{
  "schemaVersion": "1.0",
  "item": {
    "slug": "ai-rag-pipeline",
    "name": "Ai Rag Pipeline",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/okaris/ai-rag-pipeline",
    "canonicalUrl": "https://clawhub.ai/okaris/ai-rag-pipeline",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/ai-rag-pipeline",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=ai-rag-pipeline",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "slug": "ai-rag-pipeline",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-29T17:34:46.236Z",
      "expiresAt": "2026-05-06T17:34:46.236Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=ai-rag-pipeline",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=ai-rag-pipeline",
        "contentDisposition": "attachment; filename=\"ai-rag-pipeline-0.1.5.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "ai-rag-pipeline"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/ai-rag-pipeline"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/ai-rag-pipeline",
    "agentPageUrl": "https://openagent3.xyz/skills/ai-rag-pipeline/agent",
    "manifestUrl": "https://openagent3.xyz/skills/ai-rag-pipeline/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/ai-rag-pipeline/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "AI RAG Pipeline",
        "body": "Build RAG (Retrieval Augmented Generation) pipelines via inference.sh CLI."
      },
      {
        "title": "Quick Start",
        "body": "curl -fsSL https://cli.inference.sh | sh && infsh login\n\n# Simple RAG: Search + LLM\nSEARCH=$(infsh app run tavily/search-assistant --input '{\"query\": \"latest AI developments 2024\"}')\ninfsh app run openrouter/claude-sonnet-45 --input \"{\n  \\\"prompt\\\": \\\"Based on this research, summarize the key trends: $SEARCH\\\"\n}\"\n\nInstall note: The install script only detects your OS/architecture, downloads the matching binary from dist.inference.sh, and verifies its SHA-256 checksum. No elevated permissions or background processes. Manual install & verification available."
      },
      {
        "title": "What is RAG?",
        "body": "RAG combines:\n\nRetrieval: Fetch relevant information from external sources\nAugmentation: Add retrieved context to the prompt\nGeneration: LLM generates response using the context\n\nThis produces more accurate, up-to-date, and verifiable AI responses."
      },
      {
        "title": "Pattern 1: Simple Search + Answer",
        "body": "[User Query] -> [Web Search] -> [LLM with Context] -> [Answer]"
      },
      {
        "title": "Pattern 2: Multi-Source Research",
        "body": "[Query] -> [Multiple Searches] -> [Aggregate] -> [LLM Analysis] -> [Report]"
      },
      {
        "title": "Pattern 3: Extract + Process",
        "body": "[URLs] -> [Content Extraction] -> [Chunking] -> [LLM Summary] -> [Output]"
      },
      {
        "title": "Search Tools",
        "body": "ToolApp IDBest ForTavily Searchtavily/search-assistantAI-powered search with answersExa Searchexa/searchNeural search, semantic matchingExa Answerexa/answerDirect factual answers"
      },
      {
        "title": "Extraction Tools",
        "body": "ToolApp IDBest ForTavily Extracttavily/extractClean content from URLsExa Extractexa/extractAnalyze web content"
      },
      {
        "title": "LLM Tools",
        "body": "ModelApp IDBest ForClaude Sonnet 4.5openrouter/claude-sonnet-45Complex analysisClaude Haiku 4.5openrouter/claude-haiku-45Fast processingGPT-4oopenrouter/gpt-4oGeneral purposeGemini 2.5 Proopenrouter/gemini-25-proLong context"
