{"id":"6f9dda30-318a-463d-8365-a1881e483df8","entityType":"agent","slug":"clawhub-abhinas90-rag-pipeline-starter","name":"RAG Pipeline Starter","canonicalUrl":"https://www.xpersona.co/agent/clawhub-abhinas90-rag-pipeline-starter","canonicalPath":"/agent/clawhub-abhinas90-rag-pipeline-starter","generatedAt":"2026-10-12T12:24:36.163Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T22:53:32.607Z","emptyReason":null},"description":"Set up and optimize RAG pipelines for large datasets (50K-500K rows) with document chunking, embedding benchmarking, vector indexing, and retrieval tuning. Skill: RAG Pipeline Starter Owner: abhinas90 Summary: Set up and optimize RAG pipelines for large datasets (50K-500K rows) with document chunking, embedding benchmarking, vector indexing, and retrieval tuning. Tags: latest:1.0.1 Version history: v1.0.1 | 2026-05-31T18:10:30.016Z | user Release 1.0.1: RAG Pipeline Starter v1.0.0 | 2026-04-18T14:02:27.797Z | user Initial release Archive index: Archive v1.0.1: 8 files,","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 981 downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s174azs5nksq9sp64tzargsaph84203h:rag-pipeline-starter","sourceUrl":"https://clawhub.ai/abhinas90/rag-pipeline-starter","homepage":"https://clawhub.ai/abhinas90/skills/rag-pipeline-starter","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/abhinas90/rag-pipeline-starter","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/abhinas90/skills/rag-pipeline-starter","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Set up and optimize RAG pipelines for large datasets (50K-500K rows) with document chunking, embedding benchmarking, vector indexing, and retrieval tuning. Skil"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T22:53:32.607Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T22:53:32.607Z","emptyReason":null},"stars":null,"forks":null,"downloads":981,"likes":null,"task":null,"library":null,"packageName":null,"latestVersion":"1.0.1","tractionLabel":"981 downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T22:53:32.595Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T22:53:32.607Z","lastCrawledAt":"2026-10-11T22:53:32.595Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T22:53:32.595Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.1","createdAt":"2026-05-31T18:10:30.016Z","changelog":"Release 1.0.1: RAG Pipeline Starter","fileCount":8,"zipByteSize":13649},{"version":"1.0.0","createdAt":"2026-04-18T14:02:27.797Z","changelog":"Initial release","fileCount":8,"zipByteSize":13622}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s174azs5nksq9sp64tzargsaph84203h:rag-pipeline-starter","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/clawhub-abhinas90-rag-pipeline-starter/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-abhinas90-rag-pipeline-starter/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-abhinas90-rag-pipeline-starter/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-abhinas90-rag-pipeline-starter/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-abhinas90-rag-pipeline-starter/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-abhinas90-rag-pipeline-starter/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-12T12:24:36.163Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-abhinas90-rag-pipeline-starter/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-abhinas90-rag-pipeline-starter/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-abhinas90-rag-pipeline-starter/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-abhinas90-rag-pipeline-starter/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":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-11T22:53:32.607Z","emptyReason":null},"readme":"Skill: RAG Pipeline Starter\n\nOwner: abhinas90\n\nSummary: Set up and optimize RAG pipelines for large datasets (50K-500K rows) with document chunking, embedding benchmarking, vector indexing, and retrieval tuning.