Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fixes #1963

Open
wants to merge 5 commits into
base: main
Choose a base branch
from
Open

Fixes #1963

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
9471282
added llama3 prompt
hirschrobert Jun 6, 2024
757a8c7
added max_length for embedding models. Some models crash if not provi…
hirschrobert Jun 6, 2024
6af9fb8
While ingesting, some files led to a crash due to encoding error. Eve…
hirschrobert Jun 6, 2024
def2b7f
added window_size setting for ingestion
hirschrobert Jun 6, 2024
b044327
had to add one and update some packages in order not to crash
hirschrobert Jun 6, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions private_gpt/server/ingest/ingest_service.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,13 +39,14 @@ def __init__(
docstore=node_store_component.doc_store,
index_store=node_store_component.index_store,
)
node_parser = SentenceWindowNodeParser.from_defaults()
self._settings = settings()
node_parser = SentenceWindowNodeParser.from_defaults(window_size=self._settings.vectorstore.inject_win_size)

self.ingest_component = get_ingestion_component(
self.storage_context,
embed_model=embedding_component.embedding_model,
transformations=[node_parser, embedding_component.embedding_model],
settings=settings(),
settings=self._settings,
)

def _ingest_data(self, file_name: str, file_data: AnyStr) -> list[IngestedDoc]:
Expand Down
4 changes: 4 additions & 0 deletions private_gpt/settings/settings.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -120,6 +120,10 @@ class LLMSettings(BaseModel):

class VectorstoreSettings(BaseModel):
database: Literal["chroma", "qdrant", "postgres"]
inject_win_size: int = Field(
3,
description="How many sentences on either side to capture, when parsing files",
)
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you move this property to another setting? It would be nice if we have different providers like graphs, elastic search, etc.



class NodeStoreSettings(BaseModel):
Expand Down
1 change: 1 addition & 0 deletions settings.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -74,6 +74,7 @@ huggingface:

vectorstore:
database: qdrant
inject_win_size: 2
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please remove this line or set default value


nodestore:
database: simple
Expand Down