      },
      {
        "title": "Basic RAG Pipeline",
        "body": "# 1. Search for information\nSEARCH_RESULT=$(infsh app run tavily/search-assistant --input '{\n  \"query\": \"What are the latest breakthroughs in quantum computing 2024?\"\n}')\n\n# 2. Generate grounded response\ninfsh app run openrouter/claude-sonnet-45 --input \"{\n  \\\"prompt\\\": \\\"You are a research assistant. Based on the following search results, provide a comprehensive summary with citations.\n\nSearch Results:\n$SEARCH_RESULT\n\nProvide a well-structured summary with source citations.\\\"\n}\""
      },
      {
        "title": "Multi-Source Research",
        "body": "# Search multiple sources\nTAVILY=$(infsh app run tavily/search-assistant --input '{\"query\": \"electric vehicle market trends 2024\"}')\nEXA=$(infsh app run exa/search --input '{\"query\": \"EV market analysis latest reports\"}')\n\n# Combine and analyze\ninfsh app run openrouter/claude-sonnet-45 --input \"{\n  \\\"prompt\\\": \\\"Analyze these research results and identify common themes and contradictions.\n\nSource 1 (Tavily):\n$TAVILY\n\nSource 2 (Exa):\n$EXA\n\nProvide a balanced analysis with sources.\\\"\n}\""
      },
      {
        "title": "URL Content Analysis",
        "body": "# 1. Extract content from specific URLs\nCONTENT=$(infsh app run tavily/extract --input '{\n  \"urls\": [\n    \"https://example.com/research-paper\",\n    \"https://example.com/industry-report\"\n  ]\n}')\n\n# 2. Analyze extracted content\ninfsh app run openrouter/claude-sonnet-45 --input \"{\n  \\\"prompt\\\": \\\"Analyze these documents and extract key insights:\n\n$CONTENT\n\nProvide:\n1. Key findings\n2. Data points\n3. Recommendations\\\"\n}\""
      },
      {
        "title": "Fact-Checking Pipeline",
        "body": "# Claim to verify\nCLAIM=\"AI will replace 50% of jobs by 2030\"\n\n# 1. Search for evidence\nEVIDENCE=$(infsh app run tavily/search-assistant --input \"{\n  \\\"query\\\": \\\"$CLAIM evidence studies research\\\"\n}\")\n\n# 2. Verify claim\ninfsh app run openrouter/claude-sonnet-45 --input \"{\n  \\\"prompt\\\": \\\"Fact-check this claim: '$CLAIM'\n\nBased on the following evidence:\n$EVIDENCE\n\nProvide:\n1. Verdict (True/False/Partially True/Unverified)\n2. Supporting evidence\n3. Contradicting evidence\n4. Sources\\\"\n}\""
      },
      {
        "title": "Research Report Generator",
        "body": "TOPIC=\"Impact of generative AI on creative industries\"\n\n# 1. Initial research\nOVERVIEW=$(infsh app run tavily/search-assistant --input \"{\\\"query\\\": \\\"$TOPIC overview\\\"}\")\nSTATISTICS=$(infsh app run exa/search --input \"{\\\"query\\\": \\\"$TOPIC statistics data\\\"}\")\nOPINIONS=$(infsh app run tavily/search-assistant --input \"{\\\"query\\\": \\\"$TOPIC expert opinions\\\"}\")\n\n# 2. Generate comprehensive report\ninfsh app run openrouter/claude-sonnet-45 --input \"{\n  \\\"prompt\\\": \\\"Generate a comprehensive research report on: $TOPIC\n\nResearch Data:\n== Overview ==\n$OVERVIEW\n\n== Statistics ==\n$STATISTICS\n\n== Expert Opinions ==\n$OPINIONS\n\nFormat as a professional report with:\n- Executive Summary\n- Key Findings\n- Data Analysis\n- Expert Perspectives\n- Conclusion\n- Sources\\\"\n}\""
      },
      {
        "title": "Quick Answer with Sources",