\n\nTags: latest:1.0.1\n\nVersion history:\n\nv1.0.1 | 2026-05-31T18:10:30.016Z | user\n\nRelease 1.0.1: RAG Pipeline Starter\n\nv1.0.0 | 2026-04-18T14:02:27.797Z | user\n\nInitial release\n\nArchive index:\n\nArchive v1.0.1: 8 files, 13649 bytes\n\nFiles: chunking_analyzer.py (6223b), embedding_benchmark.py (5061b), retrieval_tuner.py (10119b), skill-card.md (2281b), skill.json (667b), SKILL.md (5009b), vector_store_manager.py (8623b), _meta.json (139b)\n\nFile v1.0.1:SKILL.md\n\n# RAG Pipeline Starter\n\nProduction-grade RAG pipeline setup with chunking strategies, embedding benchmarks, and retrieval tuning for 50K-500K row datasets.\n\n## Overview\n\nThis skill provides a complete toolkit for building and optimizing RAG (Retrieval-Augmented Generation) pipelines. It analyzes your data, recommends optimal chunking strategies, benchmarks embedding models, and helps tune retrieval parameters for maximum accuracy.\n\n## When to Use\n\n- Building a new RAG system from scratch\n- Optimizing an existing RAG pipeline's retrieval quality\n- Choosing the right embedding model for your domain\n- Processing large document collections (50K-500K rows)\n- Need to balance speed vs. accuracy for your use case\n\n## Scripts\n\n### chunking_analyzer.py\nAnalyzes documents and recommends optimal chunking strategies based on content structure.\n\n**Usage:**\n```bash\n# Assess data and get strategy recommendation\npython chunking_analyzer.py --assess ./data\n\n# Apply chunking strategy to documents\npython chunking_analyzer.py --strategy recursive --input ./data/doc.txt --output ./chunks/ --chunk-size 500 --overlap 50\n```\n\n**Options:**\n- `--assess <dir>` - Analyze documents and recommend strategy\n- `--strategy <name>` - Chunking strategy: fixed, semantic, recursive, hierarchical\n- `--input <path>` - Input file or directory\n- `--output <dir>` - Output directory for chunks\n- `--chunk-size <int>` - Chunk size (default: 500)\n- `--overlap <int>` - Overlap between chunks (default: 50)\n\n### embedding_benchmark.py\nTests multiple embedding models on your data to find the best fit for your domain.\n\n**Usage:**\n```bash\npython embedding_benchmark.py --data ./chunks/ --domain finance --output results.json\n```\n\n**Options:**\n- `--embeddings <models>` - Embedding models to test (space-separated)\n- `--data <dir>` - Directory with chunked text files (required)\n- `--domain <name>` - Domain name for context-specific recommendations\n- `--output <file>` - Output file for results (JSON)\n\n**Supported Embeddings:**\n- sentence-transformers/all-MiniLM-L6-v2 (384 dims, fast, free)\n- sentence-transformers/all-mpnet-base-v2 (768 dims, medium, free)\n- openai/text-embedding-ada-002 (1536 dims, fast, paid)\n- cohere/embed-english-v3.0 (1024 dims, fast, paid)\n- bm25 (sparse, fast, free)\n\n### retrieval_tuner.py\nOptimizes retrieval parameters (top-k, similarity threshold) for your specific use case.\n\n**Usage:**\n```bash\npython retrieval_tuner.py --index ./vector_store/ --queries ./test_queries.json --output tuning_results.json\n```\n\n**Options:**\n- `--index <dir>` - Vector store index directory\n- `--queries <file>` - JSON file with test queries and expected results\n- `--output <file>` - Output file for tuning results\n- `--top-k-range <min> <max>` - Range of top-k values to test (default: 1 20)\n- `--threshold-range <min> <max> <step>` - Similarity threshold range\n\n### vector_store_manager.py\nManages vector store operations: create, update, search, and maintain indexes.\n\n**Usage:**\n```bash\n# Create index from chunks\npython vector_store_manager.py --create --chunks ./chunks/ --index ./vector_store/ --embedding sentence-transformers/all-MiniLM-L6-v2\n\n# Search index\npython vector_store_manager.py --search --index ./vector_store/ --query \"your search query\" --top-k 5\n```\n\n**Options:**\n- `--create` - Create new index from chunks\n- `--chunks <dir>` - Directory with chunked text files\n- `--index <dir>` - Vector store directory\n- `--embedding <model>` - Embedding model to use\n- `--search` - Search existing index\n- `--query <text>` - Search query\n- `--top-k <int>` - Number of results to return (default: 5)\n- `--update` - Update index with new documents\n- `--stats` - Show index statistics\n\n## Pricing Strategy\n\n**Free tier** (this skill): Core chunking + embedding benchmark tools  \n**Paid guide** ($49): Complete production RAG setup with:\n- Multi-modal