Federico Aguzzi comments

Results 25 comments of


                                            Federico Aguzzi

Case XX: Extracting information using aws Bedrock

Check out [this gist](https://gist.github.com/JGalego/67a3db0005f5ed052224e549e8ee627c). As soon as #228 gets merged, Bedrock will be fully supported.

json.decoder.JSONDecodeError: Expecting value: line 10 column 5 (char 743)

Is this the complete `JSON`? Does it actually contain `...` at the end of `links` and `images` or is this a shortened version?

How to custom base_url for OpenAI request?

Try this: ```python graph_config = { "llm": { "model": "gpt-3.5-turbo", "api_key": "YOUR_API_KEY", "temperature": 0, "openai_api_base": "https://your_custom_url.com", }, } ``` The recent `DeepSeek` implementation we added in the latest beta is...

Replace poetry

I'll take this, assign me @VinciGit00

OMP: Error #15: Initializing libiomp5md.dll, but found libomp140.x86_64.dll already initialized

@baggiponte might this be related to the dependency clashes caused by Poetry you mentioned in issue #198?

feat: add deepseek-chat

I'm working on this with @VinciGit00 's supervision. We'll figure this out soon.

langchain_core.exceptions.OutputParserException: Invalid json output: I'm ready to answer your question about the content I've scraped. What would you like to know?

From the weirdness of the error message, it looks like the LLM has replied with words (in a chat-like way, by saying it's ready to analyze the scraped data) instead...

Federico Aguzzi