nsbradford / semanticsearch Goto Github PK

Get sessionId from the frontend - see index.tsx. Requires adding metadata to llm endpoint and passing through to llm.py

it's currently O(N^2), should be O(N)

Get sessionId from the frontend in index.tsx and pass it through sendLLMRequest in api.ts. Add metadata to llm endpoint in main.py and pass to llm.py - you might have to edit models.py accordingly.

Get sessionId from the frontend in index.tsx and pass it through sendLLMRequest in api.ts. Add metadata to llm endpoint in main.py and pass to llm.py - you might have to edit models.py accordingly.

Make it simple, clean, modern, and tell them to go to 'nsbradford.com' for more info. Also include a link to my twitter: https://twitter.com/n_s_bradford

Get sessionId from the frontend - see index.tsx. Requires adding metadata to llm endpoint and passing through to llm.py

Get sessionId from the frontend - see index.tsx. Requires adding metadata to llm endpoint and passing through to llm.py

instead of 30, performance tuning

Get sessionId from the frontend, pass it all the way through existing endpoints to the llm request metadata

messages should be clear and useful for debugging

Instead of white background, should be dark grey, etc.

Details

Features: Get sessionId from the frontend in index.tsx and pass it through sendLLMRequest in api.ts. Add metadata to llm endpoint in main.py and pass to llm.py - you might have to edit models.py accordingly.

Get sessionId from the frontend in index.tsx and pass it through sendLLMRequest in api.ts. Add metadata to llm endpoint in main.py and pass to llm.py - you might have to edit models.py accordingly.

Get sessionId from the frontend in index.tsx and pass it through sendLLMRequest in api.ts. Add metadata to llm endpoint in main.py and pass to llm.py - you might have to edit models.py accordingly.

Get sessionId from the frontend in index.tsx and pass it through sendLLMRequest in api.ts. Add metadata to llm endpoint in main.py and pass to llm.py - you might have to edit models.py accordingly.

Get sessionId from the frontend - see index.tsx. Requires adding metadata to llm endpoint and passing through to llm.py

Get sessionId from the frontend in index.tsx and pass it through sendLLMRequest in api.ts. Add metadata to llm endpoint in main.py and pass to llm.py - you might have to edit models.py accordingly.

Get sessionId from the frontend - see index.tsx. Requires passing it through api.ts. Add metadata to llm endpoint in main.py, and passing through to llm.py

Get sessionId from the frontend in index.tsx and pass it through sendLLMRequest in api.ts. Add metadata to llm endpoint in main.py and pass to llm.py - you might have to edit models.py accordingly.

Get sessionId from the frontend in index.tsx and pass it through sendLLMRequest in api.ts. Add metadata to llm endpoint in main.py and pass to llm.py - you might have to edit models.py accordingly.

Get sessionId from the frontend - see index.tsx.Requires adding metadata to llm endpoint and passing through to llm.py

Get sessionId from the frontend - see index.tsx. Requires adding metadata to llm endpoint.

Add a new top-level heading with a one-paragraph description

Get sessionId from the frontend in index.tsx and pass it through sendLLMRequest in api.ts. Add metadata to llm endpoint in main.py and pass to llm.py - you might have to edit models.py accordingly.

Just a friendly request regarding various Vector DB integrations and not tightly couple with pinecone for example. I came across the following open-source code and started to love the way how the Vector DBs are incorporated into the library.

https://github.com/abhishek-ch/VectorVerse

Hey @nsbradford,

I saw you're logging responses to promptlayer but also using helicone. Curious - why?

If it's for caching - is there something in our implementation you think is missing - https://docs.litellm.ai/docs/caching/

Get sessionId from the frontend in index.tsx and pass it through sendLLMRequest in api.ts. Add metadata to llm endpoint in main.py and pass to llm.py - you might have to edit models.py accordingly.

should use logger.info() everywhere

Get sessionId from the frontend in index.tsx and pass it through sendLLMRequest in api.ts. Add metadata to llm endpoint in main.py and pass to llm.py - you might have to edit models.py accordingly.