danieldekay

Is your .env file correct and in the right place?

One way to do that would be to utilize a) Quarto - incl. code execution blocks b) Pandoc: Markdown -> Latex -> PDF

Additionally, I have noticed that it likes to grab the literature appendix from my documents as related content, and not text from the actual article: 

I have an idea, why the references are not listed: for local documents the URLs are never set to the document file urls, or anything else. ```python async def _construct_detailed_report(self,...

This sounds like a good plan, @DandinPower! I have experience with converting transcripts of interviews, which might jump between topics, into a coherent report that keeps details (unlike a "summarize...

@DandinPower, LangGraph also has a human-in-the-loop feature, and we might also want to ask a human on the highest abstraction level of the report structure to provide editorial feedback. This...

@DandinPower , I am also reading the STORM paper (https://arxiv.org/pdf/2402.14207) which has loads more insights into possible processes.

@bat9527, please try the current master branch. Does it work? PS: We are also using AzureOpenAI, and I'd love for this to be stable.

This is working for me now, as described in https://github.com/assafelovic/gpt-researcher/issues/1061#issuecomment-2589862435 I did, however, request more TPM quota: I have 700k/minute now, but still hit the rate limiting a lot. However,...

FWIW: [task_1736860372_How to deal with 429 errors in Azure OpenAI .pdf](https://github.com/user-attachments/files/18410832/task_1736860372_How.to.deal.with.429.errors.in.Azure.OpenAI.pdf)