document processing\n- Hybrid search (dense + sparse)\n- Re-ranking pipeline\n- Evaluation framework\n- Deployment scripts\n\n## Workflow\n\n1. **Assess your data**\n   ```bash\n   python chunking_analyzer.py --assess ./your_data/\n   ```\n\n2. **Apply chunking strategy**\n   ```bash\n   python chunking_analyzer.py --strategy recursive --input ./data/ --output ./chunks/\n   ```\n\n3. **Benchmark embeddings**\n   ```bash\n   python embedding_benchmark.py --data ./chunks/ --domain your_domain\n   ```\n\n4. **Create vector store**\n   ```bash\n   python vector_store_manager.py --create --chunks ./chunks/ --index ./vector_store/ --embedding <recommended_model>\n   ```\n\n5. **Tune retrieval** (optional)\n   ```bash\n   python retrieval_tuner.py --index ./vector_store/ --queries ./test_queries.json\n   ```\n\n## Requirements\n\n- Python 3.8+\n- Dependencies: numpy, sentence-transformers (optional for real embeddings)\n\n## Files\n\n- `chunking_analyzer.py` - Document analysis and chunking\n- `embedding_benchmark.py` - Embedding model benchmarking\n- `retrieval_tuner.py` - Retrieval parameter optimization\n- `vector_store_manager.py` - Vector store operations\n- `skill.json` - Skill metadata\n\nFile v1.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn71hf14zhnh60jg0jb31zthnh8421nq\",\n  \"slug\": \"rag-pipeline-starter\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1780251030016\n}\n\nFile v1.0.1:skill-card.md\n\n## Description:\n\nSet up and optimize RAG pipelines for large datasets with document chunking, embedding benchmarking, vector indexing, and retrieval tuning.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[abhinas90](https://clawhub.ai/user/abhinas90)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and engineers use this skill to create or improve local RAG pipelines for large document collections, including chunking, embedding selection, vector index management, and retrieval parameter tuning.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill reads chosen document folders and writes derived chunks, results, and index files.\n\nMitigation: Run it in dedicated working directories and avoid pointing outputs at important folders.\n\nRisk: Using hosted embedding APIs in future extensions could send document chunks or queries to external providers.\n\nMitigation: Treat hosted embedding use as a separate privacy decision and prefer local models for sensitive data.\n\nRisk: Retrieval and benchmark recommendations may be affected by simplified scoring paths and data-handling caveats.\n\nMitigation: Validate recommendations with representative queries and reviewed evaluation data before relying on them in production.\n\n## Reference(s):\n\n- [RAG Pipeline Starter ClawHub page](https://clawhub.ai/abhinas90/skills/rag-pipeline-starter)\n- [Publisher profile](https://clawhub.ai/user/abhinas90)\n- [Skill documentation](artifact/SKILL.md)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown guidance with Python command examples, console text, JSON results, and generated local files]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May read user-selected document folders and write derived chunks, benchmark results, tuning results, and vector index files.]\n\n## Skill Version(s):\n\n1.0.1 (source: server release evidence and skill.json)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.0.1:skill.json\n\n{\n  \"slug\": \"rag-pipeline-starter\",\n  \"name\": \"RAG Pipeline Starter\",\n  \"version\": \"1.0.1\",\n  \"description\": \"Production-grade RAG pipeline setup with chunking strategies, embedding benchmarks, and retrieval tuning for 50K-500K row datasets\",\n  \"author\": \"Abhinas Neupane\",\n  \"tags\": [\n    \"RAG\",\n    \"retrieval\",\n    \"embeddings\",\n    \"LLM\",\n    \"vector-database\",\n    \"chunking\",\n    \"benchmark\"\n  ],\n  \"pricing\": {\n    \"type\": \"one-time\",\n    \"value\": 0\n  },\n  \"scripts\": [\n    \"chunking_analyzer.py\",\n    \"embedding_benchmark.py\",\n    \"retrieval_tuner.py\",\n    \"vector_store_manager.py\"\n  ],\n  \"requirements\": {\n    \"python\": \">=3.8\",\n    \"dependencies\": []\n  }\n}\n\nArchive v1.0.0: 8 files, 13622 bytes\n\nFiles: chunking_analyzer.py (6223b), embedding_benchmark.py (5061b), retrieval_tuner.py (10119b), skill-card.md (2226b), skill.json (636b), SKILL.md (5009b), vector_store_manager.py (8623b), _meta.json (139b)\n\nFile v1.0.0:SKILL.md\n\n# RAG Pipeline Starter\n\nProduction-grade RAG pipeline setup with chunking strategies, embedding benchmarks, and retrieval tuning for 50K-500K row datasets.