisco.ted.com/speakers-1/harrison-chase-/co-founder-and-ceo,-langchain/\", + \"content\": \"Harrison Chase, a Harvard graduate in statistics and computer + science, co-founded LangChain to streamline the development of Language Model + applications with open-source Python/Typescript packages. Chase''s experience + includes heading the Machine Learning team at Robust Intelligence, focusing + on the testing and validation of machine learning models, and leading the entity + linking team at Kensho\"}, {\"url\": \"https://techcrunch.com/author/harrison-chase/\", + \"content\": \"Harrison Chase is the CEO and co-founder of LangChain, a company + formed around the open source Python/Typescript packages that aim to make it + easy to develop Language Model applications\"}, {\"url\": \"https://www.sequoiacap.com/podcast/training-data-harrison-chase/\", + \"content\": \"Sonya Huang: Hi, and welcome to training data. We have with us + today Harrison Chase, founder and CEO of LangChain. Harrison is a legend in + the agent ecosystem, as the product visionary who first connected LLMs with + tools and actions. And LangChain is the most popular agent building framework + in the AI space.\"}, {\"url\": \"https://www.youtube.com/watch?v=7D8bw_4hTdo\", + \"content\": \"Join us for an insightful interview with Harrison Chase, the + CEO and co-founder of Langchain, as he provides a comprehensive overview of + Langchain''s innovati\"}, {\"url\": \"https://www.forbes.com/profile/harrison-chase/\", + \"content\": \"Harrison Chase only cofounded LangChain in late 2022, but the + company caught instant attention for enabling anyone to build apps powered by + large language models like GPT-4 in as little as two\"}, {\"url\": \"https://en.wikipedia.org/wiki/LangChain\", + \"content\": \"In October 2023 LangChain introduced LangServe, a deployment + tool designed to facilitate the transition from LCEL (LangChain Expression Language) + prototypes to production-ready applications.[5]\\nIntegrations[edit]\\nAs of + March 2023, LangChain included integrations with systems including Amazon, Google, + and Microsoft Azure cloud storage; API wrappers for news, movie information, + and weather; Bash for summarization, syntax and semantics checking, and execution + of shell scripts; multiple web scraping subsystems and templates; few-shot learning + prompt generation support; finding and summarizing \\\"todo\\\" tasks in code; + Google Drive documents, spreadsheets, and presentations summarization, extraction, + and creation; Google Search and Microsoft Bing web search; OpenAI, Anthropic, + and Hugging Face language models; iFixit repair guides and wikis search and + summarization; MapReduce for question answering, combining documents, and question + generation; N-gram overlap scoring; PyPDF, pdfminer, fitz, and pymupdf for PDF + file text extraction and manipulation; Python and JavaScript code generation, + analysis, and debugging; Milvus vector database[6] to store and retrieve vector + embeddings; Weaviate vector database[7] to cache embedding and data objects; + Redis cache database storage; Python RequestsWrapper and other methods for API + requests; SQL and NoSQL databases including JSON support; Streamlit, including + for logging; text mapping for k-nearest neighbors search; time zone conversion + and calendar operations; tracing and recording stack symbols in threaded and + asynchronous subprocess runs; and the Wolfram Alpha website and SDK.[8] As a + language model integration framework, LangChain''s use-cases largely overlap + with those of language models in general, including document analysis and summarization, + chatbots, and code analysis.[2]\\nHistory[edit]\\nLangChain was launched in + October 2022 as an open source project by Harrison Chase, while working at machine + learning startup Robust Intelligence. In April 2023, LangChain had incorporated + and the new startup raised over $20 million in funding at a valuation of at + least $200 million from venture firm Sequoia Capital, a week after announcing + a $10 million seed investment from Benchmark.[3][4]\\n The project quickly garnered + popularity, with improvements from hundreds of contributors on GitHub, trending + discussions on Twitter, lively activity on the project''s Discord server, many + YouTube tutorials, and meetups in San Francisco and London. As of April 2023, + it can read from more than 50 document types and data sources.[9]\\nReferences[edit]\\nExternal + links[edit]\"}, {\"url\": \"https://analyticsindiamag.com/people/harrison-chase/\", + \"content\": \"By AIM The dynamic co-founder and CEO of LangChain, Harrison + Chase is simplifying the creation of applications powered by LLMs. With a background + in statistics and computer science from Harvard University, Chase has carved + a niche in the AI landscape. AIM Brand Solutions, a marketing division within + AIM, specializes in creating diverse content such as documentaries, public artworks, + podcasts, videos, articles, and more to effectively tell compelling stories. + AIM Research produces a series of annual reports on AI & Data Science covering + every aspect of the industry. Discover how Cypher 2024 expands to the USA, bridging + AI innovation gaps and tackling the challenges of enterprise AI adoption AIM + India AIM Research AIM Leaders Council 50 Best Data Science Firms\"}, {\"url\": + \"https://www.turingpost.com/p/harrison-chase-langchain-ai-agents\", \"content\": + \"Harrison Chase, founder of LangChain, shared insights on the evolution of + AI agents and their applications during Sequoia Capital''s AI Ascent. ... Saves + you a lot of research time, plus gives a flashback to ML history and insights + into the future. Stay ahead alongside over 73,000 professionals from top AI + labs, ML startups, and enterprises\"}]", "tool_use_id": "toolu_01BqD5W1PjJea5XEEFryhmGg", + "is_error": false}]}], "model": "claude-3-5-sonnet-20240620", "system": "You + are a helpful AI assistant.\n\nSystem time: 2024-11-13T23:50:59.620569+00:00", + "tools": [{"name": "search", "description": "Search for general web results. + This function performs a search using the Tavily search engine, which is designed\nto + provide comprehensive, accurate, and trusted results. It''s particularly useful\nfor + answering questions about current events.", "input_schema": {"properties": {"query": + {"type": "string"}}, "required": ["query"], "type": "object"}}]}' + headers: {} + method: POST + uri: https://api.anthropic.com/v1/messages + response: + body: + string: !!binary | + H4sIAAAAAAAAA3RUXW/cRgz8K8QiQF90wln+SHtvjlvERh2kqG2gaFMYvBUlbW7FlXe55wiG/3vB + 9Z0/EvRJgEQOZ4ZDPRjXmpUZU3+7PLg8/P1Kmq83H9PPza9Xf/2d+vPh5hdTGZkn0ipKCXsylYnB + 6wtMySVBFlOZMbTkzcpYj7mlxeHieJECM8miWTZHy5NmaSpjAwuxmNU/D3tQoW/aXh4rcz0gb2AO + GboQ9RnhLlMSF7iGC7DIwOEephi2rqVSeO9kAMddiCNqHeA6ZAEZCLqQuaUIoYNL5P5sQMf1F/7C + 1//zEVyCc4zRpcBwNmCiGj6FSJAmsq5zFr2fV4pwUH9XqK0604bFHhm5hbPfPv84vqnhfE+gfT2d + waMQNMumqeG6oI0T8gz3mCB0nbNOGYDHzHagVjs+WwlriqUJMAEyhIl4kUKOltSqr2SlzD2sd1wH + rYM12k0flYXiJEFxSZxNhbhOzkIRknXElqCLYVTNW4wt3LDbUkxO5gJ8VMMH6opRglEc9y+qKhgI + PLXFnU9oB8cEl4SRtUwIR0CBP8M6J4ELFvLe9TqxAnzW3wWbE7UQGETjwH0huUXv2qethw7GHbjf + g5dMpsLwuH7l8112duNn6NExtTCFKXuMTmb1QWmeXujkMbOTuSqT1jOcTtF5tfmw2m36iduALUR0 + Si+5nktMWKDL3Druyx5nSGRzVAFbivCuWcLovFfejveVagOqpPysCEXFJNGOl5ayiSu6y8EhnOHk + BH0FaQhR/AzYSckeh8y2wMK7g5fmRCU2W0oyktJUsA/EdhgxbopXJzXclACXsPyUlENLMQ1uql65 + qCFakw0jAe49hC7iSPchbsoBt7QlH6bCYpq8s0VZginck7qx1ijHnsAj9xl72q0MvNsQfPzjenFU + GP14ajZwcm0Bwbe2uz5HerXINKFmadJcWuXon9e8o1d8CB1ICP4p/M8q9KZRYMQNgRMgTI4iSIAi + sfx6vqdejieS3vHpxRvZtXn8tzJJwnQbCVNgszLE7a3kyGb3IdFd1vCbFWfvK5PLH3f1YBxPWW4l + bIiTWTXL98eVCVnevHx/8vj4HwAAAP//AwBvXpD30gUAAA== + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 8e22abad2aef4caf-PHL + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 13 Nov 2024 23:51:40 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + X-Robots-Tag: + - none + anthropic-ratelimit-requests-limit: + - '4000' + anthropic-ratelimit-requests-remaining: + - '3999' + anthropic-ratelimit-requests-reset: + - '2024-11-13T23:51:35Z' + anthropic-ratelimit-tokens-limit: + - '400000' + anthropic-ratelimit-tokens-remaining: + - '400000' + anthropic-ratelimit-tokens-reset: + - '2024-11-13T23:51:40Z' + request-id: + - req_012BB17DG6rpcEU1xAbh9Zao + via: + - 1.1 google + status: + code: 200 + message: OK +- request: + body: '{"max_tokens": 1024, "messages": [{"role": "user", "content": "Who is the + founder of LangChain?"}], "model": "claude-3-5-sonnet-20240620", "system": "You + are a helpful AI assistant.\n\nSystem time: 2024-11-13T23:51:11.433533+00:00", + "tools": [{"name": "search", "description": "Search for general web results. + This function performs a search using the Tavily search engine, which is designed\nto + provide comprehensive, accurate, and trusted results. It''s particularly useful\nfor + answering questions about current events.", "input_schema": {"properties": {"query": + {"type": "string"}}, "required": ["query"], "type": "object"}}]}' + headers: {} + method: POST + uri: https://api.anthropic.com/v1/messages + response: + body: + string: !!binary | + H4sIAAAAAAAAA1SRTWvcQAyG/4rQpZdxcHY3XuJLCYX0a3tJCz2EYiYeeT2tLXktTRuz+L8Xe1vS + noQ+3lcP0hljwBJ7PVb59ef44Xtzc/+UBp8Oxce3t9vdcf+ADm0aaJkiVX8kdDhKtxS8alTzbOiw + l0Adllh3PgXKttlNpsJMlm3yzS4vNjk6rIWN2LB8PP81NXpe5Gso8YuAZ/1FI1gbFU6J1KIw+LpO + ozfqJgfvX3UdMFEAE1DyY91CI4uCoBc1SENmkgVvBJEbGXt/8XiSZHDwfHzT+sjgOUA0hUYSBxqv + 4EAGPUEQsNbb6jlJusLZvdCKdFXS5Qbr4ZY8Vfn13VTc3/XF/vT88PPdp9ooNBoEHbLvF90Fc1Hx + kAzLM54SjROW+LUViLrC/wEBaV4oX+M8f3OoJkM1klfh/ynWhtIpEdeEJaeuc5jWN5Xny7bK5Aex + YrnbFg4l2b+12/08/wYAAP//AwBjKTr0BQIAAA== + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 8e22abf709c34cb4-PHL + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 13 Nov 2024 23:51:49 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + X-Robots-Tag: + - none + anthropic-ratelimit-requests-limit: + - '4000' + anthropic-ratelimit-requests-remaining: + - '3999' + anthropic-ratelimit-requests-reset: + - '2024-11-13T23:51:47Z' + anthropic-ratelimit-tokens-limit: + - '400000' + anthropic-ratelimit-tokens-remaining: + - '400000' + anthropic-ratelimit-tokens-reset: + - '2024-11-13T23:51:49Z' + request-id: + - req_01QtVfENAkfspCf9KVLM7Emk + via: + - 1.1 google + status: + code: 200 + message: OK +- request: + body: '{"max_tokens": 1024, "messages": [{"role": "user", "content": "Who is the + founder of LangChain?"}, {"role": "assistant", "content": [{"text": "To answer + this question accurately, I''ll need to search for the most up-to-date information + about LangChain and its founder. Let me do that for you.", "type": "text"}, + {"type": "tool_use", "name": "search", "input": {"query": "Who is the founder + of LangChain?"}, "id": "toolu_01Ay6FAm67qxRvHMctedfsdo"}]}, {"role": "user", + "content": [{"type": "tool_result", "content": "[{\"url\": \"https://sfelc.com/speaker/harrison-chase\", + \"content\": \"Harrison Chase is the CEO and co-founder of LangChain, a company + formed around the open source Python/Typescript packages that aim to make it + easy to develop Language Model applications. Prior to starting LangChain, he + led the ML team at Robust Intelligence (an MLOps company focused on testing + and validation of machine learning models), led the\"}, {\"url\": \"https://aiconference.com/speakers/harrison-chase/\", + \"content\": \"Harrison Chase is the co-founder and CEO of LangChain, a company + formed around the open-source Python/Typescript packages that aim to make it + easy to develop Language Model applications. Prior to starting LangChain, he + led the ML team at Robust Intelligence (an MLOps company focused on testing + and validation of machine learning models), led the\"}, {\"url\": \"https://tedai-sanfrancisco.ted.com/speakers-1/harrison-chase-/co-founder-and-ceo,-langchain/\", + \"content\": \"Harrison Chase, a Harvard graduate in statistics and computer + science, co-founded LangChain to streamline the development of Language Model + applications with open-source Python/Typescript packages. Chase''s experience + includes heading the Machine Learning team at Robust Intelligence, focusing + on the testing and validation of machine learning models, and leading the entity + linking team at Kensho\"}, {\"url\": \"https://techcrunch.com/author/harrison-chase/\", + \"content\": \"Harrison Chase is the CEO and co-founder of LangChain, a company + formed around the open source Python/Typescript packages that aim to make it + easy to develop Language Model applications\"}, {\"url\": \"https://www.sequoiacap.com/podcast/training-data-harrison-chase/\", + \"content\": \"Sonya Huang: Hi, and welcome to training data. We have with us + today Harrison Chase, founder and CEO of LangChain. Harrison is a legend in + the agent ecosystem, as the product visionary who first connected LLMs with + tools and actions. And LangChain is the most popular agent building framework + in the AI space.