Skip to main content

Financial Data Assistant - A PocketFlow-based LLM library for financial data chat with tool calling

Project description

LLMFA Agent

A PocketFlow-based Python library for financial data chat with tool calling using Gemini AI.

Installation

pip install llmfa-agent

Quick Start

import asyncio
from src import generate_response

async def main():
    response = await generate_response([
        {"role": "user", "content": "What's the current price of NVDA?"}
    ])
    
    print(response.response)      # The assistant's reply
    print(response.tool_calls)    # Tools called with results
    print(response.sources)       # Retrieved documents

asyncio.run(main())

Environment Variables

export GEMINI_API_KEY=your_gemini_api_key
export MONGO_CONNECTION_STRING=mongodb+srv://...  # Optional

Features

  • 🤖 Gemini 3 Flash - Powered by Google's latest AI model
  • 🔧 Tool Calling - Automatic function execution for stock data
  • 📊 Real-time Data - Live stock prices via yfinance
  • 📚 RAG Support - Vector search for document retrieval
  • 🌐 Multilingual - Thai and English language support

Available Tools

  • get_minute_bars: Real-time 1-minute OHLCV data (via yfinance)
  • get_market_data: Historical stock data from MongoDB
  • vector_search: Semantic search for financial documents

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

llmfa_agent-0.1.0.tar.gz (10.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

llmfa_agent-0.1.0-py3-none-any.whl (12.6 kB view details)

Uploaded Python 3

File details

Details for the file llmfa_agent-0.1.0.tar.gz.

File metadata

  • Download URL: llmfa_agent-0.1.0.tar.gz
  • Upload date:
  • Size: 10.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.9

File hashes

Hashes for llmfa_agent-0.1.0.tar.gz
Algorithm Hash digest
SHA256 96fecf844148b0fa357a90b882f7140fb449f08c95d552b0b83dc037d0258903
MD5 4b4cc5db3e9d10e2ea406227ec68459c
BLAKE2b-256 67d23f8e9f82144aae0bb071673547f1fc37c289b3e9af4be0ca231682cf9785

See more details on using hashes here.

File details

Details for the file llmfa_agent-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: llmfa_agent-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 12.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.9

File hashes

Hashes for llmfa_agent-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 f22ebf69df6ea3c95395103943b94969ed63cb548b9119115041d60e49663998
MD5 a552a2acfc668151041aa18848714821
BLAKE2b-256 50d1d115b2b00503926ccd4ce4e45b0be4f286cd3865b4a3a7010f47f6bc77c5

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page