nsbradford / semanticsearch Goto Github PK
View Code? Open in Web Editor NEWMinimal RAG (Retrieval Augmented Generation) website with Pinecone, FastAPI, NextJS, MongoDB
Home Page: https://semantic-search-six.vercel.app
Minimal RAG (Retrieval Augmented Generation) website with Pinecone, FastAPI, NextJS, MongoDB
Home Page: https://semantic-search-six.vercel.app
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.
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.
frontend/src/pages/index.tsx
frontend/src/pages/index.tsx
❌ Sandbox failed so I made additional changesfrontend/src/pages/index.tsx
❌ Sandbox failed so I made additional changesfrontend/src/pages/index.tsx
❌ Sandbox failed so I made additional changesfrontend/src/pages/index.tsx
❌ Sandbox failed so I made additional changesfrontend/src/pages/index.tsx
❌ Sandbox failed so I made additional changesfrontend/src/pages/index.tsx
❌ Sandbox failed so I made additional changesfrontend/src/pages/index.tsx
❌ Sandbox failed so I made additional changesfrontend/src/api/api.ts
backend/main.py
backend/llm.py
backend/models.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 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.
Line 13 in f8189d5
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.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.