\n\n## Overview\n\nThis skill provides a complete toolkit for building and optimizing RAG (Retrieval-Augmented Generation) pipelines. It analyzes your data, recommends optimal chunking strategies, benchmarks embedding models, and helps tune retrieval parameters for maximum accuracy.\n\n## When to Use\n\n- Building a new RAG system from scratch\n- Optimizing an existing RAG pipeline's retrieval quality\n- Choosing the right embedding model for your domain\n- Processing large document collections (50K-500K rows)\n- Need to balance speed vs. accuracy for your use case\n\n## Scripts\n\n### chunking_analyzer.py\nAnalyzes documents and recommends optimal chunking strategies based on content structure.\n\n**Usage:**\n```bash\n# Assess data and get strategy recommendation\npython chunking_analyzer.py --assess ./data\n\n# Apply chunking strategy to documents\npython chunking_analyzer.py --strategy recursive --input ./data/doc.txt --output ./chunks/ --chunk-size 500 --overlap 50\n```\n\n**Options:**\n- `--assess <dir>` - Analyze documents and recommend strategy\n- `--strategy <name>` - Chunking strategy: fixed, semantic, recursive, hierarchical\n- `--input <path>` - Input file or directory\n- `--output <dir>` - Output directory for chunks\n- `--chunk-size <int>` - Chunk size (default: 500)\n- `--overlap <int>` - Overlap between chunks (default: 50)\n\n### embedding_benchmark.py\nTests multiple embedding models on your data to find the best fit for your domain.\n\n**Usage:**\n```bash\npython embedding_benchmark.py --data ./chunks/ --domain finance --output results.json\n```\n\n**Options:**\n- `--embeddings <models>` - Embedding models to test (space-separated)\n- `--data <dir>` - Directory with chunked text files (required)\n- `--domain <name>` - Domain name for context-specific recommendations\n- `--output <file>` - Output file for results (JSON)\n\n**Supported Embeddings:**\n- sentence-transformers/all-MiniLM-L6-v2 (384 dims, fast, free)\n- sentence-transformers/all-mpnet-base-v2 (768 dims, medium, free)\n- openai/text-embedding-ada-002 (1536 dims, fast, paid)\n- cohere/embed-english-v3.0 (1024 dims, fast, paid)\n- bm25 (sparse, fast, free)\n\n### retrieval_tuner.py\nOptimizes retrieval parameters (top-k, similarity threshold) for your specific use case.\n\n**Usage:**\n```bash\npython retrieval_tuner.py --index ./vector_store/ --queries ./test_queries.json --output tuning_results.json\n```\n\n**Options:**\n- `--index <dir>` - Vector store index directory\n- `--queries <file>` - JSON file with test queries and expected results\n- `--output <file>` - Output file for tuning results\n- `--top-k-range <min> <max>` - Range of top-k values to test (default: 1 20)\n- `--threshold-range <min> <max> <step>` - Similarity threshold range\n\n### vector_store_manager.py\nManages vector store operations: create, update, search, and maintain indexes.\n\n**Usage:**\n```bash\n# Create index from chunks\npython vector_store_manager.py --create --chunks ./chunks/ --index ./vector_store/ --embedding sentence-transformers/all-MiniLM-L6-v2\n\n# Search index\npython vector_store_manager.py --search --index ./vector_store/ --query \"your search query\" --top-k 5\n```\n\n**Options:**\n- `--create` - Create new index from chunks\n- `--chunks <dir>` - Directory with chunked text files\n- `--index <dir>` - Vector store directory\n- `--embedding <model>` - Embedding model to use\n- `--search` - Search existing index\n- `--query <text>` - Search query\n- `--top-k <int>` - Number of results to return (default: 5)\n- `--update` - Update index with new documents\n- `--stats` - Show index statistics\n\n## Pricing Strategy\n\n**Free tier** (this skill): Core chunking + embedding benchmark tools  \n**Paid guide** ($49): Complete production RAG setup with:\n- Multi-modal document processing\n- Hybrid