{"id":"0a0bdaaf-f18f-409c-8056-430f0f481fa2","entityType":"agent","slug":"crewai-diptij85-doc-intelligence-crew","name":"doc-intelligence-crew","canonicalUrl":"https://www.xpersona.co/agent/crewai-diptij85-doc-intelligence-crew","canonicalPath":"/agent/crewai-diptij85-doc-intelligence-crew","generatedAt":"2026-10-08T23:17:43.573Z","source":"GITHUB_OPENCLEW","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-05-31T06:18:23.198Z","emptyReason":null},"description":"Production-grade multi-agent AI system for enterprise contract analysis. CrewAI + Agentic RAG + Pinecone + GCS + FastAPI + Streamlit — deployed on Google Cloud Run 📄 Document Intelligence Crew !PineCone Vector DB https://app.pinecone.io/organizations A production-grade multi-agent AI system for enterprise contract analysis. Upload vendor contracts (PDF, DOCX, XLSX) and get instant risk assessment, compliance flags, and executive recommendations — powered by Agentic RAG and a 5-agent CrewAI pipeline. --- 🏗️ Architecture 📄 Documents (PDF + DOCX + XLSX) ↓ [RAG Pipeline] → chunk","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. Last updated 5/31/2026.","installCommand":"git clone https://github.com/DiptiJ85/doc-intelligence-crew.git","sourceUrl":"https://github.com/DiptiJ85/doc-intelligence-crew","homepage":null,"primaryLinks":[{"label":"View Source","url":"https://github.com/DiptiJ85/doc-intelligence-crew","kind":"source"}],"safetyScore":66,"overallRank":27.2,"popularityScore":0,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Production-grade multi-agent AI system for enterprise contract analysis. CrewAI + Agentic RAG + Pinecone + GCS + FastAPI + Streamlit — deployed on Google Cloud "},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-05-31T06:18:23.198Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[{"label":"crewai","status":"self-declared"},{"label":"multi-agent","status":"self-declared"}],"verifiedCount":0,"selfDeclaredCount":3,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"},{"key":"crewai","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"},{"key":"multi-agent","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile capability:crewai|supported|profile capability:multi-agent|supported|profile"}},"adoption":{"evidence":{"source":"no-adoption-signals","verified":false,"confidence":"low","updatedAt":"2026-05-31T06:18:23.198Z","emptyReason":"No source adoption metrics were available."},"stars":0,"forks":0,"downloads":null,"packageName":null,"latestVersion":null,"tractionLabel":null},"release":{"evidence":{"source":"agent-index","verified":false,"confidence":"medium","updatedAt":"2026-05-31T06:18:23.198Z","emptyReason":null},"lastUpdatedAt":"2026-05-31T06:18:23.198Z","lastCrawledAt":"2026-05-31T06:18:23.198Z","lastIndexedAt":null,"nextCrawlAt":"2026-06-07T06:18:23.198Z","lastVerifiedAt":null,"highlights":[]},"execution":{"evidence":{"source":"GITHUB OPENCLEW","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"git clone https://github.com/DiptiJ85/doc-intelligence-crew.git","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/crewai-diptij85-doc-intelligence-crew/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-diptij85-doc-intelligence-crew/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-diptij85-doc-intelligence-crew/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/crewai-diptij85-doc-intelligence-crew/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-diptij85-doc-intelligence-crew/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-diptij85-doc-intelligence-crew/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"GITHUB_OPENCLEW","generatedAt":"2026-10-08T23:17:43.573Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/crewai-diptij85-doc-intelligence-crew/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/crewai-diptij85-doc-intelligence-crew/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-diptij85-doc-intelligence-crew/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-diptij85-doc-intelligence-crew/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"GITHUB