\"}, {\"url\": \"https://www.youtube.com/watch?v=7D8bw_4hTdo\", + \"content\": \"Join us for an insightful interview with Harrison Chase, the + CEO and co-founder of Langchain, as he provides a comprehensive overview of + Langchain''s innovati\"}, {\"url\": \"https://www.forbes.com/profile/harrison-chase/\", + \"content\": \"Harrison Chase only cofounded LangChain in late 2022, but the + company caught instant attention for enabling anyone to build apps powered by + large language models like GPT-4 in as little as two\"}, {\"url\": \"https://en.wikipedia.org/wiki/LangChain\", + \"content\": \"In October 2023 LangChain introduced LangServe, a deployment + tool designed to facilitate the transition from LCEL (LangChain Expression Language) + prototypes to production-ready applications.[5]\\nIntegrations[edit]\\nAs of + March 2023, LangChain included integrations with systems including Amazon, Google, + and Microsoft Azure cloud storage; API wrappers for news, movie information, + and weather; Bash for summarization, syntax and semantics checking, and execution + of shell scripts; multiple web scraping subsystems and templates; few-shot learning + prompt generation support; finding and summarizing \\\"todo\\\" tasks in code; + Google Drive documents, spreadsheets, and presentations summarization, extraction, + and creation; Google Search and Microsoft Bing web search; OpenAI, Anthropic, + and Hugging Face language models; iFixit repair guides and wikis search and + summarization; MapReduce for question answering, combining documents, and question + generation; N-gram overlap scoring; PyPDF, pdfminer, fitz, and pymupdf for PDF + file text extraction and manipulation; Python and JavaScript code generation, + analysis, and debugging; Milvus vector database[6] to store and retrieve vector + embeddings; Weaviate vector database[7] to cache embedding and data objects; + Redis cache database storage; Python RequestsWrapper and other methods for API + requests; SQL and NoSQL databases including JSON support; Streamlit, including + for logging; text mapping for k-nearest neighbors search; time zone conversion + and calendar operations; tracing and recording stack symbols in threaded and + asynchronous subprocess runs; and the Wolfram Alpha website and SDK.[8] As a + language model integration framework, LangChain''s use-cases largely overlap + with those of language models in general, including document analysis and summarization, + chatbots, and code analysis.[2]\\nHistory[edit]\\nLangChain was launched in + October 2022 as an open source project by Harrison Chase, while working at machine + learning startup Robust Intelligence. In April 2023, LangChain had incorporated + and the new startup raised over $20 million in funding at a valuation of at + least $200 million from venture firm Sequoia Capital, a week after announcing + a $10 million seed investment from Benchmark.[3][4]\\n The project quickly garnered + popularity, with improvements from hundreds of contributors on GitHub, trending + discussions on Twitter, lively activity on the project''s Discord server, many + YouTube tutorials, and meetups in San Francisco and London. As of April 2023, + it can read from more than 50 document types and data sources.[9]\\nReferences[edit]\\nExternal + links[edit]\"}, {\"url\": \"https://analyticsindiamag.com/people/harrison-chase/\", + \"content\": \"By AIM The dynamic co-founder and CEO of LangChain, Harrison + Chase is simplifying the creation of applications powered by LLMs. With a background + in statistics and computer science from Harvard University, Chase has carved + a niche in the AI landscape. AIM Brand Solutions, a marketing division within + AIM, specializes in creating diverse content such as documentaries, public artworks, + podcasts, videos, articles, and more to effectively tell compelling stories. + AIM Research produces a series of annual reports on AI & Data Science covering + every aspect of the industry. Discover how Cypher 2024 expands to the USA, bridging + AI innovation gaps and tackling the challenges of enterprise AI adoption AIM + India AIM Research AIM Leaders Council 50 Best Data Science Firms\"}, {\"url\": + \"https://www.turingpost.com/p/harrison-chase-langchain-ai-agents\", \"content\": + \"Harrison Chase, founder of LangChain, shared insights on the evolution of + AI agents and their applications during Sequoia Capital''s AI Ascent. ... Saves + you a lot of research time, plus gives a flashback to ML history and insights + into the future. Stay ahead alongside over 73,000 professionals from top AI + labs, ML startups, and enterprises\"}]", "tool_use_id": "toolu_01Ay6FAm67qxRvHMctedfsdo", + "is_error": false}]}], "model": "claude-3-5-sonnet-20240620", "system": "You + are a helpful AI assistant.\n\nSystem time: 2024-11-13T23:51:14.324904+00:00", + "tools": [{"name": "search", "description": "Search for general web results. + This function performs a search using the Tavily search engine, which is designed\nto + provide comprehensive, accurate, and trusted results. It''s particularly useful\nfor + answering questions about current events.", "input_schema": {"properties": {"query": + {"type": "string"}}, "required": ["query"], "type": "object"}}]}' + headers: {} + method: POST + uri: https://api.anthropic.com/v1/messages + response: + body: + string: !!binary | + H4sIAAAAAAAAA3RVbW/bNhD+KwdiQDZA9lynaQd9a4IWyZBi6dq9AMsQnKmzxJoiFd7RrhD0vw9H + 2Z6XoZ8MUHfH5+3oJ+MaU5ue24fFi9uP169//u2PO/rzarndvXt9+/nt9t3GVEbGgbSKmLElU5kU + vR4gs2PBIKYyfWzIm9pYj7mh2fnsYsYxBJLZcrF8uXi1XJjK2BiEgpj6r6fDUKEv2l5+anOJTA3E + ANIRMGGyHSTi7IUruAGLAWwMa9dQED8CBt5RgjHmBI+ZWFwMgKuYpQxYxxwaShDXcIuhverQhfl9 + uA/XmJLjGOCqQyZw/O1y+BRhRdDHRDAkso6pgu7YY+Ps0Iahgau3vzxrv6ZEgImAY0+woRGG6ILw + HuYzJDrj2Fwr1BdzeKcXoHKrn9cfrz9pAxfAoxAsF8vlHD4VlP2AYYQdMqxj6qkBTNoHcaAw45iT + JbgbpYvhx0/jQB9tcoPAgHaDLTGgKz0CPW5caMEJELKjBBKhoS35OBQEGVuC95oFwGHwzhbcXFRf + zuES7aYtN9f/ao/KaoupgTZhkxX6zkkHCKtjuZJiQXEsznLRSUlloQRsHQVL5Y7zOdwl2rqYGejL + QKl8quGS1uogCyZRAke1ipmemuLme7SdCwS3hClomRD2SvvXuMoscBOEvHetzqwAj7quo82H4GoK + Q1sQbtG7yTgNRb8f7g/Dy8pM0rycw4fs7AbaFHfS1SduPuq5H6FFF6iBIQ7ZY3IyqiQK+s2N4uhz + cDLO4XKEN0NyXt0/r+Czwu5jkI4B16qWEwaPOdiu2id44tBhAwmd0mDXBrd2FoPAOofmwEfjs0Wf + pyjELSX4brlYQO+8d3FarYs53PQDWvlfVh1DQ2yTW2m/2n5vPLU0matQsKUgQDbyyEL9vdGwQucY + 9MHRKqtPit07mFp6ljmG729v3/MPU34kRj9FBe2UwhNZO2RYkdWljIHUH0XQR5aDxBOc2So7XxRY + J+xpF9OGT5TnAffJezWH3x2XJS18zxjaiH6CcrKcrCvDkgh7r3HQQfsN6pX+/vn4xiJVJxuI1hKz + W3kqOiHsnL5DCUNbCO2nUppEWGV2gZipILCJdNHe3MyGuKOkljzf1yPoM4aEg2sgOaYT8i40mSWN + wF3cWdTJ//X8jGFbNCkAtEvzXeD3Q0yCwU7SF6ekmx4YAlVZq4p2vhjtD5pMWzM9yCcK6AW0Xjt9 + C2Ruvv5dGZY4PCRCjsHUhkLzIDkFs//A9Jh1j00dsveVyeW/rX4yLgxZHiRuKLCpl4ufFpWJWU4P + zy8WX7/+AwAA//8DAHBCV3w8BwAA + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 8e22ac0918734cb2-PHL + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 13 Nov 2024 23:51:56 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + X-Robots-Tag: + - none + anthropic-ratelimit-requests-limit: + - '4000' + anthropic-ratelimit-requests-remaining: + - '3999' + anthropic-ratelimit-requests-reset: + - '2024-11-13T23:51:49Z' + anthropic-ratelimit-tokens-limit: + - '400000' + anthropic-ratelimit-tokens-remaining: + - '400000' + anthropic-ratelimit-tokens-reset: + - '2024-11-13T23:51:56Z' + request-id: + - req_01BLNX4GjFRn5bwxxBo3hd3r + via: + - 1.1 google + status: + code: 200 + message: OK +- request: + body: '{"max_tokens": 1024, "messages": [{"role": "user", "content": "Who is the + founder of LangChain?"}], "model": "claude-3-5-sonnet-20240620", "system": "You + are a helpful AI assistant.\n\nSystem time: 2024-11-13T23:51:55.561440+00:00", + "tools": [{"name": "search", "description": "Search for general web results. + This function performs a search using the Tavily search engine, which is designed\nto + provide comprehensive, accurate, and trusted results. It''s particularly useful\nfor + answering questions about current events.", "input_schema": {"properties": {"query": + {"type": "string"}}, "required": ["query"], "type": "object"}}]}' + headers: {} + method: POST + uri: https://api.anthropic.com/v1/messages + response: + body: + string: !!binary | + H4sIAAAAAAAAA1RRS2vbQBD+K8NcclkFxY6dZG+NIaTgXNxgU0oRa2lkCa9mJO1sY2P034vklrSn + YR7fg28uWBdosQmHLL3b0fHwbb85Plb1utsudt8X2+enFRrUc0vjFYXgDoQGe/HjwIVQB3WsaLCR + gjxazL2LBSXzZJEEYSZNZunsPl3OUjSYCyuxov1x+UuqdBrhU7H4LuA4fFAPWtUBukhBa2FweR57 + p+TPBr7eeA9MVIAKBHJ9XkEpI4KgkaAQ20QlKZwS1FxK37grx16iwtrxYVW5msFxAbUGKCVyQf0t + rEmhISgEtHI6cZ4l3uJgPt2K+CyGMYMpuLGPWXr3Rt1m177+enj5svp4OZVv283+tESD7JoRd7U5 + oriNivaCXaT+jBb/qIOUn9ZwGH4aDCpt1pMLwv8rT4tAXSTOCS1H7w3G6TX2clXIVI7EAe39fGlQ + ov47e5oPw28AAAD//wMAEu0ZMPkBAAA= + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 8e22ad0acd1032b3-PHL + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 13 Nov 2024 23:52:33 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + X-Robots-Tag: + - none + anthropic-ratelimit-requests-limit: + - '4000' + anthropic-ratelimit-requests-remaining: + - '3999' + anthropic-ratelimit-requests-reset: + - '2024-11-13T23:52:31Z' + anthropic-ratelimit-tokens-limit: + - '400000' + anthropic-ratelimit-tokens-remaining: + - '400000' + anthropic-ratelimit-tokens-reset: + - '2024-11-13T23:52:33Z' + request-id: + - req_01GSwnbYyFo11udBwAygsuuc + via: + - 1.1 google + status: + code: 200 + message: OK +- request: + body: '{"max_tokens": 1024, "messages": [{"role": "user", "content": "Who is the + founder of LangChain?"}, {"role": "assistant", "content": [{"text": "To answer + this question accurately, I''ll need to search for the most up-to-date information + about LangChain and its founder. Let me do that for you.", "type": "text"}, + {"type": "tool_use", "name": "search", "input": {"query": "founder of LangChain"}, + "id": "toolu_01MeqRWpHv7FACwFxfMVRbx6"}]}, {"role": "user", "content": [{"type": + "tool_result", "content": "[{\"url\": \"https://sfelc.com/speaker/harrison-chase\", + \"content\": \"Harrison Chase is the CEO and co-founder of LangChain, a company + formed around the open source Python/Typescript packages that aim to make it + easy to develop Language Model applications. Prior to starting LangChain, he + led the ML team at Robust Intelligence (an MLOps company focused on testing + and validation of machine learning models), led the\"}, {\"url\": \"https://aiconference.com/speakers/harrison-chase/\", + \"content\": \"Harrison Chase is the co-founder and CEO of LangChain, a company + formed around the open-source Python/Typescript packages that aim to make it + easy to develop Language Model applications. Prior to starting LangChain, he + led the ML team at Robust Intelligence (an MLOps company focused on testing + and validation of machine learning models), led the\"}, {\"url\": \"https://tedai-sanfrancisco.ted.com/speakers-1/harrison-chase-/co-founder-and-ceo,-langchain/\", + \"content\": \"Harrison Chase, a Harvard graduate in statistics and computer + science, co-founded LangChain to streamline the development of Language Model + applications with open-source Python/Typescript packages. Chase''s experience + includes heading the Machine Learning team at Robust Intelligence, focusing + on the testing and validation of machine learning models, and leading the entity + linking team at Kensho\"}, {\"url\": \"https://techcrunch.com/author/harrison-chase/\", + \"content\": \"Harrison Chase is the CEO and co-founder of LangChain, a company + formed around the open source Python/Typescript packages that aim to make it + easy to develop Language Model applications\"}, {\"url\": \"https://www.sequoiacap.com/podcast/training-data-harrison-chase/\", + \"content\": \"Sonya Huang: Hi, and welcome to training data. We have with us + today Harrison Chase, founder and CEO of LangChain. Harrison is a legend in + the agent ecosystem, as the product visionary who first connected LLMs with + tools and actions. And LangChain is the most popular agent building framework + in the AI space.\"}, {\"url\": \"https://www.youtube.com/watch?v=7D8bw_4hTdo\", + \"content\": \"Join us for an insightful interview with Harrison Chase, the + CEO and co-founder of Langchain, as he provides a comprehensive overview of + Langchain''s innovati\"}, {\"url\": \"https://www.forbes.com/profile/harrison-chase/\", + \"content\": \"Harrison Chase only cofounded LangChain in late 2022, but the + company caught instant attention for enabling anyone to build apps powered by + large language models like GPT-4 in as little as two\"}, {\"url\": \"https://en.wikipedia.org/wiki/LangChain\", + \"content\": \"In October 2023 LangChain introduced LangServe, a deployment + tool designed to facilitate the transition from LCEL (LangChain Expression Language) + prototypes to production-ready applications.