dealflow-ai / README.md
PeterBot22's picture
fix: switch to Docker SDK for full build control
b81fb8e verified
metadata
title: DealFlow AI
emoji: πŸ“Š
colorFrom: blue
colorTo: indigo
sdk: docker
app_port: 7860
pinned: false
license: mit
extra_gated_prompt: Please provide your HF_TOKEN and SERPER_API_KEY as Space secrets.

DealFlow AI

Multi-Agent Investment Due Diligence System AMD Developer Hackathon 2026 | CrewAI v1.0 + Qwen2.5-72B + HuggingFace Inference


What It Does

Upload a startup pitch deck PDF β†’ DealFlow AI deploys a 3-agent crew that:

  1. Researcher β€” extracts key claims from the pitch deck, searches the web for market validation and competitor analysis
  2. Financial Analyst β€” validates financial projections, models unit economics using Python/pandas
  3. Report Writer β€” synthesizes all findings into a professional investment memo

Quick Start (Local)

# 1. Enter project directory
cd dealflow-ai

# 2. Copy and fill in env vars
cp .env.example .env
# Edit .env: SERPER_API_KEY, HF_TOKEN

# 3. Install dependencies
pip install -r requirements.txt

# 4. Launch the app
python app.py
# β†’ Opens at http://localhost:7860

Agent Tools (per PRE-FLIGHT SPEC #1 β€” exact, no improvisation)

Agent CrewAI Tools
Researcher SerperDevTool, ScrapeWebsiteTool, WebsiteSearchTool, PDFSearchTool, FileReadTool
Financial Analyst CodeInterpreterTool, CSVSearchTool, JSONSearchTool, FileReadTool
Report Writer FileReadTool, RagTool

Inference Stack

Component Value
Model Qwen/Qwen2.5-72B-Instruct
Provider HuggingFace Serverless (featherless-ai router)
Search Serper.dev API

Deployment

AMD Fallback Protocol (PRE-FLIGHT SPEC #3) β€” ACTIVATED

Checkpoint Condition Action
T+12h MI300X not provisioned Begin parallel HF Endpoints setup as hot standby
T+60h Still no AMD credits LOCK HF fallback. Abandon AMD-specific bonus.
T+100h MI300X recovered late Do NOT switch back. HF is locked.

AMD Fallback ACTIVATED at T+63h (2026-05-06). AMD MI300X credits did not arrive by the T+60h checkpoint. Primary backend switched to HuggingFace Serverless Inference API (Qwen/Qwen2.5-72B-Instruct via featherless-ai provider). The AMD MI300X hardware-specific judging criterion is forfeited. The project qualifies for the AI Agents track and HuggingFace Space bonus criterion. Pitch narrative: "AMD-optimized architecture, deployed on HuggingFace infrastructure."

HF Space Environment Variables

Set these as Space Secrets in the HF Space settings:

Variable Description
SERPER_API_KEY Serper.dev API key for web search
HF_TOKEN HuggingFace token for inference
LLM_BACKEND Set to hf (default)

Configuration

See .env.example for all options.

Running Tests

pip install pytest
pytest tests/ -v
# Expected: 19 passed, 1 skipped

Architecture

See 03-mvp/architecture.md for full architecture diagram.


Built for AMD Developer Hackathon 2026 DealFlow AI β€” Multi-agent investment due diligence on HuggingFace Spaces