Quickstart: Document Memory

Ingest documents and query them through memory search.

What You Will Build

• Upload a document for processing
• Track document processing status
• Retrieve relevant context through memory search

Prerequisites

• PAPR_MEMORY_API_KEY configured in your environment
• A local PDF or Word document available for upload

Minimal Setup

1. Upload the document and save upload_id.
2. Poll status until processing finishes.
3. Search for one grounded answer.

1) Upload a Document

curl -X POST https://memory.papr.ai/v1/document \
  -H "X-API-Key: $PAPR_MEMORY_API_KEY" \
  -H "X-Client-Type: curl" \
  -F "file=@contract.pdf" \
  -F "external_user_id=user_123" \
  -F "organization_id=org_demo"

Save upload_id from the response.

2) Poll Processing Status

curl -X GET "https://memory.papr.ai/v1/document/status/$UPLOAD_ID" \
  -H "X-API-Key: $PAPR_MEMORY_API_KEY" \
  -H "X-Client-Type: curl"

3) Search Document Memory

curl -X POST "https://memory.papr.ai/v1/memory/search?max_memories=20&max_nodes=15" \
  -H "X-API-Key: $PAPR_MEMORY_API_KEY" \
  -H "Content-Type: application/json" \
  -H "X-Client-Type: curl" \
  -d '{
    "query": "What are termination clauses and notice periods in our latest contract?",
    "external_user_id": "user_123",
    "organization_id": "org_demo",
    "enable_agentic_graph": true
  }'

Validation Checklist

• Upload returns a valid upload_id.
• Status endpoint reaches a completed state.
• Search returns memory tied to document content.

Troubleshooting

If search returns weak results, wait for processing completion and check Document Processing Guide.

Next Steps

• Document Processing Guide
• Retrieval Guide
• Golden Paths