[5]\\nIntegrations[edit]\\nAs of + March 2023, LangChain included integrations with systems including Amazon, Google, + and Microsoft Azure cloud storage; API wrappers for news, movie information, + and weather; Bash for summarization, syntax and semantics checking, and execution + of shell scripts; multiple web scraping subsystems and templates; few-shot learning + prompt generation support; finding and summarizing \\\"todo\\\" tasks in code; + Google Drive documents, spreadsheets, and presentations summarization, extraction, + and creation; Google Search and Microsoft Bing web search; OpenAI, Anthropic, + and Hugging Face language models; iFixit repair guides and wikis search and + summarization; MapReduce for question answering, combining documents, and question + generation; N-gram overlap scoring; PyPDF, pdfminer, fitz, and pymupdf for PDF + file text extraction and manipulation; Python and JavaScript code generation, + analysis, and debugging; Milvus vector database[6] to store and retrieve vector + embeddings; Weaviate vector database[7] to cache embedding and data objects; + Redis cache database storage; Python RequestsWrapper and other methods for API + requests; SQL and NoSQL databases including JSON support; Streamlit, including + for logging; text mapping for k-nearest neighbors search; time zone conversion + and calendar operations; tracing and recording stack symbols in threaded and + asynchronous subprocess runs; and the Wolfram Alpha website and SDK.[8] As a + language model integration framework, LangChain''s use-cases largely overlap + with those of language models in general, including document analysis and summarization, + chatbots, and code analysis.[2]\\nHistory[edit]\\nLangChain was launched in + October 2022 as an open source project by Harrison Chase, while working at machine + learning startup Robust Intelligence. In April 2023, LangChain had incorporated + and the new startup raised over $20 million in funding at a valuation of at + least $200 million from venture firm Sequoia Capital, a week after announcing + a $10 million seed investment from Benchmark.[3][4]\\n The project quickly garnered + popularity, with improvements from hundreds of contributors on GitHub, trending + discussions on Twitter, lively activity on the project''s Discord server, many + YouTube tutorials, and meetups in San Francisco and London. As of April 2023, + it can read from more than 50 document types and data sources.[9]\\nReferences[edit]\\nExternal + links[edit]\"}, {\"url\": \"https://analyticsindiamag.com/people/harrison-chase/\", + \"content\": \"By AIM The dynamic co-founder and CEO of LangChain, Harrison + Chase is simplifying the creation of applications powered by LLMs. With a background + in statistics and computer science from Harvard University, Chase has carved + a niche in the AI landscape. AIM Brand Solutions, a marketing division within + AIM, specializes in creating diverse content such as documentaries, public artworks, + podcasts, videos, articles, and more to effectively tell compelling stories. + AIM Research produces a series of annual reports on AI & Data Science covering + every aspect of the industry. Discover how Cypher 2024 expands to the USA, bridging + AI innovation gaps and tackling the challenges of enterprise AI adoption AIM + India AIM Research AIM Leaders Council 50 Best Data Science Firms\"}, {\"url\": + \"https://www.turingpost.com/p/harrison-chase-langchain-ai-agents\", \"content\": + \"Harrison Chase, founder of LangChain, shared insights on the evolution of + AI agents and their applications during Sequoia Capital''s AI Ascent. ... Saves + you a lot of research time, plus gives a flashback to ML history and insights + into the future. Stay ahead alongside over 73,000 professionals from top AI + labs, ML startups, and enterprises\"}]", "tool_use_id": "toolu_01MeqRWpHv7FACwFxfMVRbx6", + "is_error": false}]}], "model": "claude-3-5-sonnet-20240620", "system": "You + are a helpful AI assistant.\n\nSystem time: 2024-11-13T23:51:58.213993+00:00", + "tools": [{"name": "search", "description": "Search for general web results. + This function performs a search using the Tavily search engine, which is designed\nto + provide comprehensive, accurate, and trusted results. It''s particularly useful\nfor + answering questions about current events.", "input_schema": {"properties": {"query": + {"type": "string"}}, "required": ["query"], "type": "object"}}]}' + headers: {} + method: POST + uri: https://api.anthropic.com/v1/messages + response: + body: + string: !!binary | + H4sIAAAAAAAAA3RU0W7cNhD8lQWfWkCnXs6Jg96bY7SIURtxE/epVxh71EraHLWUyeW5guF/L1Z3 + bmynfRJEcmdmZ4d8cNy4tRtyd7t8c/3b5erns7yKfHp18iXSr1+73zO7yuk0kp2inLEjV7kUgy1g + zpwVRV3lhthQcGvnA5aGFieLd4scRUgXq+Xq7fJ0tXSV81GURN36z4cnUKW/rXz+rN0HzNRAFNCe + IBMm30OiXILmCi7Ao8CY4p4bgikWuGftAb0vCZWApY1pQOUogNtYdEZpY5GGEsQWLlG68x5Z1hvZ + yM3/bAJn+IgpcY4C5z1mquEqJoI8kueWPYYwzQhv6lcHrdQ4fVw8IaM0cP7LpxcM9UZWNXx8om+e + cwsE62W1XK2qufiAN4woE9wV9rswQYcs1ACquWnttjEBawYWiXtU3hPgOKaIvgeNcHYBDe0pxHEg + 0XojJ/Uzznu0Qla2xiBgEd8begYUiCPJIseSPJn1X8mrifzkNW4pzTrhvudAr60w1PuYdiwdoALC + gL5nIQiESWw1KyYtI5ih1MDnuC1Z4UKUQuCOxFO9kbf1Ea83PbBFv+uS2WYqsqJyVvZ5tspsKkoJ + smcrhzbFwXTtMTXwh/CeUmad6o28q+E6cUzmzqzDBP1rSQW96TyYf3XUffmkWwkHa+k/BFfmhe+h + jb48JZnyDG4C9xi4OQQ0tt8bMt+hXFu0vk0HecimcsAdASsQ5sn+jwOdRRfsCK6s2sYe2M8clsUU + S9e/GOL1pH2Un26mkbJPPCqM6HfYUa7h5lnWzO9jzjJ3MgdfFDShnxvgwyU9u7CKoQjrNPdodYk8 + 8d4qy3Z+IBgDtEUa63Ieyp5ESyLwOLLaJqchQ+AdwRe6K5ERzo9bBvqBxPcDpt1szveXzkfJ3FCy + 2IJExW0gaLkzim9Cycc8ZaWhgtFG7kvAFKb59vR8iKsd9/Zw+WMkUkevPM7ww+XlVf7x8PxojOEQ + v4MxubJRvYgTIIxxNDJoEw408xjptnCYPTm7AOxINNfu8a/KZY3jbSLMUdzakTS3WpK440amu2Jh + c2spIVSuzK/y+sGxjEVvNe5Isluvlu9PKxeLvlh8f/L4+A8AAAD//wMAo1MaSPYFAAA= + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 8e22ad1b7c4d4cb1-PHL + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 13 Nov 2024 23:52:39 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + X-Robots-Tag: + - none + anthropic-ratelimit-requests-limit: + - '4000' + anthropic-ratelimit-requests-remaining: + - '3999' + anthropic-ratelimit-requests-reset: + - '2024-11-13T23:52:33Z' + anthropic-ratelimit-tokens-limit: + - '400000' + anthropic-ratelimit-tokens-remaining: + - '400000' + anthropic-ratelimit-tokens-reset: + - '2024-11-13T23:52:39Z' + request-id: + - req_01E8yQY8oXhidTwTxeWKdjiW + via: + - 1.1 google + status: + code: 200 + message: OK +- request: + body: '{"max_tokens": 1024, "messages": [{"role": "user", "content": "Who is the + founder of LangChain?"}], "model": "claude-3-5-sonnet-20240620", "system": "You + are a helpful AI assistant.\n\nSystem time: 2024-11-13T23:52:42.318107+00:00", + "tools": [{"name": "search", "description": "Search for general web results. + This function performs a search using the Tavily search engine, which is designed\nto + provide comprehensive, accurate, and trusted results. It''s particularly useful\nfor + answering questions about current events.", "input_schema": {"properties": {"query": + {"type": "string"}}, "required": ["query"], "type": "object"}}]}' + headers: {} + method: POST + uri: https://api.anthropic.com/v1/messages + response: + body: + string: !!binary | + H4sIAAAAAAAAA1SRXWvbUAyG/4rQzW6Oi5O2SeObQgspgzBW2tLBGObUVuJDbSk50mkSgv/7sLPR + 7Uro4331IJ0w1Fhgp5syn9w8r252+7iY3YfV9+nbkibd+8ccHdpxS8MUqfoNocMo7VDwqkHNs6HD + TmpqscCq9amm7DK7zlSYybJpPr3KZ9McHVbCRmxY/Dz9NTU6DPIxFPgs4Fn3FMGaoLBLpBaEwVdV + it6oPTr4+qVtgYlqMAElH6sG1jIoCDpRg7TNTLLaG0HgtcTOnz3eJBmsPG/uGx8YPNcQTGEtiWuK + F7Aig46gFrDG2+h5lHSBvfukFWnLpMMNxsMNeSrzyeQ1/rh7OsQFx2931/v54+HhZblEh+y7QXfG + HFS8TYbFCXeJ4hELfG0Ego7wf0BA1p+Ut9j3vxyqybaM5FX4f4qxobRLxBVhwaltHabxTcXpvK00 + eSdWLK4uZw4l2b+1xbzvfwMAAP//AwB9NM36BQIAAA== + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 8e22ae2f5dec4cb6-PHL + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 13 Nov 2024 23:53:20 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + X-Robots-Tag: + - none + anthropic-ratelimit-requests-limit: + - '4000' + anthropic-ratelimit-requests-remaining: + - '3999' + anthropic-ratelimit-requests-reset: + - '2024-11-13T23:53:18Z' + anthropic-ratelimit-tokens-limit: + - '400000' + anthropic-ratelimit-tokens-remaining: + - '400000' + anthropic-ratelimit-tokens-reset: + - '2024-11-13T23:53:20Z' + request-id: + - req_01DsVqmPigsQsHqctV3yYFQ5 + via: + - 1.1 google + status: + code: 200 + message: OK +- request: + body: '{"max_tokens": 1024, "messages": [{"role": "user", "content": "Who is the + founder of LangChain?"}, {"role": "assistant", "content": [{"text": "To answer + this question accurately, I''ll need to search for the most up-to-date information + about LangChain and its founder. Let me do that for you.", "type": "text"}, + {"type": "tool_use", "name": "search", "input": {"query": "Who is the founder + of LangChain?"}, "id": "toolu_011WrXBSxr9nrNB5w7QxGUFF"}]}, {"role": "user", + "content": [{"type": "tool_result", "content": "[{\"url\": \"https://sfelc.com/speaker/harrison-chase\", + \"content\": \"Harrison Chase is the CEO and co-founder of LangChain, a company + formed around the open source Python/Typescript packages that aim to make it + easy to develop Language Model applications. Prior to starting LangChain, he + led the ML team at Robust Intelligence (an MLOps company focused on testing + and validation of machine learning models), led the\"}, {\"url\": \"https://aiconference.com/speakers/harrison-chase/\", + \"content\": \"Harrison Chase is the co-founder and CEO of LangChain, a company + formed around the open-source Python/Typescript packages that aim to make it + easy to develop Language Model applications. Prior to starting LangChain, he + led the ML team at Robust Intelligence (an MLOps company focused on testing + and validation of machine learning models), led the\"}, {\"url\": \"https://tedai-sanfrancisco.ted.com/speakers-1/harrison-chase-/co-founder-and-ceo,-langchain/\", + \"content\": \"Harrison Chase, a Harvard graduate in statistics and computer + science, co-founded LangChain to streamline the development of Language Model + applications with open-source Python/Typescript packages. Chase''s experience + includes heading the Machine Learning team at Robust Intelligence, focusing + on the testing and validation of machine learning models, and leading the entity + linking team at Kensho\"}, {\"url\": \"https://techcrunch.com/author/harrison-chase/\", + \"content\": \"Harrison Chase is the CEO and co-founder of LangChain, a company + formed around the open source Python/Typescript packages that aim to make it + easy to develop Language Model applications\"}, {\"url\": \"https://www.sequoiacap.com/podcast/training-data-harrison-chase/\", + \"content\": \"Sonya Huang: Hi, and welcome to training data. We have with us + today Harrison Chase, founder and CEO of LangChain. Harrison is a legend in + the agent ecosystem, as the product visionary who first connected LLMs with + tools and actions. And LangChain is the most popular agent building framework + in the AI space.\"}, {\"url\": \"https://www.youtube.com/watch?v=7D8bw_4hTdo\", + \"content\": \"Join us for an insightful interview with Harrison Chase, the + CEO and co-founder of Langchain, as he provides a comprehensive overview of + Langchain''s innovati\"}, {\"url\": \"https://www.forbes.com/profile/harrison-chase/\", + \"content\": \"Harrison Chase only cofounded LangChain in late 2022, but the + company caught instant attention for enabling anyone to build apps powered by + large language models like GPT-4 in as little as two\"}, {\"url\": \"https://en.wikipedia.org/wiki/LangChain\", + \"content\": \"In October 2023 LangChain introduced LangServe, a deployment + tool designed to facilitate the transition from LCEL (LangChain Expression Language) + prototypes to production-ready applications.[5]\\nIntegrations[edit]\\nAs of + March 2023, LangChain included integrations with systems including Amazon, Google, + and Microsoft Azure cloud storage; API wrappers for news, movie information, + and weather; Bash for summarization, syntax and semantics checking, and execution + of shell scripts; multiple web scraping subsystems and templates; few-shot learning + prompt generation support; finding and summarizing \\\"todo\\\" tasks in code; + Google Drive documents, spreadsheets, and presentations summarization, extraction, + and creation; Google Search and Microsoft Bing web search; OpenAI, Anthropic, + and Hugging Face language models; iFixit repair guides and wikis search and + summarization; MapReduce for question answering, combining documents, and question + generation; N-gram overlap scoring; PyPDF, pdfminer, fitz, and pymupdf for PDF + file text extraction and manipulation; Python and JavaScript code generation, + analysis, and debugging; Milvus vector database[6] to store and retrieve vector + embeddings; Weaviate vector database[7] to cache embedding and data objects; + Redis cache database storage; Python RequestsWrapper and other methods for API + requests; SQL and NoSQL databases including JSON support; Streamlit, including + for logging; text mapping for k-nearest neighbors search; time zone conversion + and calendar operations; tracing and recording stack symbols in threaded and + asynchronous subprocess runs; and the Wolfram Alpha website and SDK.