search (dense + sparse)\n- Re-ranking pipeline\n- Evaluation framework\n- Deployment scripts\n\n## Workflow\n\n1. **Assess your data**\n   ```bash\n   python chunking_analyzer.py --assess ./your_data/\n   ```\n\n2. **Apply chunking strategy**\n   ```bash\n   python chunking_analyzer.py --strategy recursive --input ./data/ --output ./chunks/\n   ```\n\n3. **Benchmark embeddings**\n   ```bash\n   python embedding_benchmark.py --data ./chunks/ --domain your_domain\n   ```\n\n4. **Create vector store**\n   ```bash\n   python vector_store_manager.py --create --chunks ./chunks/ --index ./vector_store/ --embedding <recommended_model>\n   ```\n\n5. **Tune retrieval** (optional)\n   ```bash\n   python retrieval_tuner.py --index ./vector_store/ --queries ./test_queries.json\n   ```\n\n## Requirements\n\n- Python 3.8+\n- Dependencies: numpy, sentence-transformers (optional for real embeddings)\n\n## Files\n\n- `chunking_analyzer.py` - Document analysis and chunking\n- `embedding_benchmark.py` - Embedding model benchmarking\n- `retrieval_tuner.py` - Retrieval parameter optimization\n- `vector_store_manager.py` - Vector store operations\n- `skill.json` - Skill metadata\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn71hf14zhnh60jg0jb31zthnh8421nq\",\n  \"slug\": \"rag-pipeline-starter\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1776520947797\n}\n\nFile v1.0.0:skill-card.md\n\n## Description: <br>\nSet up and optimize RAG pipelines for large datasets with document chunking, embedding benchmarking, vector indexing, and retrieval tuning. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[abhinas90](https://clawhub.ai/user/abhinas90) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and engineers use this skill to bootstrap and tune RAG workflows for medium-to-large document collections, including chunking, model comparison, local indexing, retrieval testing, and parameter tuning. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Generated chunks, benchmark reports, and index files may contain sensitive source document content. <br>\nMitigation: Run the skill in a controlled workspace and protect or delete generated artifacts according to the sensitivity of the input documents. <br>\nRisk: Embedding benchmark and retrieval recommendations can be misleading because the artifact uses mock or keyword-based scoring paths. <br>\nMitigation: Treat recommendations as starter guidance and validate them with reviewed embedding backends, representative queries, and ground-truth evaluation data before production use. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/abhinas90/rag-pipeline-starter) <br>\n- [Publisher profile](https://clawhub.ai/user/abhinas90) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, code, shell commands, configuration, JSON, files] <br>\n**Output Format:** [Markdown guidance with shell commands, JSON reports, local text chunks, and local vector index files.] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Python 3.8+ local command-line workflow; optional real embedding backends are not included in the artifact.] <br>\n\n## Skill Version(s): <br>\n1.0.0 (source: server release metadata and skill.json) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nFile v1.0.0:skill.json\n\n{\n  \"slug\": \"rag-pipeline-starter\",\n  \"name\": \"RAG Pipeline Starter\",\n  \"version\": \"1.0.0\",\n  \"description\": \"Production-grade RAG pipeline setup with chunking strategies, embedding benchmarks, and retrieval tuning for 50K-500K row datasets\",\n  \"author\": \"Abhinas Neupane\",\n  \"tags\": [\"RAG\", \"retrieval\", \"embeddings\", \"LLM\", \"vector-database\", \"chunking\", \"benchmark\"],\n  \"pricing\": {\n    \"type\": \"one-time\",\n    \"value\": 0\n  },\n  \"scripts\": [\n    \"chunking_analyzer.py\",\n    \"embedding_benchmark.py\", \n    \"retrieval_tuner.py\",\n    \"vector_store_manager.py\"\n  ],\n  \"requirements\": {\n    \"python\": \">=3.8\",\n    \"dependencies\": []\n  }\n}","readmeExcerpt":"Skill: RAG Pipeline Starter Owner: abhinas90 Summary: Set up and optimize RAG pipelines for large datasets (50K-500K rows) with document chunking, embedding benchmarking, vector indexing, and