OLLAMA + LLAMA3 + RAG + Vector Database (Local, Open Source, Free)

출처: https://dev.to/tspannhw/ollama-llama3-rag-vector-database-local-open-source-free-1fid

OLLAMA + LLAMA3 + RAG + Vector Database (Local, Open Source, Free)

#milvus#rag#genai#ollama

https://dzone.com/articles/multiple-vectors-and-advanced-search-data-model-design

https://github.com/tspannhw/AIM-NYCStreetCams/blob/main/MultipleVectorsAdvanced%20SearchDataModelDesign/streetcamsrag.ipynb

Utilizing Multiple Vectors and Advanced Search Data Model Design
Goal of this Application
In this application, we will build an advanced data model and use it for ingest and various search options.

1️⃣ Ingest Data Fields, Enrich Data With Lookups, and Format :
Learn to ingest data from including JSON and Images, format and transform to optimize hybrid searches. This is done inside the streetcams.py application.

2️⃣ Store Data into Milvus:
Learn to store data into Milvus, an efficient vector database designed for high-speed similarity searches and AI applications. In this step we are optimizing data model with scalar and multiple vector fields -- one for text and one for the camera image. We do this in the streetcams.py application.

3️⃣ Use Open Source Models for Data Queries in a Hybrid Multi-Modal, Multi-Vector Search:
Discover how to use scalars and multiple vectors to query data stored in Milvus and re-rank the final results in this notebook.

4️⃣ Display resulting text and images:
Build a quick output for validation and checking in this notebook.

5️⃣ Simple Retrieval-Augmented Generation (RAG) with LangChain:
Build a simple Python RAG application (streetcamrag.py) to use Milvus for asking about the current weather via OLLAMA. While outputing to the screen we also send the results to Slack formatted as Markdown.

🔍 Summary
By the end of this application, you’ll have a comprehensive understanding of using Milvus, data ingest object semi-structured and unstructured data, and using Open Source models to build a robust and efficient data retrieval system. For future enhancements, we can use these results to build prompts for LLM, slack bots, streaming data to Kafka and as a Street Camera search engine.

diagram

Future Features
https://github.com/tspannhw/AIM-AirQuality/tree/main
Resources
https://511ny.org/developers/help/api/get-api-getcameras_key_format
https://zilliz.com/blog/building-multilingual-rag-milvus-langchain-openai
https://medium.com/@tspann/utilizing-multiple-vectors-and-advanced-search-data-model-design-for-city-data-705d68d8daf2
https://www.youtube.com/watch?v=HaRc0rsaMo0
https://dzone.com/articles/multiple-vectors-and-advanced-search-data-model-design