OPENCLEW","verified":false,"confidence":"high","updatedAt":"2026-05-31T06:18:23.198Z","emptyReason":null},"readme":"# 📄 Document Intelligence Crew\n\n![Python](https://img.shields.io/badge/Python-3.12-blue)\n![CrewAI](https://img.shields.io/badge/CrewAI-Multi--Agent-green)\n![FastAPI](https://img.shields.io/badge/FastAPI-REST%20API-009688)\n![Streamlit](https://img.shields.io/badge/Streamlit-UI-FF4B4B)\n!PineCone Vector DB https://app.pinecone.io/organizations\n![Gemini](https://img.shields.io/badge/Gemini-2.5%20Flash-4285F4)\n\n> A production-grade multi-agent AI system for enterprise contract analysis.\n> Upload vendor contracts (PDF, DOCX, XLSX) and get instant risk assessment,\n> compliance flags, and executive recommendations — powered by Agentic RAG\n> and a 5-agent CrewAI pipeline.\n\n---\n\n## 🏗️ Architecture\n\n📄 Documents (PDF + DOCX + XLSX)\n↓\n[RAG Pipeline]   → chunk → embed → Pinecone Vector DB\n↓\n[RAG Agent]      → autonomous search + rerank + reflect\n↓\n[Extractor]      → ExtractedDoc (Pydantic)\n↓\n[Analyst]        → AnalysisResult (Pydantic)\n↓\n[Action Planner] → ActionPlan (Pydantic)\n↓\n[Summary Agent]  → Executive Report\n↓\n[FastAPI]        → REST endpoints\n[Streamlit]      → Interactive UI\n\n---\n\n## ✨ Key Features\n\n- **Multi-Agent Orchestration** — 5 specialized CrewAI agents with typed handoffs\n- **Agentic RAG** — autonomous retrieval with re-ranking and self-reflection\n- **Multi-Format Ingestion** — PDF, DOCX, XLSX document support\n- **Pydantic Typed Contracts** — strongly typed inter-agent schemas\n- **Vector Semantic Search** — Pinecone VectorDB + Google text-embedding-001\n- **Re-ranking** — cross-encoder scoring for precision retrieval\n- **Self-Reflection** — agent evaluates its own retrieval completeness\n- **REST API** — FastAPI with 4 endpoints + Swagger docs\n- **Interactive UI** — Streamlit with file upload and live agent traces\n- **PII Detection** — sensitive data flagged in contract analysis\n- **Structured Logging** — timestamped log files per run\n\n---\n\n## 🛠️ Tech Stack\n\n| Layer | Technology |\n|---|---|\n| **Agent Orchestration** | CrewAI |\n| **LLM** | Google Gemini 2.5 Flash |\n| **Embeddings** | Google gemini-embedding-001 |\n| **Vector Store** | Pinecone VectorDB |\n| **RAG Strategy** | Agentic RAG + Re-ranking + Reflection |\n| **Typed Contracts** | Pydantic AI |\n| **Backend API** | FastAPI + Uvicorn |\n| **Frontend UI** | Streamlit |\n| **Document Parsing** | PyMuPDF, python-docx, openpyxl |\n| **Observability** | Structured logging |\n| **Language** | Python 3.12 |\n\n---\n\n## 📁 Project Structure\ndoc-intelligence-crew/\n├── agents/                    # CrewAI agent definitions\n│   ├── rag_agent.py           # Agentic RAG with search + rerank + reflect\n│   ├── extractor_agent.py     # Contract data extraction\n│   ├── analyst_agent.py       # Risk classification\n│   ├── action_agent.py        # Action planning\n│   └── summary_agent.py      # Executive summary\n├── tasks/                     # Task definitions per agent\n├── schemas/                   # Pydantic typed inter-agent contracts\n│   └── contract_schemas.py    # ExtractedDoc, AnalysisResult, ActionPlan\n├── tools/                     # CrewAI tools\n│   ├── search_tool.py         # Pinecone VectorDB semantic search\n│   ├── reranker_tool.py       # Cross-encoder re-ranking\n│   └── reflection_tool.py     # Coverage self-reflection\n├── config/                    # Configuration\n│   └── llm_config.py          # LLM + PineCone VectorDB setup\n├── pipeline/                  # RAG ingestion pipeline\n│   └── rag_pipeline.py        # Load → chunk → embed → store\n├── api/                       # FastAPI routes\n│   └── routes/\n│       ├── analyze.py         # POST /analyze\n│       ├── documents.py       # GET /documents, POST /upload\n│       └── health.py          # GET /health\n├── data/                      # Contract documents (PDF, DOCX, XLSX)\n├── logs/                      # Timestamped run logs\n├── app.py                     # FastAPI entry point\n├── streamlit_app.py           # Streamlit UI\n└── orchestrator.py            # Full crew orchestration\n\n---\n\n## 🚀 Quick Start\n\n### Prerequisites\n- Python 3.12+\n- Google Gemini API key ([get one here](https://aistudio.google.com))\n\n### Installation\n\n```bash\n# clone the repo\ngit clone https://github.com/YOUR_USERNAME/doc-intelligence-crew.git\ncd doc-intelligence-crew\n\n# create virtual environment\npython -m venv venv\nsource venv/bin/activate  # Windows: venv\\Scripts\\activate\n\n# install dependencies\npip install -r requirements.txt\n```\n\n### Configuration\n\n```bash\n# create env file\nmkdir env\ncp .env.example env/.env\n\n# add your API keys\nGEMINI_API_KEY=your-gemini-api-key\nGOOGLE_API_KEY=your-gemini-api-key\nPINECONE_API_KEY-your-pinecone-api-key\nPINECONE_INDEX=doc-intelligence\n```\n\n### Run\n\n```bash\n# Step 1 — ingest documents into PineCone VectorDB\npython pipeline/rag_pipeline.py\n\n# Step 2 — start FastAPI backend\nuvicorn app:app --reload --port 8000\n\n# Step 3 — start Streamlit UI (new terminal)\nstreamlit run streamlit_app.py\n```\n\nOpen 👉 `http://localhost:8501`\n\n---\n\n## 🔌 API Endpoints\n\n| Method | Endpoint | Description |\n|---|---|---|\n| `GET` | `/health` | System health check |\n| `GET` | `/documents` | List ingested documents |\n| `POST` | `/documents/upload` | Upload new contracts |\n| `POST` | `/ingest` | Re-ingest all documents |\n| `POST` | `/analyze` | Run full 5-agent analysis |\n\nInteractive docs: `http://localhost:8000/docs`\n\n---\n\n## 📊 Results\n\n| Metric | Value |\n|---|---|\n| Documents supported | PDF, DOCX, XLSX |\n| Agents in pipeline | 5 |\n| Avg retrieval precision | High (re-ranked) |\n| Contracts analyzed | 6 vendor contracts |\n| Total contract value analyzed | $25.1M |\n| Risk findings identified | 35+ across all contracts |\n| PII elements detected | SSN, Email, Phone, Bank Account |\n\n---\n\n## 🤖 Agent Pipeline\n\n| Agent | Role | Output Schema |\n|---|---|---|\n| RAG Agent | Autonomous retrieval + rerank + reflect | Raw context |\n| Extractor Agent | Structured data extraction | `ExtractedDoc` |\n| Analyst Agent | Risk classification by severity | `AnalysisResult` |\n| Action Agent | Prioritized action planning | `ActionPlan` |\n| Summary Agent | Executive brief | Plain prose |\n\n---\n\n## 👩‍💻 Author\n\n**Dipti Joshi**\nSenior Software Engineer → Agentic AI Engineer\n[LinkedIn](https://linkedin.com/in/joshidipti) | [GitHub](https://github.com/diptij85)\n\n[def]: architecture.png\n","readmeExcerpt":"📄 Document Intelligence Crew !PineCone Vector DB https://app.pinecone.io/organizations A production-grade multi-agent AI system for enterprise contract analysis. Upload vendor contracts (PDF, DOCX, XLSX) and get instant risk assessment, compliance flags, and executive recommendations — powered by Agentic RAG and a 5-agent CrewAI pipeline. --- 🏗️ Architecture 📄 Documents (PDF + DOCX + XLSX) ↓ [RAG Pipeline] → chunk","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"# clone the repo\ngit clone https://github.com/YOUR_USERNAME/doc-intelligence-crew.git\ncd doc-intelligence-crew\n\n# create virtual environment\npython -m venv venv\nsource venv/bin/activate  # Windows: venv\\Scripts\\activate\n\n# install dependencies\npip install -r requirements.txt"},{"language":"bash","snippet":"# create env file\nmkdir env\ncp .env.example env/.env\n\n# add your API keys\nGEMINI_API_KEY=your-gemini-api-key\nGOOGLE_API_KEY=your-gemini-api-key\nPINECONE_API_KEY-your-pinecone-api-key\nPINECONE_INDEX=doc-intelligence"},{"language":"bash","snippet":"# Step 1 — ingest documents into PineCone