retrieval tuning. Tags: latest:1.0.1 Version history: v1.0.1 | 2026-05-31T18:10:30.016Z | user Release 1.0.1: RAG Pipeline Starter v1.0.0 | 2026-04-18T14:02:27.797Z | user Initial release Archive index: Archive v1.0.1: 8 files, ","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"# Assess data and get strategy recommendation\npython chunking_analyzer.py --assess ./data\n\n# Apply chunking strategy to documents\npython chunking_analyzer.py --strategy recursive --input ./data/doc.txt --output ./chunks/ --chunk-size 500 --overlap 50"},{"language":"bash","snippet":"python embedding_benchmark.py --data ./chunks/ --domain finance --output results.json"},{"language":"bash","snippet":"python retrieval_tuner.py --index ./vector_store/ --queries ./test_queries.json --output tuning_results.json"},{"language":"bash","snippet":"# Create index from chunks\npython vector_store_manager.py --create --chunks ./chunks/ --index ./vector_store/ --embedding sentence-transformers/all-MiniLM-L6-v2\n\n# Search index\npython vector_store_manager.py --search --index ./vector_store/ --query \"your search query\" --top-k 5"},{"language":"bash","snippet":"python chunking_analyzer.py --assess ./your_data/"},{"language":"bash","snippet":"python chunking_analyzer.py --strategy recursive --input ./data/ --output ./chunks/"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"# RAG Pipeline Starter\n\nProduction-grade RAG pipeline setup with chunking strategies, embedding benchmarks, and retrieval tuning for 50K-500K row datasets.\n\n## Overview\n\nThis skill provides a complete toolkit for building and optimizing RAG (Retrieval-Augmented Generation) pipelines. It analyzes your data, recommends optimal chunking strategies, benchmarks embedding models, and helps tune retrieval parameters for maximum accuracy.\n\n## When to Use\n\n- Building a new RAG system from scratch\n- Optimizing an existing RAG pipeline's retrieval quality\n- Choosing the right embedding model for your domain\n- Processing large document collections (50K-500K rows)\n- Need to balance speed vs. accuracy for your use case\n\n## Scripts\n\n### chunking_analyzer.py\nAnalyzes documents and recommends optimal chunking strategies based on content structure.\n\n**Usage:**\n```bash\n# Assess data and get strategy recommendation\npython chunking_analyzer.py --assess ./data\n\n# Apply chunking strategy to documents\npython chunking_analyzer.py --strategy recursive --input ./data/doc.txt --output ./chunks/ --chunk-size 500 --overlap 50\n```\n\n**Options:**\n- `--assess <dir>` - Analyze documents and recommend strategy\n- `--strategy <name>` - Chunking strategy: fixed, semantic, recursive, hierarchical\n- `--input <path>` - Input file or directory\n- `--output <dir>` - Output directory for chunks\n- `--chunk-size <int>` - Chunk size (default: 500)\n- `--overlap <int>` - Overlap between chunks (default: 50)\n\n### embedding_benchmark.py\nTests multiple embedding models on your data to find the best fit for your domain.\n\n**Usage:**\n```bash\npython embedding_benchmark.py --data ./chunks/ --domain finance --output results.json\n```\n\n**Options:**\n- `--embeddings <models>` - Embedding models to test (space-separated)\n- `--data <dir>` - Directory with chunked text files (required)\n- `--domain <name>` - Domain name for context-specific recommendations\n- `--output <file>` - Output file for results (JSON)\n\n**Supported Embeddings:**\n- sentence-transformers/all-MiniLM-L6-v2 (384 dims, fast, free)\n- sentence-transformers/all-mpnet-base-v2 (768 dims, medium, free)\n- openai/text-embedding-ada-002 (1536 dims, fast, paid)\n- cohere/embed-english-v3.0 (1024 dims, fast, paid)\n- bm25 (sparse, fast, free)\n\n### retrieval_tuner.py\nOptimizes retrieval parameters (top-k, similarity threshold) for your specific use case.\n\n**Usage:**\n```bash\npython retrieval_tuner.py --index ./vector_store/ --queries ./test_queries.json --output tuning_results.json\n```\n\n**Options:**\n- `--index <dir>` - Vector store index directory\n- `--queries <file>` - JSON file with test queries and expected results\n- `--output <file>` - Output file for tuning results\n- `--top-k-range <min> <max>` - Range of top-k values to test (default: 1 20)\n- `--threshold-range <min> <max> <step>` - Similarity threshold range\n\n### vector_store_manager.py\nManages vector store operations: create, update, search, and maintain indexes.