https://github.com/stackmodel/autogen-financial-analyst

Demonstrates how to build and coordinate multiple AI agents to tackle complex tasks
https://github.com/stackmodel/autogen-financial-analyst

anthropic autogen aws bedrock finance financial-analysis python

Last synced: about 2 months ago
JSON representation

Demonstrates how to build and coordinate multiple AI agents to tackle complex tasks

• Host: GitHub
• URL: https://github.com/stackmodel/autogen-financial-analyst
• Owner: stackmodel
• License: mit
• Created: 2024-11-28T19:10:48.000Z (2 months ago)
• Default Branch: main
• Last Pushed: 2024-12-02T22:45:43.000Z (2 months ago)
• Last Synced: 2024-12-06T16:32:46.740Z (about 2 months ago)
• Topics: anthropic, autogen, aws, bedrock, finance, financial-analysis, python
• Language: Python
• Homepage:
• Size: 8.79 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: readme.md
  • License: LICENSE

Awesome Lists containing this project

README

        
**AutoGen Financial Analyst**

This demo demonstrates 

-  How to build and coordinate multiple AI agents to solve complex tasks using Microsoft's AutoGen.

-  How AutoGen can be integrated with AWS Bedrock.

-  How two agents, code_executor_agent and code_writer_agent, collaborate to complete a task of analyzing stock data and plotting a graph. 

The code_writer_agent uses the anthropic.claude-3-sonnet model to generate Python code, which is then executed locally by the code_executor_agent.

**Pricing** - https://aws.amazon.com/bedrock/pricing/

**Steps to run this demo**

1. Clone the repo and run the command

   - cd autogen-financial-analyst

2. Rename .env.example to .env and populate it with your aws credentials

3.  run below commands 

    - python -m venv venv

    - source venv/bin/activate

    - pip install -r requirements.txt

    - python app.py

After successful run, you should see the generated Python code and YTD graph in the coding directory.

**credits / references**

https://microsoft.github.io/autogen/0.2/docs/topics/code-execution/cli-code-executor

https://microsoft.github.io/autogen/0.2/docs/topics/non-openai-models/cloud-bedrock