VectorDB\npython pipeline/rag_pipeline.py\n\n# Step 2 — start FastAPI backend\nuvicorn app:app --reload --port 8000\n\n# Step 3 — start Streamlit UI (new terminal)\nstreamlit run streamlit_app.py"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["python"],"docsSourceLabel":"GITHUB OPENCLEW","editorialOverview":"Production-grade multi-agent AI system for enterprise contract analysis. CrewAI + Agentic RAG + Pinecone + GCS + FastAPI + Streamlit — deployed on Google Cloud Run 📄 Document Intelligence Crew !PineCone Vector DB https://app.pinecone.io/organizations A production-grade multi-agent AI system for enterprise contract analysis. Upload vendor contracts (PDF, DOCX, XLSX) and get instant risk assessment, compliance flags, and executive recommendations — powered by Agentic RAG and a 5-agent CrewAI pipeline. --- 🏗️ Architecture 📄 Documents (PDF + DOCX + XLSX) ↓ [RAG Pipeline] → chunk","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":389,"uniquenessScore":66,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-05-31T06:18:23.198Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-05-31T06:18:23.198Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-08T23:17:43.573Z","emptyReason":null},"items":[{"id":"959108e7-5f7c-45ac-bea0-9ab67f017226","entityType":"agent","canonicalPath":"/agent/langchain-x1pay-langchain","slug":"langchain-x1pay-langchain","name":"@x1pay/langchain","description":"LangChain/LangGraph tools for AI agent x402 payments on X1","url":"https://www.npmjs.com/package/@x1pay/langchain","homepage":null,"source":"GITHUB_OPENCLEW","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":70,"overallRank":65,"updatedAt":"2026-06-01T00:29:07.099Z","createdAt":"2026-05-23T06:52:58.553Z","downloads":null},{"id":"4f8f8f95-34f7-49a9-b516-391d1c355d6c","entityType":"agent","canonicalPath":"/agent/langchain-langchain-langgraph-swarm","slug":"langchain-langchain-langgraph-swarm","name":"@langchain/langgraph-swarm","description":"An implementation of a multi-agent swarm using LangGraph","url":"git+ssh://git@github.com/langchain-ai/langgraphjs.git","homepage":"https://github.com/langchain-ai/langgraphjs#readme","source":"GITHUB_OPENCLEW","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":70,"overallRank":65,"updatedAt":"2026-06-01T00:29:03.792Z","createdAt":"2026-05-23T06:52:55.396Z","downloads":null},{"id":"e36fd59b-38d7-4e73-aa20-c1431a8f7434","entityType":"agent","canonicalPath":"/agent/langchain-langchain-langgraph-supervisor","slug":"langchain-langchain-langgraph-supervisor","name":"@langchain/langgraph-supervisor","description":"LangGraph Multi-Agent Supervisor","url":"git+ssh://git@github.com/langchain-ai/langgraphjs.git","homepage":"https://github.com/langchain-ai/langgraphjs#readme","source":"GITHUB_OPENCLEW","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":70,"overallRank":65,"updatedAt":"2026-06-01T00:29:03.756Z","createdAt":"2026-05-23T06:52:55.353Z","downloads":null},{"id":"d1d0f93e-b722-4791-9bbf-2532470054c2","entityType":"agent","canonicalPath":"/agent/langchain-oceanbus-langchain","slug":"langchain-oceanbus-langchain","name":"oceanbus-langchain","description":"LangChain tools for OceanBus — give your LangChain and CrewAI agents a global identity, encrypted messaging, and Yellow Pages service discovery with a single import.","url":"git+https://github.com/oceanbus/oceanbus.git","homepage":"https://github.com/oceanbus/oceanbus#readme","source":"GITHUB_OPENCLEW","protocols":["OPENCLAW"],"capabilities":["oceanbus","langchain","langchain-tools","agent-to-agent","ai-agent","communication","messaging","e2ee","structured-tool","yellow-pages","service-discovery","reputation","crewai"],"safetyScore":70,"overallRank":65,"updatedAt":"2026-06-01T00:29:02.595Z","createdAt":"2026-05-23T06:52:54.240Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/github_openclew","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}