[8] As a + language model integration framework, LangChain''s use-cases largely overlap + with those of language models in general, including document analysis and summarization, + chatbots, and code analysis.[2]\\nHistory[edit]\\nLangChain was launched in + October 2022 as an open source project by Harrison Chase, while working at machine + learning startup Robust Intelligence. In April 2023, LangChain had incorporated + and the new startup raised over $20 million in funding at a valuation of at + least $200 million from venture firm Sequoia Capital, a week after announcing + a $10 million seed investment from Benchmark.[3][4]\\n The project quickly garnered + popularity, with improvements from hundreds of contributors on GitHub, trending + discussions on Twitter, lively activity on the project''s Discord server, many + YouTube tutorials, and meetups in San Francisco and London. As of April 2023, + it can read from more than 50 document types and data sources.[9]\\nReferences[edit]\\nExternal + links[edit]\"}, {\"url\": \"https://analyticsindiamag.com/people/harrison-chase/\", + \"content\": \"By AIM The dynamic co-founder and CEO of LangChain, Harrison + Chase is simplifying the creation of applications powered by LLMs. With a background + in statistics and computer science from Harvard University, Chase has carved + a niche in the AI landscape. AIM Brand Solutions, a marketing division within + AIM, specializes in creating diverse content such as documentaries, public artworks, + podcasts, videos, articles, and more to effectively tell compelling stories. + AIM Research produces a series of annual reports on AI & Data Science covering + every aspect of the industry. Discover how Cypher 2024 expands to the USA, bridging + AI innovation gaps and tackling the challenges of enterprise AI adoption AIM + India AIM Research AIM Leaders Council 50 Best Data Science Firms\"}, {\"url\": + \"https://www.turingpost.com/p/harrison-chase-langchain-ai-agents\", \"content\": + \"Harrison Chase, founder of LangChain, shared insights on the evolution of + AI agents and their applications during Sequoia Capital''s AI Ascent. ... Saves + you a lot of research time, plus gives a flashback to ML history and insights + into the future. Stay ahead alongside over 73,000 professionals from top AI + labs, ML startups, and enterprises\"}]", "tool_use_id": "toolu_011WrXBSxr9nrNB5w7QxGUFF", + "is_error": false}]}], "model": "claude-3-5-sonnet-20240620", "system": "You + are a helpful AI assistant.\n\nSystem time: 2024-11-13T23:52:45.186170+00:00", + "tools": [{"name": "search", "description": "Search for general web results. + This function performs a search using the Tavily search engine, which is designed\nto + provide comprehensive, accurate, and trusted results. It''s particularly useful\nfor + answering questions about current events.", "input_schema": {"properties": {"query": + {"type": "string"}}, "required": ["query"], "type": "object"}}]}' + headers: {} + method: POST + uri: https://api.anthropic.com/v1/messages + response: + body: + string: !!binary | + H4sIAAAAAAAAA2RV0W4bRwz8FWIRoC1wUhXZSdp7i402NuCgbpunNoVB7VF3jPZ210uuHNXIvxc8 + SbGcPgnYI4fDIYd6dNy51o3S3y1e3sa/7h/ecL6X128+XXU3//rxLJ27xukuk0WRCPbkGldSsAcU + YVGM6ho3po6Ca50PWDuanc1ezSTFSDpbLpbni9fLhWucT1Epqmv/fjyCKn229OmndRco1EGKoAOB + EBY/QCGpQaWBa/AYIZe05Y5glyo8sA6A3teCSsBxncqIyikCrlLVCWWdauyoQFrDDcb+ckCO7cf4 + MV5hKSwpwuWAQsDyLBxjB5e//PYsbQ5XVAiwEEgaCTa0g5w4qhzqfQNpGM9rvpzDZZodarTfxvvj + p5M04AjBulsulsu5YSzncIF+0xcLbZ/Yo8FtsXTQF+yq5ez1gdXXcEMTRWVR9jIR9GnMVamAeKbo + aapxZjzHjHEH6+SrtKeErJQ/fF1VDgq4B0+Z4kxSLZ7gdqdDij9+2GUSXzgrZPQb7MlkRgXkETTB + iBsCViAUpmIvHW0ppDwVrNgTvLfNAsw5sJ+GKxPF8zncFtpyqgL0OVOZ2LdwQetkA1IsyrF/It48 + yR2om4b9Hv3AkeCGsEQLVsIRUOGPtKqicB2VQuDekJuTridNDotKMpUxKbcYuNvvX1rDeAAPR/DJ + Invyr+bwe2W/gb6kBx1O5b2397CDHjlSBznlGrCw7mx2RvrttfEYa2TdNfsRm68Kr+qkDqxLGmGo + sSvUiTE5SEpFjPE71qu6mgijV94SdCy+ikzJKcIWy6RqDqjmqD3l13P4tcaOY9/CdYS3uXCwpTxr + 4JNpNaaogwCubZdYBQLW6IfmpLWCPKm2pQIvlgsYOQQTiyOs99CmPZqO9auMqKagqGU8pUw9bilq + LQRrLiP8Sfc1McIlZlYMc/gwsIDHkUCGVDTsDtwQXrx8AhIic8WWREeKuge+oOiHEctm6vzNHK7H + jF7/Z1grkKJwR4U6QBDuI6/ZowFxb9yehoa94ZNPshOlsYFsG+ptusFWqoARttNqSd6Opz9scOnp + Gz8IfH9z815+2M9fUwrydaJHh5xs/v6mPWf/nZiwHRUZODcwoMCKvN21FMmUN95jEj3u4L6DmVl+ + mtW64EgPqWzkpEvJaF6hiKtgQSe7pwl8IbtLp2aGnB4m+VY7CFOn4djp3jAQeEPw7vbD7BxGs7bd + Cptm7I5mmbsv/zRONOW7QigputZR7O60lugOH4Tuq/nYtbGG0Lg6/Ze1j45jrnqnaUNRXLtc/LRo + XKp6+nh2/vOXL/8BAAD//wMABqZyviwHAAA= + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 8e22ae419e4532cc-PHL + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 13 Nov 2024 23:53:26 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + X-Robots-Tag: + - none + anthropic-ratelimit-requests-limit: + - '4000' + anthropic-ratelimit-requests-remaining: + - '3999' + anthropic-ratelimit-requests-reset: + - '2024-11-13T23:53:20Z' + anthropic-ratelimit-tokens-limit: + - '400000' + anthropic-ratelimit-tokens-remaining: + - '400000' + anthropic-ratelimit-tokens-reset: + - '2024-11-13T23:53:26Z' + request-id: + - req_01B7UWY6NpA4GBZ9DRu9YWdS + via: + - 1.1 google + status: + code: 200 + message: OK +- request: + body: '{"max_tokens": 1024, "messages": [{"role": "user", "content": "Who is the + founder of LangChain?"}], "model": "claude-3-5-sonnet-20240620", "system": "You + are a helpful AI assistant.\n\nSystem time: 2024-11-13T23:53:11.070630+00:00", + "tools": [{"name": "search", "description": "Search for general web results. + This function performs a search using the Tavily search engine, which is designed\nto + provide comprehensive, accurate, and trusted results. It''s particularly useful\nfor + answering questions about current events.", "input_schema": {"properties": {"query": + {"type": "string"}}, "required": ["query"], "type": "object"}}]}' + headers: {} + method: POST + uri: https://api.anthropic.com/v1/messages + response: + body: + string: !!binary | + H4sIAAAAAAAAA1SRXWvbUAyG/4rQzW6Oi5ukKfPN2AalLWWMURhlDHPso8RebSk+0qHxgv/7sNPR + 7Uro4331IJ2wDVhgr/syv/x6fwxfwup5qId6M1zfbNpqPX5DhzYeaJ4iVb8ndBilmwtetVXzbOiw + l0AdFlh3PgXK1tlVpsJMlq3y1SbfrnJ0WAsbsWHx4/TX1Og4y5dQ4KOAZ32hCNa0CkMitVYYfF2n + 6I260cHdu64DJgpgAko+1g3sZFYQ9KIG6ZCZZMEbQcs7ib0/e1SSDB487z83vmXwHKA1hZ0kDhQv + 4IEMeoIgYI23xXOUdIGTe6MV6cqk8w2Ww815KvPLq5tfcnza7l+q6uNtHKqnT4/H3yM6ZN/PujPm + rOJDMixOOCSKIxb4vRFodYF/BQHZvVF+wGn66VBNDmUkr8L/UywNpSER14QFp65zmJY3FafzttLk + mVix2Ky3DiXZv7X319P0BwAA//8DAHnV818FAgAA + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 8e22aee2bec36992-PHL + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 13 Nov 2024 23:53:48 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + X-Robots-Tag: + - none + anthropic-ratelimit-requests-limit: + - '4000' + anthropic-ratelimit-requests-remaining: + - '3999' + anthropic-ratelimit-requests-reset: + - '2024-11-13T23:53:46Z' + anthropic-ratelimit-tokens-limit: + - '400000' + anthropic-ratelimit-tokens-remaining: + - '400000' + anthropic-ratelimit-tokens-reset: + - '2024-11-13T23:53:48Z' + request-id: + - req_01Jk8NvFFDybK94i9Qz4cRk5 + via: + - 1.1 google + status: + code: 200 + message: OK +- request: + body: '{"max_tokens": 1024, "messages": [{"role": "user", "content": "Who is the + founder of LangChain?"}, {"role": "assistant", "content": [{"text": "To answer + this question accurately, I''ll need to search for the most up-to-date information + about LangChain and its founder. Let me do that for you.", "type": "text"}, + {"type": "tool_use", "name": "search", "input": {"query": "Who is the founder + of LangChain?"}, "id": "toolu_015FjoxY6gwbbAHrqbYBTxzy"}]}, {"role": "user", + "content": [{"type": "tool_result", "content": "[{\"url\": \"https://sfelc.com/speaker/harrison-chase\", + \"content\": \"Harrison Chase is the CEO and co-founder of LangChain, a company + formed around the open source Python/Typescript packages that aim to make it + easy to develop Language Model applications. Prior to starting LangChain, he + led the ML team at Robust Intelligence (an MLOps company focused on testing + and validation of machine learning models), led the\"}, {\"url\": \"https://aiconference.com/speakers/harrison-chase/\", + \"content\": \"Harrison Chase is the co-founder and CEO of LangChain, a company + formed around the open-source Python/Typescript packages that aim to make it + easy to develop Language Model applications. Prior to starting LangChain, he + led the ML team at Robust Intelligence (an MLOps company focused on testing + and validation of machine learning models), led the\"}, {\"url\": \"https://tedai-sanfrancisco.ted.com/speakers-1/harrison-chase-/co-founder-and-ceo,-langchain/\", + \"content\": \"Harrison Chase, a Harvard graduate in statistics and computer + science, co-founded LangChain to streamline the development of Language Model + applications with open-source Python/Typescript packages. Chase''s experience + includes heading the Machine Learning team at Robust Intelligence, focusing + on the testing and validation of machine learning models, and leading the entity + linking team at Kensho\"}, {\"url\": \"https://techcrunch.com/author/harrison-chase/\", + \"content\": \"Harrison Chase is the CEO and co-founder of LangChain, a company + formed around the open source Python/Typescript packages that aim to make it + easy to develop Language Model applications\"}, {\"url\": \"https://www.sequoiacap.com/podcast/training-data-harrison-chase/\", + \"content\": \"Sonya Huang: Hi, and welcome to training data. We have with us + today Harrison Chase, founder and CEO of LangChain. Harrison is a legend in + the agent ecosystem, as the product visionary who first connected LLMs with + tools and actions. And LangChain is the most popular agent building framework + in the AI space.\"}, {\"url\": \"https://www.youtube.com/watch?v=7D8bw_4hTdo\", + \"content\": \"Join us for an insightful interview with Harrison Chase, the + CEO and co-founder of Langchain, as he provides a comprehensive overview of + Langchain''s innovati\"}, {\"url\": \"https://www.forbes.com/profile/harrison-chase/\", + \"content\": \"Harrison Chase only cofounded LangChain in late 2022, but the + company caught instant attention for enabling anyone to build apps powered by + large language models like GPT-4 in as little as two\"}, {\"url\": \"https://en.wikipedia.org/wiki/LangChain\", + \"content\": \"In October 2023 LangChain introduced LangServe, a deployment + tool designed to facilitate the transition from LCEL (LangChain Expression Language) + prototypes to production-ready applications.[5]\\nIntegrations[edit]\\nAs of + March 2023, LangChain included integrations with systems including Amazon, Google, + and Microsoft Azure cloud storage; API wrappers for news, movie information, + and weather; Bash for summarization, syntax and semantics checking, and execution + of shell scripts; multiple web scraping subsystems and templates; few-shot learning + prompt generation support; finding and summarizing \\\"todo\\\" tasks in code; + Google Drive documents, spreadsheets, and presentations summarization, extraction, + and creation; Google Search and Microsoft Bing web search; OpenAI, Anthropic, + and Hugging Face language models; iFixit repair guides and wikis search and + summarization; MapReduce for question answering, combining documents, and question + generation; N-gram overlap scoring; PyPDF, pdfminer, fitz, and pymupdf for PDF + file text extraction and manipulation; Python and JavaScript code generation, + analysis, and debugging; Milvus vector database[6] to store and retrieve vector + embeddings; Weaviate vector database[7] to cache embedding and data objects; + Redis cache database storage; Python RequestsWrapper and other methods for API + requests; SQL and NoSQL databases including JSON support; Streamlit, including + for logging; text mapping for k-nearest neighbors search; time zone conversion + and calendar operations; tracing and recording stack symbols in threaded and + asynchronous subprocess runs; and the Wolfram Alpha website and SDK.[8] As a + language model integration framework, LangChain''s use-cases largely overlap + with those of language models in general, including document analysis and summarization, + chatbots, and code analysis.[2]\\nHistory[edit]\\nLangChain was launched in + October 2022 as an open source project by Harrison Chase, while working at machine + learning startup Robust Intelligence. In April 2023, LangChain had incorporated + and the new startup raised over $20 million in funding at a valuation of at + least $200 million from venture firm Sequoia Capital, a week after announcing + a $10 million seed investment from Benchmark.[3][4]\\n The project quickly garnered + popularity, with improvements from hundreds of contributors on GitHub, trending + discussions on Twitter, lively activity on the project''s Discord server, many + YouTube tutorials, and meetups in San Francisco and London. As of April 2023, + it can read from more than 50 document types and data sources.