Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The following PR adds support for local LLMs that are running through an Ollama server. As the
TextGenerationInference
custom AIs were no longer supported, the config objectai_custom
has been repurposed for specifying Ollama models to connect to. The reason Ollama was chosen is due to the wide array of available models that they support. As Ollama supports ChatModels directly (rather than text completion models), the ESBMC-AI code has been adapted to use Chat style code only from Lang Chain for simplicity. Additionally, the parameterserver_type
has been added, which in the future could provide additional types of server support. Currently, it only supportsollama
.This PR closes #138
Example config: