Ofer Mendelevitch

For a categorical variable, is there a way to get the categorical value that has the highest count (like mode() in python)?

# Vectara Integration This PR provides integration with Vectara. Implemented here are: * langchain/vectorstore/vectara.py * tests/integration_tests/vectorstores/test_vectara.py * langchain/retrievers/vectara_retriever.py And two IPYNB notebooks to do more testing: * docs/modules/chains/index_examples/vectara_text_generation.ipynb * docs/modules/indexes/vectorstores/examples/vectara.ipynb

Vectara integration

6

## Description This provides an integration with Vectara as a vector DB as well as RAG platform. ## Type of change Please delete options that are not relevant. - [X]...

It would be great to add NLTK to the default set of packages installed.

Vectara integration

1

Adding Vectara as a Results Storage option

community: Vectara Integration Update - Streaming, FCS, Chat, updates to documentation and example notebooks

2

Thank you for contributing to LangChain! **Description:** update to the Vectara / Langchain integration to integrate new Vectara capabilities: - Full RAG implemented as a Runnable with as_rag() - Vectara...

Is it possible for convert() to return generators?

2

### Question I have a pretty large PDF document that I'm trying to convert, and often run OOM. Clearly I can increase memory, but that's not as scalable. is it...

# Description Added Vectara part_metadata to returned Node metadata. Now the "metadata" in each node is the part_metadata from Vectara, and document level metadata comes as a sub-dictionary with the...

added open-rag-eval

2

Added for RAG evaluation with example notebook.

Added a category for RAG (Retrieval augmented generation) - representing systems that provide the full query functionality over an end-to-end RAG system. Added Vectara as the first entry there.