[9]\\nReferences[edit]\\nExternal + links[edit]\"}, {\"url\": \"https://analyticsindiamag.com/people/harrison-chase/\", + \"content\": \"By AIM The dynamic co-founder and CEO of LangChain, Harrison + Chase is simplifying the creation of applications powered by LLMs. With a background + in statistics and computer science from Harvard University, Chase has carved + a niche in the AI landscape. AIM Brand Solutions, a marketing division within + AIM, specializes in creating diverse content such as documentaries, public artworks, + podcasts, videos, articles, and more to effectively tell compelling stories. + AIM Research produces a series of annual reports on AI & Data Science covering + every aspect of the industry. Discover how Cypher 2024 expands to the USA, bridging + AI innovation gaps and tackling the challenges of enterprise AI adoption AIM + India AIM Research AIM Leaders Council 50 Best Data Science Firms\"}, {\"url\": + \"https://www.turingpost.com/p/harrison-chase-langchain-ai-agents\", \"content\": + \"Harrison Chase, founder of LangChain, shared insights on the evolution of + AI agents and their applications during Sequoia Capital''s AI Ascent. ... Saves + you a lot of research time, plus gives a flashback to ML history and insights + into the future. Stay ahead alongside over 73,000 professionals from top AI + labs, ML startups, and enterprises\"}]", "tool_use_id": "toolu_015FjoxY6gwbbAHrqbYBTxzy", + "is_error": false}]}], "model": "claude-3-5-sonnet-20240620", "system": "You + are a helpful AI assistant.\n\nSystem time: 2024-11-13T23:53:13.741829+00:00", + "tools": [{"name": "search", "description": "Search for general web results. + This function performs a search using the Tavily search engine, which is designed\nto + provide comprehensive, accurate, and trusted results. It''s particularly useful\nfor + answering questions about current events.", "input_schema": {"properties": {"query": + {"type": "string"}}, "required": ["query"], "type": "object"}}]}' + headers: {} + method: POST + uri: https://api.anthropic.com/v1/messages + response: + body: + string: !!binary | + H4sIAAAAAAAAA3RUYW8bNwz9K4RQYBtw9mynKTp/a4NhyZagxZYOGNYhoHW8O8068ipKzg5B/vtA + xUHdDvtkQ0e+9/j4pAcXWrd1o/Z3q/X58JrO1r+vf54vflnvfvpjg+v1+aVrXJ4nsipSxZ5c45JE + O0DVoBk5u8aN0lJ0W+cjlpYWZ4vzhQoz5cVmtXm5erVZucZ54Uyc3fbPh2fQTP9Ye/3Zureo1IIw + 5IFACZMfIJGWmLWBK/DIMCU5hJZglgL3IQ+1NHAnacQchAF3UnI97aRwSwmkg2vk/mLAwNuP/JFv + /+cjBIVLTCmoMFwMqLSEG0kEOpEPXfAY41wR1suvCq3VOL0snpGRW7j48d0XDEtr3izh8llAe8rO + EDETbFabzRJuK9o4Ic9wjwrSdcEHUwARC/uBWkAFZJCJeKFSkiez52/y2bDe+Sw7Sk9wxnu2hPcp + SIIsoBlTDtx/pm++nuhe0t44MiCM6IfABJEwsbXV/jKBWUIt/Cq7ohmuOFOMoSf21MD9QIlgsK62 + mnNzDZlwrGJeLo80gw0BO/T7PpklJl0z5qA5eK0umg0lUwL1waChSzKa3AOmFj5wOFDSkOcKfL48 + sfRTCX4fZ+gxMLUwyVQippBnYzFJb64MfSwc8txUst0Mb6YUovl21hyX+rSGAVtIGCyjGnquieAM + XeE2cF9XNoOSL8lSfKAELzYrGEOMFszAz5VPnh4wlqfISmcnkVCzdXxuqXP+Rp+KBIQLnELG2EAn + Mcp9xYEX68/VSmTuHUjzSKbLut8S+2HEtK/mvFrChxrO6v03aqQtJR3C1JzYZjvZkZeRQJhMn9kw + iuZnCwF74rzYlRDrRF3CkSwxeuKsTmg56MQXtSJhGHFv/0IGQp0tiS0dKMpU2Qv2BDf2lABOUwy+ + +qNwbD/J+fs5D8Lf384TqU9hyjCh32NPWuf87+X0whpass3gl9sLfUl0opq86KyZxgYmuyTe5o0z + dJJgCFrvhZV7e9/88RKlnr6aQOHb6+sb/e74SonEpzCjrzPZ9Qh+OFpNFo8uFuIcMD6LOVpTlymd + aauuH3FODFq6x78ap1mmu0Sowm7riNu7XBK74welT8Uuj9tyibFxpT7m2wcXeCr5LsueWN12s3q9 + apyU/MXhD68fH/8FAAD//wMA0hFTIS0GAAA= + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 8e22aef3a88e32c6-PHL + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 13 Nov 2024 23:53:54 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + X-Robots-Tag: + - none + anthropic-ratelimit-requests-limit: + - '4000' + anthropic-ratelimit-requests-remaining: + - '3999' + anthropic-ratelimit-requests-reset: + - '2024-11-13T23:53:49Z' + anthropic-ratelimit-tokens-limit: + - '400000' + anthropic-ratelimit-tokens-remaining: + - '400000' + anthropic-ratelimit-tokens-reset: + - '2024-11-13T23:53:54Z' + request-id: + - req_01HxWKuEjZTokR87xSj3FNGK + via: + - 1.1 google + status: + code: 200 + message: OK +- request: + body: '{"max_tokens": 1024, "messages": [{"role": "user", "content": "Who is the + founder of LangChain?"}], "model": "claude-3-5-sonnet-20240620", "system": "You + are a helpful AI assistant.\n\nSystem time: 2024-11-13T23:54:04.768568+00:00", + "tools": [{"name": "search", "description": "Search for general web results. + This function performs a search using the Tavily search engine, which is designed\nto + provide comprehensive, accurate, and trusted results. It''s particularly useful\nfor + answering questions about current events.", "input_schema": {"properties": {"query": + {"type": "string"}}, "required": ["query"], "type": "object"}}]}' + headers: {} + method: POST + uri: https://api.anthropic.com/v1/messages + response: + body: + string: !!binary | + H4sIAAAAAAAAA1RRW0/bUAz+K5Zf9nKCQluYdt42hLisSIUxBJpQdEjcNuPEbmMfrVGV/46SbmI8 + Wb58F33eY12hx0ZXRX789fP5nV3Wi+ty3j38/P14Kbtvtzt0aN2GhitSDStCh63EYRBUa7XAhg4b + qSiixzKGVFE2zU4yFWaybJJPZvnpJEeHpbARG/pf+3+kRrsBPhaP9wKB9Q+1YOtaYZtIrRaGUJap + DUaxc3D1KUZgogpMQCm05RqWMiAIGlGDtMlMsioYQc1LaZtw4HiRZDAPvDpbh5ohcAW1KSwlcUXt + EczJoCGoBGwdbOTsJB1h797disQi6ZDBGNzQpyI/nun317Pbxd3DzeLx4ub6/iKdPP1o0CGHZsAd + bA4o3iRDv8dtorZDj3/VQZbv1rDvnx2qyaZoKajwR+VxobRNxCWh5xSjwzS+xu8PCoXJK7Gin01P + HUqy/2dfpn3/BgAA//8DABCOjgv5AQAA + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 8e22b0325b034cb6-PHL + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 13 Nov 2024 23:54:42 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + X-Robots-Tag: + - none + anthropic-ratelimit-requests-limit: + - '4000' + anthropic-ratelimit-requests-remaining: + - '3999' + anthropic-ratelimit-requests-reset: + - '2024-11-13T23:54:40Z' + anthropic-ratelimit-tokens-limit: + - '400000' + anthropic-ratelimit-tokens-remaining: + - '400000' + anthropic-ratelimit-tokens-reset: + - '2024-11-13T23:54:42Z' + request-id: + - req_01SsSvCQgy3vQfuMCiJiaZLM + via: + - 1.1 google + status: + code: 200 + message: OK +- request: + body: '{"max_tokens": 1024, "messages": [{"role": "user", "content": "Who is the + founder of LangChain?"}, {"role": "assistant", "content": [{"text": "To answer + this question accurately, I''ll need to search for the most up-to-date information + about LangChain and its founder. Let me do that for you.", "type": "text"}, + {"type": "tool_use", "name": "search", "input": {"query": "founder of LangChain"}, + "id": "toolu_014sKkCQPRVMPXGMJTGu5YSm"}]}, {"role": "user", "content": [{"type": + "tool_result", "content": "[{\"url\": \"https://sfelc.com/speaker/harrison-chase\", + \"content\": \"Harrison Chase is the CEO and co-founder of LangChain, a company + formed around the open source Python/Typescript packages that aim to make it + easy to develop Language Model applications. Prior to starting LangChain, he + led the ML team at Robust Intelligence (an MLOps company focused on testing + and validation of machine learning models), led the\"}, {\"url\": \"https://aiconference.com/speakers/harrison-chase/\", + \"content\": \"Harrison Chase is the co-founder and CEO of LangChain, a company + formed around the open-source Python/Typescript packages that aim to make it + easy to develop Language Model applications. Prior to starting LangChain, he + led the ML team at Robust Intelligence (an MLOps company focused on testing + and validation of machine learning models), led the\"}, {\"url\": \"https://tedai-sanfrancisco.ted.com/speakers-1/harrison-chase-/co-founder-and-ceo,-langchain/\", + \"content\": \"Harrison Chase, a Harvard graduate in statistics and computer + science, co-founded LangChain to streamline the development of Language Model + applications with open-source Python/Typescript packages. Chase''s experience + includes heading the Machine Learning team at Robust Intelligence, focusing + on the testing and validation of machine learning models, and leading the entity + linking team at Kensho\"}, {\"url\": \"https://techcrunch.com/author/harrison-chase/\", + \"content\": \"Harrison Chase is the CEO and co-founder of LangChain, a company + formed around the open source Python/Typescript packages that aim to make it + easy to develop Language Model applications\"}, {\"url\": \"https://www.sequoiacap.com/podcast/training-data-harrison-chase/\", + \"content\": \"Sonya Huang: Hi, and welcome to training data. We have with us + today Harrison Chase, founder and CEO of LangChain. Harrison is a legend in + the agent ecosystem, as the product visionary who first connected LLMs with + tools and actions. And LangChain is the most popular agent building framework + in the AI space.\"}, {\"url\": \"https://www.youtube.com/watch?v=7D8bw_4hTdo\", + \"content\": \"Join us for an insightful interview with Harrison Chase, the + CEO and co-founder of Langchain, as he provides a comprehensive overview of + Langchain''s innovati\"}, {\"url\": \"https://www.forbes.com/profile/harrison-chase/\", + \"content\": \"Harrison Chase only cofounded LangChain in late 2022, but the + company caught instant attention for enabling anyone to build apps powered by + large language models like GPT-4 in as little as two\"}, {\"url\": \"https://en.wikipedia.org/wiki/LangChain\", + \"content\": \"In October 2023 LangChain introduced LangServe, a deployment + tool designed to facilitate the transition from LCEL (LangChain Expression Language) + prototypes to production-ready applications.[5]\\nIntegrations[edit]\\nAs of + March 2023, LangChain included integrations with systems including Amazon, Google, + and Microsoft Azure cloud storage; API wrappers for news, movie information, + and weather; Bash for summarization, syntax and semantics checking, and execution + of shell scripts; multiple web scraping subsystems and templates; few-shot learning + prompt generation support; finding and summarizing \\\"todo\\\" tasks in code; + Google Drive documents, spreadsheets, and presentations summarization, extraction, + and creation; Google Search and Microsoft Bing web search; OpenAI, Anthropic, + and Hugging Face language models; iFixit repair guides and wikis search and + summarization; MapReduce for question answering, combining documents, and question + generation; N-gram overlap scoring; PyPDF, pdfminer, fitz, and pymupdf for PDF + file text extraction and manipulation; Python and JavaScript code generation, + analysis, and debugging; Milvus vector database[6] to store and retrieve vector + embeddings; Weaviate vector database[7] to cache embedding and data objects; + Redis cache database storage; Python RequestsWrapper and other methods for API + requests; SQL and NoSQL databases including JSON support; Streamlit, including + for logging; text mapping for k-nearest neighbors search; time zone conversion + and calendar operations; tracing and recording stack symbols in threaded and + asynchronous subprocess runs; and the Wolfram Alpha website and SDK.[8] As a + language model integration framework, LangChain''s use-cases largely overlap + with those of language models in general, including document analysis and summarization, + chatbots, and code analysis.[2]\\nHistory[edit]\\nLangChain was launched in + October 2022 as an open source project by Harrison Chase, while working at machine + learning startup Robust Intelligence. In April 2023, LangChain had incorporated + and the new startup raised over $20 million in funding at a valuation of at + least $200 million from venture firm Sequoia Capital, a week after announcing + a $10 million seed investment from Benchmark.[3][4]\\n The project quickly garnered + popularity, with improvements from hundreds of contributors on GitHub, trending + discussions on Twitter, lively activity on the project''s Discord server, many + YouTube tutorials, and meetups in San Francisco and London. As of April 2023, + it can read from more than 50 document types and data sources.[9]\\nReferences[edit]\\nExternal + links[edit]\"}, {\"url\": \"https://analyticsindiamag.com/people/harrison-chase/\", + \"content\": \"By AIM The dynamic co-founder and CEO of LangChain, Harrison + Chase is simplifying the creation of applications powered by LLMs. With a background + in statistics and computer science from Harvard University, Chase has carved + a niche in the AI landscape. AIM Brand Solutions, a marketing division within + AIM, specializes in creating diverse content such as documentaries, public artworks, + podcasts, videos, articles, and more to effectively tell compelling stories. + AIM Research produces a series of annual reports on AI & Data Science covering + every aspect of the industry. Discover how Cypher 2024 expands to the USA, bridging + AI innovation gaps and tackling the challenges of enterprise AI adoption AIM + India AIM Research AIM Leaders Council 50 Best Data Science Firms\"}, {\"url\": + \"https://www.turingpost.com/p/harrison-chase-langchain-ai-agents\", \"content\": + \"Harrison Chase, founder of LangChain, shared insights on the evolution of + AI agents and their applications during Sequoia Capital''s AI Ascent. ... Saves + you a lot of research time, plus gives a flashback to ML history and insights + into the future. Stay ahead alongside over 73,000 professionals from top AI + labs, ML startups, and enterprises\"}]", "tool_use_id": "toolu_014sKkCQPRVMPXGMJTGu5YSm", + "is_error": false}]}], "model": "claude-3-5-sonnet-20240620", "system": "You + are a helpful AI assistant.