{
  "schemaVersion": "1.0",
  "item": {
    "slug": "langchain",
    "name": "LangChain",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/ivangdavila/langchain",
    "canonicalUrl": "https://clawhub.ai/ivangdavila/langchain",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/langchain",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=langchain",
    "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",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/langchain"
    },
    "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/langchain",
    "agentPageUrl": "https://openagent3.xyz/skills/langchain/agent",
    "manifestUrl": "https://openagent3.xyz/skills/langchain/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/langchain/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": "LCEL Basics",
        "body": "| pipes output to next — prompt | llm | parser\nRunnablePassthrough() forwards input unchanged — use in parallel branches\nRunnableParallel runs branches concurrently — {\"a\": chain1, \"b\": chain2}\n.invoke() for single, .batch() for multiple, .stream() for tokens\nInput must match expected keys — {\"question\": x} not just x if prompt expects {question}"
      },
      {
        "title": "Memory Gotchas",
        "body": "Memory doesn't auto-persist between sessions — save/load explicitly\nConversationBufferMemory grows unbounded — use ConversationSummaryMemory for long chats\nMemory key must match prompt variable — memory_key=\"chat_history\" needs {chat_history} in prompt\nreturn_messages=True for chat models — False returns string for completion models"
      },
      {
        "title": "RAG Chunking",
        "body": "Chunk size affects retrieval quality — too small loses context, too large dilutes relevance\nChunk overlap prevents cutting mid-sentence — 10-20% overlap typical\nRecursiveCharacterTextSplitter preserves structure — splits on paragraphs, then sentences\nEmbedding dimension must match vector store — mixing models causes silent failures"
      },
      {
        "title": "Output Parsers",
        "body": "PydanticOutputParser needs format instructions in prompt — call .get_format_instructions()\nParser failures aren't always loud — malformed JSON may partially parse\nOutputFixingParser retries with LLM — wraps another parser, fixes errors\nwith_structured_output() on chat models — cleaner than manual parsing for supported models"
      },
      {
        "title": "Retrieval",
        "body": "similarity_search returns documents — .page_content for text\nk parameter controls results count — more isn't always better, noise increases\nMetadata filtering before similarity — filter={\"source\": \"docs\"} in most vector stores\nmax_marginal_relevance_search for diversity — avoids redundant similar chunks"
      },
      {
        "title": "Agents",
        "body": "Agents decide tool order dynamically — chains are fixed sequence\nTool descriptions matter — agent uses them to decide when to call\nhandle_parsing_errors=True — prevents crash on malformed agent output\nMax iterations prevents infinite loops — max_iterations=10 default may be too low"
      },
      {
        "title": "Common Mistakes",
        "body": "Prompt template variables case-sensitive — {Question} ≠ {question}\nChat models need message format — ChatPromptTemplate, not PromptTemplate\nCallbacks not propagating — pass config={\"callbacks\": [...]} through chain\nRate limits crash silently sometimes — wrap in retry logic\nToken count exceeds context — use trim_messages or summarization for long histories"
      }
    ],
    "body": "LCEL Basics\n| pipes output to next — prompt | llm | parser\nRunnablePassthrough() forwards input unchanged — use in parallel branches\nRunnableParallel runs branches concurrently — {\"a\": chain1, \"b\": chain2}\n.invoke() for single, .batch() for multiple, .stream() for tokens\nInput must match expected keys — {\"question\": x} not just x if prompt expects {question}\nMemory Gotchas\nMemory doesn't auto-persist between sessions — save/load explicitly\nConversationBufferMemory grows unbounded — use ConversationSummaryMemory for long chats\nMemory key must match prompt variable — memory_key=\"chat_history\" needs {chat_history} in prompt\nreturn_messages=True for chat models — False returns string for completion models\nRAG Chunking\nChunk size affects retrieval quality — too small loses context, too large dilutes relevance\nChunk overlap prevents cutting mid-sentence — 10-20% overlap typical\nRecursiveCharacterTextSplitter preserves structure — splits on paragraphs, then sentences\nEmbedding dimension must match vector store — mixing models causes silent failures\nOutput Parsers\nPydanticOutputParser needs format instructions in prompt — call .get_format_instructions()\nParser failures aren't always loud — malformed JSON may partially parse\nOutputFixingParser retries with LLM — wraps another parser, fixes errors\nwith_structured_output() on chat models — cleaner than manual parsing for supported models\nRetrieval\nsimilarity_search returns documents — .page_content for text\nk parameter controls results count — more isn't always better, noise increases\nMetadata filtering before similarity — filter={\"source\": \"docs\"} in most vector stores\nmax_marginal_relevance_search for diversity — avoids redundant similar chunks\nAgents\nAgents decide tool order dynamically — chains are fixed sequence\nTool descriptions matter — agent uses them to decide when to call\nhandle_parsing_errors=True — prevents crash on malformed agent output\nMax iterations prevents infinite loops — max_iterations=10 default may be too low\nCommon Mistakes\nPrompt template variables case-sensitive — {Question} ≠ {question}\nChat models need message format — ChatPromptTemplate, not PromptTemplate\nCallbacks not propagating — pass config={\"callbacks\": [...]} through chain\nRate limits crash silently sometimes — wrap in retry logic\nToken count exceeds context — use trim_messages or summarization for long histories"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ivangdavila/langchain",
    "publisherUrl": "https://clawhub.ai/ivangdavila/langchain",
    "owner": "ivangdavila",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/langchain",
    "downloadUrl": "https://openagent3.xyz/downloads/langchain",
    "agentUrl": "https://openagent3.xyz/skills/langchain/agent",
    "manifestUrl": "https://openagent3.xyz/skills/langchain/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/langchain/agent.md"
  }
}