Rip&Tear comments

Results 77 comments of


                                            Rip&Tear

Error："Unknown request URL: POST /openai/v1/embeddings. Please check the URL for typos " when using groq API

https://docs.crewai.com/core-concepts/Memory/#how-memory-systems-empower-agents - read this, you are using a non openai endpoint. by default memory uses Openai - you need to specify an embedding

Error："Unknown request URL: POST /openai/v1/embeddings. Please check the URL for typos " when using groq API

correct, Embedchain is used for RAG / Memory and they do not currently support Ollama so that an issue that cannot be resolved by crewai. there is a PR for...

Azure Openai support in tool config

> Same question, anyone figure out this? https://github.com/crewAIInc/crewAI/issues/541#issuecomment-2118393378

undocumented sqlite3 dependency

Investigating

undocumented sqlite3 dependency

> This continues to be an issue for me, what's the solution? currently have in my requirements.txt > > crewai crewai[tools] chromadb==0.4.0 pysqlite3-binary>=0.5.0 Hi @dregules, I am struggling to reproduce...

how to use crewAI for existing code with multiple files and nested multiple folders ?

need more context as to what your problem is here

Any way to set crew Input Arguments at runtime?

You dont need to use the inputs method, you can just define it all in your agents / tasks for example

the result of Full blog post by official demo is too short and meaningless ,how to optimize it

Change your task description to tell it to be longer

the result of Full blog post by official demo is too short and meaningless ,how to optimize it

Have you refined the prompt?

the result of Full blog post by official demo is too short and meaningless ,how to optimize it

No I don't, a prompt that works for somebody else may not work for you, this is an iterative process where you refine the prompt till you get the output...