\n\nSystem time: 2024-11-13T23:54:07.180606+00:00", + "tools": [{"name": "search", "description": "Search for general web results. + This function performs a search using the Tavily search engine, which is designed\nto + provide comprehensive, accurate, and trusted results. It''s particularly useful\nfor + answering questions about current events.", "input_schema": {"properties": {"query": + {"type": "string"}}, "required": ["query"], "type": "object"}}]}' + headers: {} + method: POST + uri: https://api.anthropic.com/v1/messages + response: + body: + string: !!binary | + H4sIAAAAAAAAA3SUW28bNxCF/8qAKNAWWKmyfEmjt8QIHAN2YjTOS5rCGHFnVxNxhzQvUreG/3sx + lFTbafskLXdn5juHh3ww3JqFGVJ/Nzt6ffplLvdXR/2Hi7f9xYf1uy/fxr8G05g8BtKvKCXsyTQm + eqcLmBKnjJJNYwbfkjMLYx2WlibHk9NJ8iKUJ/PZ/GR2Np+ZxlgvmSSbxe8Ph6aZ/tTy+rMwbzFR + C14grwgSYbQriJSKy6mBS7AoEKLfcEsw+gJbzitg6XwcMLMXwKUvuRZ3vkhLEXwHVyj9+QpZFl/l + q9z+z0vgBO8xRk5e4HyFiaZw7SNBCmS5Y4vOjbXD0fS7D7VUZ1o/OXRGaeH83ccXE6ZaPJ/C+wNA + +3y6gMNMMJ/N54AJUMAHkknyJVpS1d/IZtiu2BFsfVyz9IAZEAa0KxYCRxhFV1PGmEsAJaYWfvPL + kjJcSibnuCexVEmOp3v6lY6DJdp1H5VLWVLGzCmzTVWK9UMomSIky9oAuugHdWGDsYXPwhuKifNY + G59M4Sayj5D9jkWh/lHawEpZ2+rY9Z796sCeCQeV9R/QjYq3K+i8LYeUUKrNFXGDjttdCnz3b1Nq + PlPlO50+8/2+sF27EXpkoRaCD8Vh5DyqC4r45lLVD0U4j02dxAJvQmSne3Xc7Hd+CCgjRGRFS9xL + jYxk6Iq0LH0DLNYV/Qt+QxF+mM9gYOcUuLr5ie6LZ4RzDJzRVdSz6cuArsVvBTofgXN6EZCbMa+8 + /HI7Bko2csgQ0K6xJ42m5oQH3Y8B1wScgTCN+tzShpwPdUrBnuBafQIMwbGtbu48ezV9irr1kril + SC2gBnNgIRXKfYn0zDbsdZmsT2PKNDQQNAtW/XVjFWH1hrD7fMSevsNI8NPV1XX6eXfOs/dul0a0 + T2AvT+KPCTac1NJa8uSdZnxJJDWTPATH3Vg5Q/SWUtLM2Ei4i9Mz9RD8tkpdjuAqozsw7iIFjtcE + Fze3k5NG7dUGnAGttuWlIx2JsFXHIKL0pLP2vlPcKYq0u+z0+cnAjsm1U/P4R2NS9uEuEiYvZmFI + 2rtcopj9i0T3RY+IWUhxrjGl3tOLB8MSSr7Lfk2SzGI+e3XWGF/yi8VfXz8+/g0AAP//AwD0aedG + CAYAAA== + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 8e22b04158a84cb1-PHL + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 13 Nov 2024 23:54:48 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + X-Robots-Tag: + - none + anthropic-ratelimit-requests-limit: + - '4000' + anthropic-ratelimit-requests-remaining: + - '3999' + anthropic-ratelimit-requests-reset: + - '2024-11-13T23:54:42Z' + anthropic-ratelimit-tokens-limit: + - '400000' + anthropic-ratelimit-tokens-remaining: + - '400000' + anthropic-ratelimit-tokens-reset: + - '2024-11-13T23:54:48Z' + request-id: + - req_01Ty6RLDuDeMCfmVfunAmMKp + via: + - 1.1 google + status: + code: 200 + message: OK +- request: + body: '{"max_tokens": 1024, "messages": [{"role": "user", "content": "Who is the + founder of LangChain?"}], "model": "claude-3-5-sonnet-20240620", "system": "You + are a helpful AI assistant.\n\nSystem time: 2024-11-13T23:54:32.018816+00:00", + "tools": [{"name": "search", "description": "Search for general web results. + This function performs a search using the Tavily search engine, which is designed\nto + provide comprehensive, accurate, and trusted results. It''s particularly useful\nfor + answering questions about current events.", "input_schema": {"properties": {"query": + {"type": "string"}}, "required": ["query"], "type": "object"}}]}' + headers: {} + method: POST + uri: https://api.anthropic.com/v1/messages + response: + body: + string: !!binary | + H4sIAAAAAAAAA1SRTW8TQQyG/4rlC5fZapO0KZ0LEqAWlB4Q4UMBodWw42QXdu1k7KGNov3vaDeg + wsnyx/v6kX3CNqLHXndVObtpZ6vHu+cPH3/Zdbh7t9ysbjerNTq0457GKVINO0KHSbqxEFRbtcCG + DnuJ1KHHugs5UrEorgoVZrJiXs4vy+W8RIe1sBEb+q+nv6ZGj6N8Ch4/CATWB0pgTatwyKTWCkOo + 65yCUXd08PZZ1wETRTABpZDqBrYyKgh6UYO8L0yKGIyg5a2kPpw9vks2uA+8e9WEliFwhNYUtpI5 + UrqAezLoCaKANcEmz6PkCxzcE61IV2UdbzAdbsxzVc7WdBVvfzRfXu7im0+vZ+v3i2aeNuiQQz/q + zpijivfZ0J/wkCkd0ePnRqDVCf4PCMj2ifIFDsM3h2qyrxIFFf6fYmooHTJxTeg5d53DPL3Jn87b + KpOfxIr+crF0KNn+rd1cD8NvAAAA//8DAPfUzMAFAgAA + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 8e22b0dcbd844caf-PHL + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 13 Nov 2024 23:55:09 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + X-Robots-Tag: + - none + anthropic-ratelimit-requests-limit: + - '4000' + anthropic-ratelimit-requests-remaining: + - '3999' + anthropic-ratelimit-requests-reset: + - '2024-11-13T23:55:07Z' + anthropic-ratelimit-tokens-limit: + - '400000' + anthropic-ratelimit-tokens-remaining: + - '400000' + anthropic-ratelimit-tokens-reset: + - '2024-11-13T23:55:09Z' + request-id: + - req_018TP5XzbuQ82VrDc4fbETo3 + via: + - 1.1 google + status: + code: 200 + message: OK +- request: + body: '{"max_tokens": 1024, "messages": [{"role": "user", "content": "Who is the + founder of LangChain?"}, {"role": "assistant", "content": [{"text": "To answer + this question accurately, I''ll need to search for the most up-to-date information + about LangChain and its founder. Let me do that for you.", "type": "text"}, + {"type": "tool_use", "name": "search", "input": {"query": "Who is the founder + of LangChain?"}, "id": "toolu_01Se5dFjhZBgdHVD1SR3h2rY"}]}, {"role": "user", + "content": [{"type": "tool_result", "content": "[{\"url\": \"https://sfelc.com/speaker/harrison-chase\", + \"content\": \"Harrison Chase is the CEO and co-founder of LangChain, a company + formed around the open source Python/Typescript packages that aim to make it + easy to develop Language Model applications. Prior to starting LangChain, he + led the ML team at Robust Intelligence (an MLOps company focused on testing + and validation of machine learning models), led the\"}, {\"url\": \"https://aiconference.com/speakers/harrison-chase/\", + \"content\": \"Harrison Chase is the co-founder and CEO of LangChain, a company + formed around the open-source Python/Typescript packages that aim to make it + easy to develop Language Model applications. Prior to starting LangChain, he + led the ML team at Robust Intelligence (an MLOps company focused on testing + and validation of machine learning models), led the\"}, {\"url\": \"https://tedai-sanfrancisco.ted.com/speakers-1/harrison-chase-/co-founder-and-ceo,-langchain/\", + \"content\": \"Harrison Chase, a Harvard graduate in statistics and computer + science, co-founded LangChain to streamline the development of Language Model + applications with open-source Python/Typescript packages. Chase''s experience + includes heading the Machine Learning team at Robust Intelligence, focusing + on the testing and validation of machine learning models, and leading the entity + linking team at Kensho\"}, {\"url\": \"https://techcrunch.com/author/harrison-chase/\", + \"content\": \"Harrison Chase is the CEO and co-founder of LangChain, a company + formed around the open source Python/Typescript packages that aim to make it + easy to develop Language Model applications\"}, {\"url\": \"https://www.sequoiacap.com/podcast/training-data-harrison-chase/\", + \"content\": \"Sonya Huang: Hi, and welcome to training data. We have with us + today Harrison Chase, founder and CEO of LangChain. Harrison is a legend in + the agent ecosystem, as the product visionary who first connected LLMs with + tools and actions. And LangChain is the most popular agent building framework + in the AI space.\"}, {\"url\": \"https://www.youtube.com/watch?v=7D8bw_4hTdo\", + \"content\": \"Join us for an insightful interview with Harrison Chase, the + CEO and co-founder of Langchain, as he provides a comprehensive overview of + Langchain''s innovati\"}, {\"url\": \"https://www.forbes.com/profile/harrison-chase/\", + \"content\": \"Harrison Chase only cofounded LangChain in late 2022, but the + company caught instant attention for enabling anyone to build apps powered by + large language models like GPT-4 in as little as two\"}, {\"url\": \"https://en.wikipedia.org/wiki/LangChain\", + \"content\": \"In October 2023 LangChain introduced LangServe, a deployment + tool designed to facilitate the transition from LCEL (LangChain Expression Language) + prototypes to production-ready applications.[5]\\nIntegrations[edit]\\nAs of + March 2023, LangChain included integrations with systems including Amazon, Google, + and Microsoft Azure cloud storage; API wrappers for news, movie information, + and weather; Bash for summarization, syntax and semantics checking, and execution + of shell scripts; multiple web scraping subsystems and templates; few-shot learning + prompt generation support; finding and summarizing \\\"todo\\\" tasks in code; + Google Drive documents, spreadsheets, and presentations summarization, extraction, + and creation; Google Search and Microsoft Bing web search; OpenAI, Anthropic, + and Hugging Face language models; iFixit repair guides and wikis search and + summarization; MapReduce for question answering, combining documents, and question + generation; N-gram overlap scoring; PyPDF, pdfminer, fitz, and pymupdf for PDF + file text extraction and manipulation; Python and JavaScript code generation, + analysis, and debugging; Milvus vector database[6] to store and retrieve vector + embeddings; Weaviate vector database[7] to cache embedding and data objects; + Redis cache database storage; Python RequestsWrapper and other methods for API + requests; SQL and NoSQL databases including JSON support; Streamlit, including + for logging; text mapping for k-nearest neighbors search; time zone conversion + and calendar operations; tracing and recording stack symbols in threaded and + asynchronous subprocess runs; and the Wolfram Alpha website and SDK.[8] As a + language model integration framework, LangChain''s use-cases largely overlap + with those of language models in general, including document analysis and summarization, + chatbots, and code analysis.[2]\\nHistory[edit]\\nLangChain was launched in + October 2022 as an open source project by Harrison Chase, while working at machine + learning startup Robust Intelligence. In April 2023, LangChain had incorporated + and the new startup raised over $20 million in funding at a valuation of at + least $200 million from venture firm Sequoia Capital, a week after announcing + a $10 million seed investment from Benchmark.[3][4]\\n The project quickly garnered + popularity, with improvements from hundreds of contributors on GitHub, trending + discussions on Twitter, lively activity on the project''s Discord server, many + YouTube tutorials, and meetups in San Francisco and London. As of April 2023, + it can read from more than 50 document types and data sources.[9]\\nReferences[edit]\\nExternal + links[edit]\"}, {\"url\": \"https://analyticsindiamag.com/people/harrison-chase/\", + \"content\": \"By AIM The dynamic co-founder and CEO of LangChain, Harrison + Chase is simplifying the creation of applications powered by LLMs. With a background + in statistics and computer science from Harvard University, Chase has carved + a niche in the AI landscape. AIM Brand Solutions, a marketing division within + AIM, specializes in creating diverse content such as documentaries, public artworks, + podcasts, videos, articles, and more to effectively tell compelling stories. + AIM Research produces a series of annual reports on AI & Data Science covering + every aspect of the industry. Discover how Cypher 2024 expands to the USA, bridging + AI innovation gaps and tackling the challenges of enterprise AI adoption AIM + India AIM Research AIM Leaders Council 50 Best Data Science Firms\"}, {\"url\": + \"https://www.turingpost.com/p/harrison-chase-langchain-ai-agents\", \"content\": + \"Harrison Chase, founder of LangChain, shared insights on the evolution of + AI agents and their applications during Sequoia Capital''s AI Ascent. ... Saves + you a lot of research time, plus gives a flashback to ML history and insights + into the future. Stay ahead alongside over 73,000 professionals from top AI + labs, ML startups, and enterprises\"}]", "tool_use_id": "toolu_01Se5dFjhZBgdHVD1SR3h2rY", + "is_error": false}]}], "model": "claude-3-5-sonnet-20240620", "system": "You + are a helpful AI assistant.