Add .tsv files to exclusion list

Add "migrations" folder to exclusion list

update broken discord link

Nits to README for NVIDIA reranker

Fix Marqo namespace issue. (#45)

download nltk if not detected (#42)

fix merge conflict

sage env

Pass access_token in the constructor of DataManagers.

Bump package version

move punkt download to vector store where it's actually used

Update vector_store.py

Take "namespace" out of the vector store constructors.

download nltk if not downloaded

README nit

Add instructions for private repositories

Script to run retrieval for the Kaggle competition

Retrieval benchmark (#39)

Add YAML configurations (#38)

Split --index-name flag into --pinecone-index-name and --index-namespace.

Option to index repo at specific commit.

Add Cohere, NVIDIA, Jina & HuggingFace rerankers (#37)

Update README.md

Update README.md

Add link to Discord channel.

Add missing pinecone-text dependency

Add option for Pinecone + BM25 hybrid retrieval. (#36)

Now that we have a reranker, retrieve 25 items from the vector DB.

Streaming responses.

Add Hugging Face cross-encoders

Add Cohere reranker

Simplify name to "Sage" (#35)

Move badges higher.

Further hack on README.

KBD hack for image border

Rename repo2vec to CodeSage (#34)

Add warning about quick development

Fix crashes on typescript parsing

Bump version

Option to not store file chunk content to vector store

Default to Marqo to simplify "Getting started"

Add option to exclude based on file and folder name, not just extension.

Fix IpynbChunker and add unit tests.

Minor README clarifications (#29)

Rename index/chat commands to avoid clash with local utilities (#31)

Default readme remote options to closed (#28)

Improve the docs based on stargazers' feedback (#25)

fix: Use `elif` which is possibly the intended behavior (#23)

The vector store shouldn't expect a "filename" in the metadata.

Downgrade fastapi, otherwise chat doesn't work.