        "body": "# Use Exa Answer for direct factual questions\ninfsh app run exa/answer --input '{\n  \"question\": \"What is the current market cap of NVIDIA?\"\n}'"
      },
      {
        "title": "1. Query Optimization",
        "body": "# Bad: Too vague\n\"AI news\"\n\n# Good: Specific and contextual\n\"latest developments in large language models January 2024\""
      },
      {
        "title": "2. Context Management",
        "body": "# Summarize long search results before sending to LLM\nSEARCH=$(infsh app run tavily/search-assistant --input '{\"query\": \"...\"}')\n\n# If too long, summarize first\nSUMMARY=$(infsh app run openrouter/claude-haiku-45 --input \"{\n  \\\"prompt\\\": \\\"Summarize these search results in bullet points: $SEARCH\\\"\n}\")\n\n# Then use summary for analysis\ninfsh app run openrouter/claude-sonnet-45 --input \"{\n  \\\"prompt\\\": \\\"Based on this research summary, provide insights: $SUMMARY\\\"\n}\""
      },
      {
        "title": "3. Source Attribution",
        "body": "Always ask the LLM to cite sources:\n\ninfsh app run openrouter/claude-sonnet-45 --input '{\n  \"prompt\": \"... Always cite sources in [Source Name](URL) format.\"\n}'"
      },
      {
        "title": "4. Iterative Research",
        "body": "# First pass: broad search\nINITIAL=$(infsh app run tavily/search-assistant --input '{\"query\": \"topic overview\"}')\n\n# Second pass: dive deeper based on findings\nDEEP=$(infsh app run tavily/search-assistant --input '{\"query\": \"specific aspect from initial search\"}')"
      },
      {
        "title": "Agent Research Tool",
        "body": "#!/bin/bash\n# research.sh - Reusable research function\n\nresearch() {\n  local query=\"$1\"\n\n  # Search\n  local results=$(infsh app run tavily/search-assistant --input \"{\\\"query\\\": \\\"$query\\\"}\")\n\n  # Analyze\n  infsh app run openrouter/claude-haiku-45 --input \"{\n    \\\"prompt\\\": \\\"Summarize: $results\\\"\n  }\"\n}\n\nresearch \"your query here\""
      },
      {
        "title": "Related Skills",
        "body": "# Web search tools\nnpx skills add inference-sh/skills@web-search\n\n# LLM models\nnpx skills add inference-sh/skills@llm-models\n\n# Content pipelines\nnpx skills add inference-sh/skills@ai-content-pipeline\n\n# Full platform skill\nnpx skills add inference-sh/skills@inference-sh\n\nBrowse all apps: infsh app list"
      },
      {
        "title": "Documentation",
        "body": "Adding Tools to Agents - Agent tool integration\nBuilding a Research Agent - Full guide"
      }
    ],
    "body": "AI RAG Pipeline\n\nBuild RAG (Retrieval Augmented Generation) pipelines via inference.sh CLI.\n\nQuick Start\ncurl -fsSL https://cli.inference.sh | sh && infsh login\n\n# Simple RAG: Search + LLM\nSEARCH=$(infsh app run tavily/search-assistant --input '{\"query\": \"latest AI developments 2024\"}')\ninfsh app run openrouter/claude-sonnet-45 --input \"{\n  \\\"prompt\\\": \\\"Based on this research, summarize the key trends: $SEARCH\\\"\n}\"\n\n\nInstall note: The install script only detects your OS/architecture, downloads the matching binary from dist.inference.sh, and verifies its SHA-256 checksum. No elevated permissions or background processes. Manual install & verification available.\n\nWhat is RAG?\n\nRAG combines:\n\nRetrieval: Fetch relevant information from external sources\nAugmentation: Add retrieved context to the prompt\nGeneration: LLM generates response using the context\n\nThis produces more accurate, up-to-date, and verifiable AI responses.