\n\n**Usage:**\n```bash\n# Create index from "},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn71hf14zhnh60jg0jb31zthnh8421nq\",\n  \"slug\": \"rag-pipeline-starter\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1780251030016\n}"},{"path":"skill-card.md","content":"## Description:\n\nSet up and optimize RAG pipelines for large datasets with document chunking, embedding benchmarking, vector indexing, and retrieval tuning.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[abhinas90](https://clawhub.ai/user/abhinas90)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and engineers use this skill to create or improve local RAG pipelines for large document collections, including chunking, embedding selection, vector index management, and retrieval parameter tuning.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill reads chosen document folders and writes derived chunks, results, and index files.\n\nMitigation: Run it in dedicated working directories and avoid pointing outputs at important folders.\n\nRisk: Using hosted embedding APIs in future extensions could send document chunks or queries to external providers.\n\nMitigation: Treat hosted embedding use as a separate privacy decision and prefer local models for sensitive data.\n\nRisk: Retrieval and benchmark recommendations may be affected by simplified scoring paths and data-handling caveats.\n\nMitigation: Validate recommendations with representative queries and reviewed evaluation data before relying on them in production.\n\n## Reference(s):\n\n- [RAG Pipeline Starter ClawHub page](https://clawhub.ai/abhinas90/skills/rag-pipeline-starter)\n- [Publisher profile](https://clawhub.ai/user/abhinas90)\n- [Skill documentation](artifact/SKILL.md)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown guidance with Python command examples, console text, JSON results, and generated local files]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May read user-selected document folders and write derived chunks, benchmark results, tuning results, and vector index files.]\n\n## Skill Version(s):\n\n1.0.1 (source: server release evidence and skill.json)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."},{"path":"skill.json","content":"{\n  \"slug\": \"rag-pipeline-starter\",\n  \"name\": \"RAG Pipeline Starter\",\n  \"version\": \"1.0.1\",\n  \"description\": \"Production-grade RAG pipeline setup with chunking strategies, embedding benchmarks, and retrieval tuning for 50K-500K row datasets\",\n  \"author\": \"Abhinas Neupane\",\n  \"tags\": [\n    \"RAG\",\n    \"retrieval\",\n    \"embeddings\",\n    \"LLM\",\n    \"vector-database\",\n    \"chunking\",\n    \"benchmark\"\n  ],\n  \"pricing\": {\n    \"type\": \"one-time\",\n    \"value\": 0\n  },\n  \"scripts\": [\n    \"chunking_analyzer.py\",\n    \"embedding_benchmark.py\",\n    \"retrieval_tuner.py\",\n    \"vector_store_manager.py\"\n  ],\n  \"requirements\": {\n    \"python\": \">=3.8\",\n    \"dependencies\": []\n  }\n}"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Set up and optimize RAG pipelines for large datasets (50K-500K rows) with document chunking, embedding benchmarking, vector indexing, and retrieval tuning. Skill: RAG Pipeline Starter Owner: abhinas90 Summary: Set up and optimize RAG pipelines for large datasets (50K-500K rows) with document chunking, embedding benchmarking, vector indexing, and retrieval tuning. Tags: latest:1.0.1 Version history: v1.0.1 | 2026-05-31T18:10:30.016Z | user Release 1.0.1: RAG Pipeline Starter v1.0.0 | 2026-04-18T14:02:27.797Z | user Initial release Archive index: Archive v1.0.1: 8 files,","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1075,"uniquenessScore":52,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T22:53:32.607Z","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":"2026-10-11T22:53:32.607Z","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":"2026-10-12T12:24:36.163Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}