FBR_65 comments

Results 8 comments of


                                            FBR_65

Can't fetch Embedding Model because of Proxy

"use the configured proxy" -> normaly there is a proxy configuration either in Windows or Linux. This is set in the environment variables.

Can't fetch Embedding Model because of Proxy

Hi, it's works like a charm ;) Thanks

local llms without using Ollama -with vllm or huggingface

I'm also interessted in vllm connections.

Iteration component get stucked, and can't iterate

Here the same problem. Iteration works with 1 chunk. Iteration get stuck with iteration > 1. But not always at the same time. Sometimes it iterates until 3 and sometimes...

Iteration component get stucked, and can't iterate

Hi, yes, I'll will paste a screenshot. I coded the same iteration in python and I got an error, because of "openai.APITimeoutError: Request timed out". It might also be the...

Iteration component get stucked, and can't iterate

Hi, thanks for the support. In the meanwhile I could figure out, that the problem was lying in the tested Text. It was chunked in a bad manor so that...

Vllm or Huggingface for local LLMs for CrewAI

I have the same request features.

Vllm or Huggingface for local LLMs for CrewAI

Hi, my solution on this request: ```python from langchain_openai import ChatOpenAI as LOAI os.environ["OPENAI_API_KEY"] = "NA" llm_model = LOAI(base_url="http://your_endpoint/v1", model_name = 'your_model') your_agent = Agent( role="Your Role", goal="Your goal", backstory="Your...