\n\nRAG Pipeline Patterns\nPattern 1: Simple Search + Answer\n[User Query] -> [Web Search] -> [LLM with Context] -> [Answer]\n\nPattern 2: Multi-Source Research\n[Query] -> [Multiple Searches] -> [Aggregate] -> [LLM Analysis] -> [Report]\n\nPattern 3: Extract + Process\n[URLs] -> [Content Extraction] -> [Chunking] -> [LLM Summary] -> [Output]\n\nAvailable Tools\nSearch Tools\nTool\tApp ID\tBest For\nTavily Search\ttavily/search-assistant\tAI-powered search with answers\nExa Search\texa/search\tNeural search, semantic matching\nExa Answer\texa/answer\tDirect factual answers\nExtraction Tools\nTool\tApp ID\tBest For\nTavily Extract\ttavily/extract\tClean content from URLs\nExa Extract\texa/extract\tAnalyze web content\nLLM Tools\nModel\tApp ID\tBest For\nClaude Sonnet 4.5\topenrouter/claude-sonnet-45\tComplex analysis\nClaude Haiku 4.5\topenrouter/claude-haiku-45\tFast processing\nGPT-4o\topenrouter/gpt-4o\tGeneral purpose\nGemini 2.5 Pro\topenrouter/gemini-25-pro\tLong context\nPipeline Examples\nBasic RAG Pipeline\n# 1. Search for information\nSEARCH_RESULT=$(infsh app run tavily/search-assistant --input '{\n  \"query\": \"What are the latest breakthroughs in quantum computing 2024?\"\n}')\n\n# 2. Generate grounded response\ninfsh app run openrouter/claude-sonnet-45 --input \"{\n  \\\"prompt\\\": \\\"You are a research assistant. Based on the following search results, provide a comprehensive summary with citations.\n\nSearch Results:\n$SEARCH_RESULT\n\nProvide a well-structured summary with source citations.\\\"\n}\"\n\nMulti-Source Research\n# Search multiple sources\nTAVILY=$(infsh app run tavily/search-assistant --input '{\"query\": \"electric vehicle market trends 2024\"}')\nEXA=$(infsh app run exa/search --input '{\"query\": \"EV market analysis latest reports\"}')\n\n# Combine and analyze\ninfsh app run openrouter/claude-sonnet-45 --input \"{\n  \\\"prompt\\\": \\\"Analyze these research results and identify common themes and contradictions.\n\nSource 1 (Tavily):\n$TAVILY\n\nSource 2 (Exa):\n$EXA\n\nProvide a balanced analysis with sources.\\\"\n}\"\n\nURL Content Analysis\n# 1. Extract content from specific URLs\nCONTENT=$(infsh app run tavily/extract --input '{\n  \"urls\": [\n    \"https://example.com/research-paper\",\n    \"https://example.com/industry-report\"\n  ]\n}')\n\n# 2. Analyze extracted content\ninfsh app run openrouter/claude-sonnet-45 --input \"{\n  \\\"prompt\\\": \\\"Analyze these documents and extract key insights:\n\n$CONTENT\n\nProvide:\n1. Key findings\n2. Data points\n3. Recommendations\\\"\n}\"\n\nFact-Checking Pipeline\n# Claim to verify\nCLAIM=\"AI will replace 50% of jobs by 2030\"\n\n# 1. Search for evidence\nEVIDENCE=$(infsh app run tavily/search-assistant --input \"{\n  \\\"query\\\": \\\"$CLAIM evidence studies research\\\"\n}\")\n\n# 2. Verify claim\ninfsh app run openrouter/claude-sonnet-45 --input \"{\n  \\\"prompt\\\": \\\"Fact-check this claim: '$CLAIM'\n\nBased on the following evidence:\n$EVIDENCE\n\nProvide:\n1. Verdict (True/False/Partially True/Unverified)\n2. Supporting evidence\n3. Contradicting evidence\n4. Sources\\\"\n}\"\n\nResearch Report Generator\nTOPIC=\"Impact of generative AI on creative industries\"\n\n# 1. Initial research\nOVERVIEW=$(infsh app run tavily/search-assistant --input \"{\\\"query\\\": \\\"$TOPIC overview\\\"}\")\nSTATISTICS=$(infsh