James Braza comments

Results 182 comments of


                                            James Braza

client.model_name doesn't work for langchain ChatAnthropic

Similar issue to https://github.com/Future-House/paper-qa/issues/279, please see its resolution

Update README with separate vector database example

This is roughly documented in https://github.com/Future-House/paper-qa/tree/v5.0.0?tab=readme-ov-file#using-external-dbvector-db-and-caching. It can definitely use more information, we are open to docs contributions

wrong citations if initiate the Docs object with texts_index

> Any guidance how to integrate with external vector db such as chromadb? I don't find any documentation for the same. This was asked for in https://github.com/Future-House/paper-qa/issues/153, you can see...

Exception: "cannot pickle '_thread.RLock' object" from "import paperqa" (dependency on openai <= 0.28.1?)

Looks like this was resolved in v4. We also have released v5 today which again totally changes the dependencies, and depends on Pydantic v2

Add docx reader

Hi @NISH1001 thank you for this PR. We just released v5 today which changes basically the whole repo. If you are still interested, please rebase this PR atop the current...

Cache embeddings and OCR results?

@MilesCranmer we just released version 5 today that: - Moves all LLM management to https://github.com/BerriAI/litellm - Drops both LangChain and faiss from dependencies - Centers on a directory of texts...

adding support for claude, azure, cohere, replicate

Implemented by https://github.com/Future-House/paper-qa/pull/362. Thank you @krrishdholakia for the contribution, we are big fans of LiteLLM!

Local LLM ISSUE GGML_ASSERT

Hello everyone, we have just released version 5, which completely outsources all LLM management to https://github.com/BerriAI/litellm. If your issue persists, please reopen a new issue using `paper-qa>=5`

minimal example of how to use FAISS: storing, combining, reusing

Hi @daliagachc yes we can use a docs contribution here. Feel free to make one

Pydantic throwing an error when following example code

It's because `Docs` forbids extra parameters: https://github.com/Future-House/paper-qa/blob/v4.9.0/paperqa/docs.py#L75 It looks like you were trying to set an `embedding_model`, which is not an attribute of `Docs`. What you should do instead is...