RetroSearch Browse

Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Showing content from https://github.com/runtime/langchain-rag-openai below:

runtime/langchain-rag-openai: ingest pdfs, transforms, embeds, stores and tests embeddings against queries

Arduino Sensor RAG w/OpenAI Embedding & Mistral (on Ollama) for Query Match

This is an MVP of a LLM Document Search RAG.

Requirements Doc:

Scan PDF (pypdf) (AWS Textract)
Create pages
Chunk pages (langchain)
Embeddings (openAI)
Store in Vector DB (Chroma)
Test our embeddings (pyTest)
Retrieve with search query (nistral)

run this command to install dependencies in the requirements.txt file.

pip install -r requirements.txt

pip install pytest 
pip install pyPdf

Step 1: Start or Add to Existing Chroma db

To Scan all the pdf files in the data folder and put them into the RAG run:

This will scan the pdfs using pypdf through langchain document loader, split the docs into pages and then will chunk it. Chunks are embedded and stored in Chroma

Step 2: Query the database

Query the Chroma DB and use Mistral to create an answer

python query_data.py "Your question relevant to the context of the application"

Step 3: Test the Query Returns using PyTest and Mistral

Test Mistral's answers using PyTest

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4