\n\nSystem time: 2024-11-13T23:54:34.582739+00:00", + "tools": [{"name": "search", "description": "Search for general web results. + This function performs a search using the Tavily search engine, which is designed\nto + provide comprehensive, accurate, and trusted results. It''s particularly useful\nfor + answering questions about current events.", "input_schema": {"properties": {"query": + {"type": "string"}}, "required": ["query"], "type": "object"}}]}' + headers: {} + method: POST + uri: https://api.anthropic.com/v1/messages + response: + body: + string: !!binary | + H4sIAAAAAAAAA2yUYW8bNwyG/wpxGLANOHuuk3SAv2VGsWZz0CLLgA7rENA6+k61jlQkyq5R9L8P + lJ0sSffpAB1FPnz5Ul8a3zWLZsz93ezVm9vzv8ryfjVf9mfp5mJz8+HD+NvvTdvoIZJFUc7YU9M2 + SYIdYM4+K7I2bTNKR6FZNC5g6WhyNrmYZGEmncxn8/PZ6/msaRsnrMTaLP7+8pBU6bNdr59Fczsg + b+EgBTaSICbZ+c5zDyPB3usAOhBIjJK0sNcDqEAmTG6o8fZ3lKxQ4kRl0qESeN5IGlG98BR+wUwd + CNfI08VEuQTNLVyBQwYnvPEdsYYDIOc9JcNJcF8oW5LFR/7ItwPBRgp3lEA2sELulwN6Bp/hLabk + szAsB8w0reFyasXwEkGV4bPWVK+mL25YDhaFTyVr5TwVamFdjgdOJg/FkTtYvnn3DKKWnE+fUO0x + Q8DCbqAOPMM7p7KmBPPZfA6YARkkEk+ylOTIWD+RU1gfXqLtBx8IBqoZ95K2NhtUQBjRDZ4JAmFi + O82KSUsEhyFQBzeytn6uWCkE3xO7ozRn01PqwThgjW7bJ2vOOLOi+qze5dqokzEWpQTZeUsAmySj + Ie4wdfAn+x2l7PVQE59P4X3yZgo5shjUoyStNWFcpuf1iX31wK6Eo7X1P9CtaVDt5sqDl8wYpgN3 + sMPgu2o2G8k3otQlyZXv4umA7ot323CAHj1TB1FiCZjM4P7o1csr636spm8BVRO6WnQo3CXqspUz + WyW/LiopG9ivXt+WdeVak5OxQsLedxQO0PnsSrYWVKJ3Fr/D5KVkiAHVluYI+noKVwyXMflghjlr + n9qdnaQoCZW6aqQ6I+RDLZrQW/7se/Yb75AVNoVtn1u7GUpdbdlRgu/mMxh9CCZcneofdF/EIywx + esXQmrKlzqYuwKmImrRZ7frj/Qr98xRu/wv8PsNouHVotl/y3PDvDzoI/3R7iJRd8lEhottiTxl0 + MHv70Ww04pbAKxDm+vJ0tKMgsepRsCe4tvECxhi8qybILUSznrNxhsdpJsIw2sQurwB7Yj36e7W6 + hh9WmHp6kfJHiLKnZBo/yV0b/fbtcMLZd8do2PnshTE9NVKOaD5+Bmav5+CPO22hzp7uo8NWq+t8 + enxFwpHUzFe7G3H7bK9AmKyxx5f4ZGXYJBzJsudaa118qNN/VGDafP2nbbJKvEuEWbhZNMTdnZbE + zelHpvtiS9gs/lVeaU6OjlIpuDqyqlbKzCsoLYkvyc9OzStWsjIysDDQUcovLUEWNDY2q60FAAAA + //8DAHryTTDvBgAA + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 8e22b0ec98794caf-PHL + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 13 Nov 2024 23:55:17 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + X-Robots-Tag: + - none + anthropic-ratelimit-requests-limit: + - '4000' + anthropic-ratelimit-requests-remaining: + - '3999' + anthropic-ratelimit-requests-reset: + - '2024-11-13T23:55:10Z' + anthropic-ratelimit-tokens-limit: + - '400000' + anthropic-ratelimit-tokens-remaining: + - '400000' + anthropic-ratelimit-tokens-reset: + - '2024-11-13T23:55:17Z' + request-id: + - req_011iT4S1koK6LtTJefPZgpb9 + via: + - 1.1 google + status: + code: 200 + message: OK +- request: + body: '{"max_tokens": 1024, "messages": [{"role": "user", "content": "Who is the + founder of LangChain?"}], "model": "claude-3-5-sonnet-20240620", "system": "You + are a helpful AI assistant.\n\nSystem time: 2024-11-13T23:54:53.846143+00:00", + "tools": [{"name": "search", "description": "Search for general web results. + This function performs a search using the Tavily search engine, which is designed\nto + provide comprehensive, accurate, and trusted results. It''s particularly useful\nfor + answering questions about current events.", "input_schema": {"properties": {"query": + {"type": "string"}}, "required": ["query"], "type": "object"}}]}' + headers: {} + method: POST + uri: https://api.anthropic.com/v1/messages + response: + body: + string: !!binary | + H4sIAAAAAAAAA1RRS2vcQAz+K0KXXsbBu5um6dySQCAQckiXPijFTD3y2slYsmc0JO7i/17sbUl7 + Enp8Dz4dsfNosU+HqtxsPrdPfjNcf2A3Svvl5uGXxKtLNKjTQMsVpeQOhAajhGXgUuqSOlY02Iun + gBbr4LKnYle8L5IwkxbbcnteXmxLNFgLK7Gi/X78S6r0usDXYnEv4Di9UARtuwRjpqSdMLi6ztEp + hcnA3bsQgIk8qEAiF+sWGlkQBL0khTwUKoV3StBxI7F3J46fkhXuHR9uWtcxOPbQaYJGMnuKZ3BP + Cj2BF9DW6co5ST7D2by5FQlVTksGa3BLn6tyczt9uv76bV9f7X39eCnj+Hpo+hc0yK5fcCebC4qH + rGiPOGaKE1r8ow7SvFnDef5hMKkMVSSXhP9XXheJxkxcE1rOIRjM62vs8aRQqTwTJ7TnuwuDkvXf + 2cfdPP8GAAD//wMAgzLCHfkBAAA= + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 8e22b1653bb54cb6-PHL + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 13 Nov 2024 23:55:32 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + X-Robots-Tag: + - none + anthropic-ratelimit-requests-limit: + - '4000' + anthropic-ratelimit-requests-remaining: + - '3999' + anthropic-ratelimit-requests-reset: + - '2024-11-13T23:55:29Z' + anthropic-ratelimit-tokens-limit: + - '400000' + anthropic-ratelimit-tokens-remaining: + - '400000' + anthropic-ratelimit-tokens-reset: + - '2024-11-13T23:55:32Z' + request-id: + - req_01RU57s1YVTHykXPQ2qnPNr4 + via: + - 1.1 google + status: + code: 200 + message: OK +- request: + body: '{"max_tokens": 1024, "messages": [{"role": "user", "content": "Who is the + founder of LangChain?"}, {"role": "assistant", "content": [{"text": "To answer + this question accurately, I''ll need to search for the most up-to-date information + about LangChain and its founder. Let me do that for you.", "type": "text"}, + {"type": "tool_use", "name": "search", "input": {"query": "founder of LangChain"}, + "id": "toolu_01FySBXYTcATdcR8oqqxgfmw"}]}, {"role": "user", "content": [{"type": + "tool_result", "content": "[{\"url\": \"https://sfelc.com/speaker/harrison-chase\", + \"content\": \"Harrison Chase is the CEO and co-founder of LangChain, a company + formed around the open source Python/Typescript packages that aim to make it + easy to develop Language Model applications. Prior to starting LangChain, he + led the ML team at Robust Intelligence (an MLOps company focused on testing + and validation of machine learning models), led the\"}, {\"url\": \"https://aiconference.com/speakers/harrison-chase/\", + \"content\": \"Harrison Chase is the co-founder and CEO of LangChain, a company + formed around the open-source Python/Typescript packages that aim to make it + easy to develop Language Model applications. Prior to starting LangChain, he + led the ML team at Robust Intelligence (an MLOps company focused on testing + and validation of machine learning models), led the\"}, {\"url\": \"https://tedai-sanfrancisco.ted.com/speakers-1/harrison-chase-/co-founder-and-ceo,-langchain/\", + \"content\": \"Harrison Chase, a Harvard graduate in statistics and computer + science, co-founded LangChain to streamline the development of Language Model + applications with open-source Python/Typescript packages. Chase''s experience + includes heading the Machine Learning team at Robust Intelligence, focusing + on the testing and validation of machine learning models, and leading the entity + linking team at Kensho\"}, {\"url\": \"https://techcrunch.com/author/harrison-chase/\", + \"content\": \"Harrison Chase is the CEO and co-founder of LangChain, a company + formed around the open source Python/Typescript packages that aim to make it + easy to develop Language Model applications\"}, {\"url\": \"https://www.sequoiacap.com/podcast/training-data-harrison-chase/\", + \"content\": \"Sonya Huang: Hi, and welcome to training data. We have with us + today Harrison Chase, founder and CEO of LangChain. Harrison is a legend in + the agent ecosystem, as the product visionary who first connected LLMs with + tools and actions. And LangChain is the most popular agent building framework + in the AI space.\"}, {\"url\": \"https://www.youtube.com/watch?v=7D8bw_4hTdo\", + \"content\": \"Join us for an insightful interview with Harrison Chase, the + CEO and co-founder of Langchain, as he provides a comprehensive overview of + Langchain''s innovati\"}, {\"url\": \"https://www.forbes.com/profile/harrison-chase/\", + \"content\": \"Harrison Chase only cofounded LangChain in late 2022, but the + company caught instant attention for enabling anyone to build apps powered by + large language models like GPT-4 in as little as two\"}, {\"url\": \"https://en.wikipedia.org/wiki/LangChain\", + \"content\": \"In October 2023 LangChain introduced LangServe, a deployment + tool designed to facilitate the transition from LCEL (LangChain Expression Language) + prototypes to production-ready applications.[5]\\nIntegrations[edit]\\nAs of + March 2023, LangChain included integrations with systems including Amazon, Google, + and Microsoft Azure cloud storage; API wrappers for news, movie information, + and weather; Bash for summarization, syntax and semantics checking, and execution + of shell scripts; multiple web scraping subsystems and templates; few-shot learning + prompt generation support; finding and summarizing \\\"todo\\\" tasks in code; + Google Drive documents, spreadsheets, and presentations summarization, extraction, + and creation; Google Search and Microsoft Bing web search; OpenAI, Anthropic, + and Hugging Face language models; iFixit repair guides and wikis search and + summarization; MapReduce for question answering, combining documents, and question + generation; N-gram overlap scoring; PyPDF, pdfminer, fitz, and pymupdf for PDF + file text extraction and manipulation; Python and JavaScript code generation, + analysis, and debugging; Milvus vector database[6] to store and retrieve vector + embeddings; Weaviate vector database[7] to cache embedding and data objects; + Redis cache database storage; Python RequestsWrapper and other methods for API + requests; SQL and NoSQL databases including JSON support; Streamlit, including + for logging; text mapping for k-nearest neighbors search; time zone conversion + and calendar operations; tracing and recording stack symbols in threaded and + asynchronous subprocess runs; and the Wolfram Alpha website and SDK.[8] As a + language model integration framework, LangChain''s use-cases largely overlap + with those of language models in general, including document analysis and summarization, + chatbots, and code analysis.[2]\\nHistory[edit]\\nLangChain was launched in + October 2022 as an open source project by Harrison Chase, while working at machine + learning startup Robust Intelligence. In April 2023, LangChain had incorporated + and the new startup raised over $20 million in funding at a valuation of at + least $200 million from venture firm Sequoia Capital, a week after announcing + a $10 million seed investment from Benchmark.[3][4]\\n The project quickly garnered + popularity, with improvements from hundreds of contributors on GitHub, trending + discussions on Twitter, lively activity on the project''s Discord server, many + YouTube tutorials, and meetups in San Francisco and London. As of April 2023, + it can read from more than 50 document types and data sources.[9]\\nReferences[edit]\\nExternal + links[edit]\"}, {\"url\": \"https://analyticsindiamag.com/people/harrison-chase/\", + \"content\": \"By AIM The dynamic co-founder and CEO of LangChain, Harrison + Chase is simplifying the creation of applications powered by LLMs. With a background + in statistics and computer science from Harvard University, Chase has carved + a niche in the AI landscape. AIM Brand Solutions, a marketing division within + AIM, specializes in creating diverse content such as documentaries, public artworks, + podcasts, videos, articles, and more to effectively tell compelling stories. + AIM Research produces a series of annual reports on AI & Data Science covering + every aspect of the industry. Discover how Cypher 2024 expands to the USA, bridging + AI innovation gaps and tackling the challenges of enterprise AI adoption AIM + India AIM Research AIM Leaders Council 50 Best Data Science Firms\"}, {\"url\": + \"https://www.turingpost.com/p/harrison-chase-langchain-ai-agents\", \"content\": + \"Harrison Chase, founder of LangChain, shared insights on the evolution of + AI agents and their applications during Sequoia Capital''s AI Ascent. ... Saves + you a lot of research time, plus gives a flashback to ML history and insights + into the future. Stay ahead alongside over 73,000 professionals from top AI + labs, ML startups, and enterprises\"}]", "tool_use_id": "toolu_01FySBXYTcATdcR8oqqxgfmw", + "is_error": false}]}], "model": "claude-3-5-sonnet-20240620", "system": "You + are a helpful AI assistant.\n\nSystem time: 2024-11-13T23:54:56.977251+00:00", + "tools": [{"name": "search", "description": "Search for general web results. + This function performs a search using the Tavily search engine, which is designed\nto + provide comprehensive, accurate, and trusted results. It''s particularly useful\nfor + answering questions about current events.", "input_schema": {"properties": {"query": + {"type": "string"}}, "required": ["query"], "type": "object"}}]}' + headers: {} + method: POST + uri: https://api.anthropic.com/v1/messages + response: + body: + string: !!binary | + H4sIAAAAAAAAA3RVbW/bRgz+K4RQYBsge4nTppu/tdnQZEnQbnWHDesQ0CdaYn3iXY48p1rR/z6c + bDd2h30yJB3Jh8/L+VPFTTWvem3vTk6vf/1w+ePpu9D8IYvww0eJv5xd/35d1ZUNkcopUsWWqrpK + wZcXqMpqKFbVVR8a8tW8ch5zQ5OzybOJBhGyyexk9vTkfHZS1ZULYiRWzf/6tG9q9LGUjz/z6iUq + NRAErCNQwuQ6SKTZm9ZwBQ4FYgobbgiGkOGBrQOWVUg9GgcBXIZsY/EqZGkoQVjBDUp70SHL/L28 + l8X/fARWuMSUWIPARYdKU1gEWBL0IRHERI6VauionCwjXJjsG6E0cPHz66OGU7ikRICJQENPsKYB + YmAx3cE8njb2OIZ6Ov36zJeRzSFwAY9GMDuZzaalbjY9XgvBhT6iDFCYogYwlSYQIslEQ06O4M1g + XZDvF0Okty5xNIjo1thS2RUNkHuwAD2uCdiAUIfy3NCGfIjjvIwtwW3xAWCMnt2oiY6QzqbwJnFI + pUYNk7G0jyDrr/acvxcAmMANNSPTtzdghD2gwW9hmdXgSoy855bEUQ0ocHvzOurBni7vnUQ6Div0 + btBzs3VKWEGPrmMh8IRJypHRwwXv0XASYxvAs6zLoT2QaxLtwrjc0+lOng4L2Ut063bLMEvZ1liN + nY4QCsJslEAdF/CwSqEv628wNfBOeENJ2Yax8bNDIe8zu7UfoEUWaiCGmD2mAo23eXlxVbr3WdiG + epuNErjEyzwKsR3VZWkSNVoY2KlHSQtTr9gu87IGdMYbgobVZdWxMggsHthsZ/WfWF1ITT0+SO4p + hazwZ8iLvCSwbCEx+q3y51O4EngRE/vi0LP6yLkupBgSWjFl4W70Ro5j44RcNFRuhVfsUAxWWRqW + du+P1xtK8GR2Aj17X1Rl2R8pEmERPH/RG61IrVYqHktGUjYklhPBilMPb+k+B0a4wMiGfu+HRccK + DnuCD8WBCA9Ea8DVlhQJWdw4F56cPnZXouKCDan1VBYo016SuK7HtB4Jev6flLNCIhda4X/2vJTL + Y8VtwfioNralJbmggxr1NcQSLFds4cesF/2F3C5sqaWvcqrw7c3NrX63NYuF4LcmLQ7YJ/cgpNu7 + 7hjsN1pIbShpx7EeE7AkV+473FsUVgl7eghpPWJaZvZbhQ4uCYjhgRI1sBzAj0j9Huk2leB5TfDq + zWLytAYSXPrS4sDAFsAlKvfgi6vJvhvGqNv7m1DZD+N2uyBNq89/15VaiHeJUINU84qkubOcpNp9 + ULrPJaXVXLL3dZXHP8D5p4olZruzsCbRaj47eX5eVyHb4cuz5+efP/8LAAD//wMAjIY6NGEHAAA= + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 8e22b178d9d04cb4-PHL + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 13 Nov 2024 23:55:39 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + X-Robots-Tag: + - none + anthropic-ratelimit-requests-limit: + - '4000' + anthropic-ratelimit-requests-remaining: + - '3999' + anthropic-ratelimit-requests-reset: + - '2024-11-13T23:55:32Z' + anthropic-ratelimit-tokens-limit: + - '400000' + anthropic-ratelimit-tokens-remaining: + - '400000' + anthropic-ratelimit-tokens-reset: + - '2024-11-13T23:55:39Z' + request-id: + - req_015HcqrgirHzeLfD6UpmyE4r + via: + - 1.1 google + status: + code: 200 + message: OK +- request: + body: '{"max_tokens": 1024, "messages": [{"role": "user", "content": "Who is the + founder of LangChain?"