app run exa/search --input \"{\\\"query\\\": \\\"$TOPIC statistics data\\\"}\")\nOPINIONS=$(infsh app run tavily/search-assistant --input \"{\\\"query\\\": \\\"$TOPIC expert opinions\\\"}\")\n\n# 2. Generate comprehensive report\ninfsh app run openrouter/claude-sonnet-45 --input \"{\n  \\\"prompt\\\": \\\"Generate a comprehensive research report on: $TOPIC\n\nResearch Data:\n== Overview ==\n$OVERVIEW\n\n== Statistics ==\n$STATISTICS\n\n== Expert Opinions ==\n$OPINIONS\n\nFormat as a professional report with:\n- Executive Summary\n- Key Findings\n- Data Analysis\n- Expert Perspectives\n- Conclusion\n- Sources\\\"\n}\"\n\nQuick Answer with Sources\n# Use Exa Answer for direct factual questions\ninfsh app run exa/answer --input '{\n  \"question\": \"What is the current market cap of NVIDIA?\"\n}'\n\nBest Practices\n1. Query Optimization\n# Bad: Too vague\n\"AI news\"\n\n# Good: Specific and contextual\n\"latest developments in large language models January 2024\"\n\n2. Context Management\n# Summarize long search results before sending to LLM\nSEARCH=$(infsh app run tavily/search-assistant --input '{\"query\": \"...\"}')\n\n# If too long, summarize first\nSUMMARY=$(infsh app run openrouter/claude-haiku-45 --input \"{\n  \\\"prompt\\\": \\\"Summarize these search results in bullet points: $SEARCH\\\"\n}\")\n\n# Then use summary for analysis\ninfsh app run openrouter/claude-sonnet-45 --input \"{\n  \\\"prompt\\\": \\\"Based on this research summary, provide insights: $SUMMARY\\\"\n}\"\n\n3. Source Attribution\n\nAlways ask the LLM to cite sources:\n\ninfsh app run openrouter/claude-sonnet-45 --input '{\n  \"prompt\": \"... Always cite sources in [Source Name](URL) format.\"\n}'\n\n4. Iterative Research\n# First pass: broad search\nINITIAL=$(infsh app run tavily/search-assistant --input '{\"query\": \"topic overview\"}')\n\n# Second pass: dive deeper based on findings\nDEEP=$(infsh app run tavily/search-assistant --input '{\"query\": \"specific aspect from initial search\"}')\n\nPipeline Templates\nAgent Research Tool\n#!/bin/bash\n# research.sh - Reusable research function\n\nresearch() {\n  local query=\"$1\"\n\n  # Search\n  local results=$(infsh app run tavily/search-assistant --input \"{\\\"query\\\": \\\"$query\\\"}\")\n\n  # Analyze\n  infsh app run openrouter/claude-haiku-45 --input \"{\n    \\\"prompt\\\": \\\"Summarize: $results\\\"\n  }\"\n}\n\nresearch \"your query here\"\n\nRelated Skills\n# Web search tools\nnpx skills add inference-sh/skills@web-search\n\n# LLM models\nnpx skills add inference-sh/skills@llm-models\n\n# Content pipelines\nnpx skills add inference-sh/skills@ai-content-pipeline\n\n# Full platform skill\nnpx skills add inference-sh/skills@inference-sh\n\n\nBrowse all apps: infsh app list\n\nDocumentation\nAdding Tools to Agents - Agent tool integration\nBuilding a Research Agent - Full guide"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/okaris/ai-rag-pipeline",
    "publisherUrl": "https://clawhub.ai/okaris/ai-rag-pipeline",
    "owner": "okaris",
    "version": "0.1.5",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/ai-rag-pipeline",
    "downloadUrl": "https://openagent3.xyz/downloads/ai-rag-pipeline",
    "agentUrl": "https://openagent3.xyz/skills/ai-rag-pipeline/agent",
    "manifestUrl": "https://openagent3.xyz/skills/ai-rag-pipeline/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/ai-rag-pipeline/agent.md"
  }
}