Quickstart

1. Clone the Repository

git clone https://github.com/sidxz/docu-store.git
cd docu-store/services

2. Configure Environment

Copy the example environment file and adjust settings:

cp .env.example .env

Key settings to configure:

# LLM Provider (ollama, openai, or gemini)
LLM_PROVIDER=ollama
LLM_BASE_URL=http://host.docker.internal:11434

# Embedding model
EMBEDDING_MODEL=nomic-embed-text-v1.5
EMBEDDING_DEVICE=cpu

3. Start the Stack

make docker-up

This starts all infrastructure services and the DocuStore application. The first startup takes a few minutes as Docker pulls images and initializes databases.

4. Verify Services

Once running, verify the services are healthy:

• API: http://localhost:8000/docs — FastAPI Swagger UI
• EventStoreDB: http://localhost:2113 — Admin dashboard
• Temporal: http://localhost:8233 — Workflow dashboard
• Qdrant: http://localhost:6333/dashboard — Vector DB dashboard

5. Upload Your First Document

curl -X POST http://localhost:8000/artifacts \
  -F "file=@/path/to/your/document.pdf" \
  -F "name=My Research Paper"

DocuStore will automatically:

1. Parse pages from the PDF
2. Extract chemical compounds (OCSR)
3. Run named entity recognition (NER)
4. Generate page and document summaries
5. Create text, summary, and SMILES embeddings

Monitor progress in the Temporal dashboard at http://localhost:8233.

6. Search Your Documents

Once processing completes, search via the API:

# Text search
curl "http://localhost:8000/search/pages?q=kinase+inhibitor"

# Hierarchical search (summaries + chunks)
curl -X POST http://localhost:8000/search/hierarchical \
  -H "Content-Type: application/json" \
  -d '{"query": "What compounds showed selectivity for CDK4?"}'

Next Steps

• Configuration Reference — all environment variables
• Production Deployment — Docker Swarm setup
• Architecture Overview — understand the pipeline