}], "model": "claude-3-5-sonnet-20240620", "system": "You + are a helpful AI assistant.", "tools": [{"name": "search", "description": "Search + for general web results. This function performs a search using the Tavily search + engine, which is designed\nto provide comprehensive, accurate, and trusted results. + It''s particularly useful\nfor answering questions about current events.", "input_schema": + {"properties": {"query": {"type": "string"}}, "required": ["query"], "type": + "object"}}]}' + headers: {} + method: POST + uri: https://api.anthropic.com/v1/messages + response: + body: + string: !!binary | + H4sIAAAAAAAAA1SR3WrcQAyFX0Xopjfj4HWzKZm7JrTQsimhBAIpxcza8nqoLe2ONLRm8bsXe1vS + Xgn9nKMP6YyxRY+jHupy8/jxOcfbB9me7qqc08uXd81Ee3Ro05GWKVINB0KHSYalEFSjWmBDh6O0 + NKDHZgi5peJtsS1UmMmKqqyuy5uqRIeNsBEb+m/nv6ZGvxb5Gjw+CQTWn5TA+qhwyqQWhSE0TU7B + aJgcfHozDMBELZiAUkhND50sCoJR1CAfC5OiDUYQuZM0hovHXrLBLvDhvg+RIXAL0RQ6ydxSuoId + GYwErYD1wVbPSfIVzu6VVmSosy43WA+35LkuN7v3U5zuuj1/eHmi/ePnr4ftw31ChxzGRXfBXFR8 + zIb+jKdMaUKPz71A1BX+DwhI90qJ8/zdoZoc60RBhf+HWBtKp0zcEHrOw+Awr1/y58uy2uQHsaK/ + 3lQOJdu/tdubef4NAAD//wMAEAehhwQCAAA= + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 8e22b64a18a54caf-PHL + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 13 Nov 2024 23:58:52 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + X-Robots-Tag: + - none + anthropic-ratelimit-requests-limit: + - '4000' + anthropic-ratelimit-requests-remaining: + - '3999' + anthropic-ratelimit-requests-reset: + - '2024-11-13T23:58:49Z' + anthropic-ratelimit-tokens-limit: + - '400000' + anthropic-ratelimit-tokens-remaining: + - '400000' + anthropic-ratelimit-tokens-reset: + - '2024-11-13T23:58:52Z' + request-id: + - req_01JfEnoQAvmWG3PFoZTmVtmb + via: + - 1.1 google + status: + code: 200 + message: OK +- request: + body: '{"max_tokens": 1024, "messages": [{"role": "user", "content": "Who is the + founder of LangChain?"}, {"role": "assistant", "content": [{"text": "To answer + this question accurately, I''ll need to search for the most up-to-date information + about LangChain and its founder. Let me do that for you.", "type": "text"}, + {"type": "tool_use", "name": "search", "input": {"query": "Who is the founder + of LangChain"}, "id": "toolu_01LAyiyBfbnEZTebPJRg5MCr"}]}, {"role": "user", + "content": [{"type": "tool_result", "content": "[{\"url\": \"https://sfelc.com/speaker/harrison-chase\", + \"content\": \"Harrison Chase is the CEO and co-founder of LangChain, a company + formed around the open source Python/Typescript packages that aim to make it + easy to develop Language Model applications. Prior to starting LangChain, he + led the ML team at Robust Intelligence (an MLOps company focused on testing + and validation of machine learning models), led the\"}, {\"url\": \"https://aiconference.com/speakers/harrison-chase/\", + \"content\": \"Harrison Chase is the co-founder and CEO of LangChain, a company + formed around the open-source Python/Typescript packages that aim to make it + easy to develop Language Model applications. Prior to starting LangChain, he + led the ML team at Robust Intelligence (an MLOps company focused on testing + and validation of machine learning models), led the\"}, {\"url\": \"https://tedai-sanfrancisco.ted.com/speakers-1/harrison-chase-/co-founder-and-ceo,-langchain/\", + \"content\": \"Harrison Chase, a Harvard graduate in statistics and computer + science, co-founded LangChain to streamline the development of Language Model + applications with open-source Python/Typescript packages. Chase''s experience + includes heading the Machine Learning team at Robust Intelligence, focusing + on the testing and validation of machine learning models, and leading the entity + linking team at Kensho\"}, {\"url\": \"https://techcrunch.com/author/harrison-chase/\", + \"content\": \"Harrison Chase is the CEO and co-founder of LangChain, a company + formed around the open source Python/Typescript packages that aim to make it + easy to develop Language Model applications\"}, {\"url\": \"https://www.sequoiacap.com/podcast/training-data-harrison-chase/\", + \"content\": \"Sonya Huang: Hi, and welcome to training data. We have with us + today Harrison Chase, founder and CEO of LangChain. Harrison is a legend in + the agent ecosystem, as the product visionary who first connected LLMs with + tools and actions. And LangChain is the most popular agent building framework + in the AI space.\"}, {\"url\": \"https://www.youtube.com/watch?v=7D8bw_4hTdo\", + \"content\": \"Join us for an insightful interview with Harrison Chase, the + CEO and co-founder of Langchain, as he provides a comprehensive overview of + Langchain''s innovati\"}, {\"url\": \"https://www.forbes.com/profile/harrison-chase/\", + \"content\": \"Harrison Chase only cofounded LangChain in late 2022, but the + company caught instant attention for enabling anyone to build apps powered by + large language models like GPT-4 in as little as two\"}, {\"url\": \"https://en.wikipedia.org/wiki/LangChain\", + \"content\": \"In October 2023 LangChain introduced LangServe, a deployment + tool designed to facilitate the transition from LCEL (LangChain Expression Language) + prototypes to production-ready applications.[5]\\nIntegrations[edit]\\nAs of + March 2023, LangChain included integrations with systems including Amazon, Google, + and Microsoft Azure cloud storage; API wrappers for news, movie information, + and weather; Bash for summarization, syntax and semantics checking, and execution + of shell scripts; multiple web scraping subsystems and templates; few-shot learning + prompt generation support; finding and summarizing \\\"todo\\\" tasks in code; + Google Drive documents, spreadsheets, and presentations summarization, extraction, + and creation; Google Search and Microsoft Bing web search; OpenAI, Anthropic, + and Hugging Face language models; iFixit repair guides and wikis search and + summarization; MapReduce for question answering, combining documents, and question + generation; N-gram overlap scoring; PyPDF, pdfminer, fitz, and pymupdf for PDF + file text extraction and manipulation; Python and JavaScript code generation, + analysis, and debugging; Milvus vector database[6] to store and retrieve vector + embeddings; Weaviate vector database[7] to cache embedding and data objects; + Redis cache database storage; Python RequestsWrapper and other methods for API + requests; SQL and NoSQL databases including JSON support; Streamlit, including + for logging; text mapping for k-nearest neighbors search; time zone conversion + and calendar operations; tracing and recording stack symbols in threaded and + asynchronous subprocess runs; and the Wolfram Alpha website and SDK.[8] As a + language model integration framework, LangChain''s use-cases largely overlap + with those of language models in general, including document analysis and summarization, + chatbots, and code analysis.[2]\\nHistory[edit]\\nLangChain was launched in + October 2022 as an open source project by Harrison Chase, while working at machine + learning startup Robust Intelligence. In April 2023, LangChain had incorporated + and the new startup raised over $20 million in funding at a valuation of at + least $200 million from venture firm Sequoia Capital, a week after announcing + a $10 million seed investment from Benchmark.[3][4]\\n The project quickly garnered + popularity, with improvements from hundreds of contributors on GitHub, trending + discussions on Twitter, lively activity on the project''s Discord server, many + YouTube tutorials, and meetups in San Francisco and London. As of April 2023, + it can read from more than 50 document types and data sources.[9]\\nReferences[edit]\\nExternal + links[edit]\"}, {\"url\": \"https://analyticsindiamag.com/people/harrison-chase/\", + \"content\": \"By AIM The dynamic co-founder and CEO of LangChain, Harrison + Chase is simplifying the creation of applications powered by LLMs. With a background + in statistics and computer science from Harvard University, Chase has carved + a niche in the AI landscape. AIM Brand Solutions, a marketing division within + AIM, specializes in creating diverse content such as documentaries, public artworks, + podcasts, videos, articles, and more to effectively tell compelling stories. + AIM Research produces a series of annual reports on AI & Data Science covering + every aspect of the industry. Discover how Cypher 2024 expands to the USA, bridging + AI innovation gaps and tackling the challenges of enterprise AI adoption AIM + India AIM Research AIM Leaders Council 50 Best Data Science Firms\"}, {\"url\": + \"https://www.turingpost.com/p/harrison-chase-langchain-ai-agents\", \"content\": + \"Harrison Chase, founder of LangChain, shared insights on the evolution of + AI agents and their applications during Sequoia Capital''s AI Ascent. ... Saves + you a lot of research time, plus gives a flashback to ML history and insights + into the future. Stay ahead alongside over 73,000 professionals from top AI + labs, ML startups, and enterprises\"}]", "tool_use_id": "toolu_01LAyiyBfbnEZTebPJRg5MCr", + "is_error": false}]}], "model": "claude-3-5-sonnet-20240620", "system": "You + are a helpful AI assistant.", "tools": [{"name": "search", "description": "Search + for general web results. This function performs a search using the Tavily search + engine, which is designed\nto provide comprehensive, accurate, and trusted results. + It''s particularly useful\nfor answering questions about current events.", "input_schema": + {"properties": {"query": {"type": "string"}}, "required": ["query"], "type": + "object"}}]}' + headers: {} + method: POST + uri: https://api.anthropic.com/v1/messages + response: + body: + string: !!binary | + H4sIAAAAAAAAA3RU0W4bRwz8FeIQoC1wEmQ5KVC/2UZQu5DQNEmf6iKg9nh3jPa45yVPqhD03wuu + LEdx26cFdpfkcGbILxU31VU1aPdpcbFu9q8vfnv/y0/j5frx1j7vbldv391UdWWHkfwXqWJHVV3l + FP0CVVkNxaq6GlJDsbqqQsSpodnl7M1MkwjZbLlYvl78uFxUdRWSGIlVV398OSU1+svDy3FV3aBS + A0nAegIlzKGHTDpF0xruIaBASNJyQ2LxACi6pwyHNGV4nEiNkwBu0mQlQZsmaShDamGF0t32yDJ/ + kAf5+D+PwAp3mDNrErjtUWkO65QJdKTALQeM8XDlGS7mLz56qNcMaXbKjNLA7dtfX5ZfzuHuVL45 + ry0Q0QiWi+WyBhY29nKACiiQRpKZpikHgjGnzxQM9j1Hgn3KW5YO0ABhwNCzEETCLH6rhtmmERw6 + NfA+bSY1uBejGLkjCTR/kMv5GY49KoRMaNSAJRhwS8AGhMqU/aahHcU0Ao5j5IBOusKY9pSpgc0B + Vpg7Kgkn7AjW7gyF71ertf5Q6P+QBgJsGvZQjMBilF096aDFYPqk4QuGnc9nmCcVjk+9kwQbDNsu + O7FOphoaq3HQEhnSME5GGTSwtw1tToOX2GFu4HfhHWVlOxwVepc5lWYLfw7suXINvfPbFLnXT3yv + Tnwb4eBS/AfRNbQpTOq/3OFPDTu2HUZuCpFuln9pWGZLX+r0OHHYxgN0yEINjGmcIma2gzfv2K7v + velhErZDDXu23ofHMm+mo2aFgX6SJlOjXvlJWcrqCH9mu5s2BSAG4x1Bwxom1RKcBHaYOU0KY0Rr + Ux4c4us53Atcj5mjO/my/sbhIeUx5WKtopiLgnIoNTKyD79yJ2XUxKCdpGHp5vCxpwNkCsQ73w87 + yvBquYCBY3TSWE5fj1Owwzg904nmTKp5xNeQ0vsHepwSI9ziyIaxBu1TLoultTLAkiYJJS28uvga + rERusR2pDeQ4PdkNSegHzNv5g7w5F8rNuaHgpk9CDsnVGZLaSTTAjsRmm4ljaaLNOJDPtZ5pqSO6 + h7aS9gJtyi6mUDiac7XWo8KWUtRnzZJombhvJ+k7hR27iseQl0hJivF5GCO3h1J+zCmQFo+U1eA1 + r+9np6E/3wS1bwx/Z4PBdycGD+VNpLPl4RZzkBufB1IlBYy8pXn19591pZbGT/kfpSYW5+cpWSml + 5qXEl5QW5SlBJYpTC0tB+UnJKq80J0dHqRRcK1lVK2XmFZSWxJfkZ6fmFStZGRmYmuoo5ZeWIAsa + mxjW1gIAAAD//wMALzV23/YGAAA= + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 8e22b65b6bda4caf-PHL + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 13 Nov 2024 23:58:59 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + X-Robots-Tag: + - none + anthropic-ratelimit-requests-limit: + - '4000' + anthropic-ratelimit-requests-remaining: + - '3999' + anthropic-ratelimit-requests-reset: + - '2024-11-13T23:58:52Z' + anthropic-ratelimit-tokens-limit: + - '400000' + anthropic-ratelimit-tokens-remaining: + - '400000' + anthropic-ratelimit-tokens-reset: + - '2024-11-13T23:58:59Z' + request-id: + - req_013QF9W14BVn6VHs6PZwfFs7 + via: + - 1.1 google + status: + code: 200 + message: OK +version: 1 diff --git a/tests/integration_tests/test_graph.py b/tests/integration_tests/test_graph.py index d7c03ab..cd90afb 100644 --- a/tests/integration_tests/test_graph.py +++ b/tests/integration_tests/test_graph.py @@ -8,7 +8,8 @@ @unit async def test_react_agent_simple_passthrough() -> None: res = await graph.ainvoke( - {"messages": [("user", "Who is the founder of LangChain?")]} + {"messages": [("user", "Who is the founder of LangChain?")]}, + {"configurable": {"system_prompt": "You are a helpful AI assistant."}}, ) assert "harrison" in str(res["messages"][-1].content).lower()