Dellagi/FinAI-Agent-RAG-Spark-Pipeline

A sophisticated trading system leveraging local LLM deployment through Ollama, distributed computing with Apache Spark, and vector-based episodic memory using ChromaDB to make intelligent trading decisions.

17
/ 100
Experimental

Combines hybrid RAG retrieval (BM25 + dense embeddings with cross-encoder reranking) with Kafka stream processing for real-time multi-symbol analysis, backed by ChromaDB's semantic memory with importance scoring and automatic consolidation. Integrates Alpaca market data feeds and finance-tuned local LLM inference to aggregate multi-source research, technical indicators, and sentiment analysis into a unified trading decision pipeline with configurable relevance thresholds and temporal context filtering.

No commits in the last 6 months.

No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 1 / 25
Community 10 / 25

How are scores calculated?

Stars

15

Forks

2

Language

Python

License

Last pushed

Feb 03, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/Dellagi/FinAI-Agent-RAG-Spark-Pipeline"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.