[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CTYX5AX9D0CK5THQBRWS1Q":3,"skill-same:01M7CTYX5AX9D0CK5THQBRWS1Q":72},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":42,"commitSha":43,"skillDirectory":44,"forksCount":13,"repositoryHtmlUrl":45,"repositoryHomepageUrl":6,"ownerHtmlUrl":46,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":47,"install":48,"resources":61},"01M7CTYX5AX9D0CK5THQBRWS1Q","pinecone-research",null,"Agent RAG and long-term memory with Pinecone.","dwikanugraha13\u002FProject-Anara","dwikanugraha13","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F63535036?v=4","01M7CTBN0DG8GDNP4QZ68W8M0A","01M7CTBN10Q015JDBYJS6AJRGN",0,"MIT","https:\u002F\u002Fgithub.com\u002Fdwikanugraha13\u002FProject-Anara\u002Fblob\u002Fmain\u002Fbackend\u002Foptional-skills\u002Fresearch\u002Fpinecone-research\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: pinecone-research\ndescription: Agent RAG and long-term memory with Pinecone.\nversion: 1.0.0\nauthor: immuhammadfurqan\nlicense: MIT\ndependencies: [pinecone-client, langchain-pinecone]\nplatforms: [linux, macos, windows]\nmetadata:\n  anara:\n    tags: [RAG, Pinecone, Memory, Research, Vector Database, Agent, Retrieval]\n\n---\n\n# Pinecone Research — Agent RAG & Long-Term Memory\n\nUse Pinecone as a retrieval-augmented generation (RAG) backend for agent\nconversations: persist embeddings, retrieve relevant context from past\nsessions, and build long-term memory.\n\n## When to use this skill\n\n**Use when:**\n- Building agent RAG pipelines with Pinecone as the vector store\n- Need persistent long-term memory across agent sessions\n- Combining retrieval with agent tool use\n- Researching or prototyping semantic search workflows\n\n**Use the mlops\u002Fpinecone skill instead when:**\n- Need a general Pinecone reference (index management, CRUD, hybrid search)\n- Working on production infrastructure without agent integration\n\n## Quick start\n\n### Setup\n\n```bash\npip install pinecone-client langchain-pinecone langchain-openai\n```\n\nSet your API key:\n```bash\nexport PINECONE_API_KEY=\"your-api-key\"\n```\n\n### Basic RAG pipeline\n\n```python\nfrom pinecone import Pinecone, ServerlessSpec\nfrom langchain_pinecone import PineconeVectorStore\nfrom langchain_openai import OpenAIEmbeddings\n\n# Initialize Pinecone\npc = Pinecone(api_key=os.environ[\"PINECONE_API_KEY\"])\n\n# Create or connect to index\nindex_name = \"agent-memory\"\nif index_name not in [i.name for i in pc.list_indexes()]:\n    pc.create_index(\n        name=index_name,\n        dimension=1536,\n        metric=\"cosine\",\n        spec=ServerlessSpec(cloud=\"aws\", region=\"us-east-1\"),\n    )\n\n# Build vector store\nvectorstore = PineconeVectorStore.from_documents(\n    documents=docs,\n    embedding=OpenAIEmbeddings(),\n    index_name=index_name,\n)\n\n# Retrieve relevant context\nretriever = vectorstore.as_retriever(search_kwargs={\"k\": 5})\nresults = retriever.invoke(\"What did the agent discuss yesterday?\")\n```\n\n### Namespace-based session memory\n\n```python\n# Store per-session memory\nvectorstore = PineconeVectorStore(\n    index=pc.Index(index_name),\n    embedding=OpenAIEmbeddings(),\n    namespace=f\"session-{session_id}\",\n)\n\n# Query across all sessions (no namespace filter)\nall_memory = PineconeVectorStore(\n    index=pc.Index(index_name),\n    embedding=OpenAIEmbeddings(),\n)\nresults = all_memory.similarity_search(\"relevant query\", k=10)\n```\n\n## Best practices\n\n1. **Namespace by session or user** — isolate data for multi-tenant agents\n2. **Batch upserts** — 100–200 vectors per batch for efficiency\n3. **Metadata filtering** — tag vectors with session ID, timestamp, topic\n4. **Prune old memory** — delete stale namespaces to control costs\n5. **Use serverless** — auto-scaling, pay-per-use pricing\n\n## Resources\n\n- **Pinecone Docs**: https:\u002F\u002Fdocs.pinecone.io\n- **LangChain Integration**: https:\u002F\u002Fpython.langchain.com\u002Fdocs\u002Fintegrations\u002Fvectorstores\u002Fpinecone\n- **Free Tier**: 1 index, 100K vectors (1536 dimensions)\n","# Pinecone Research — Agent RAG & Long-Term Memory\n\nUse Pinecone as a retrieval-augmented generation (RAG) backend for agent\nconversations: persist embeddings, retrieve relevant context from past\nsessions, and build long-term memory.\n\n## When to use this skill\n\n**Use when:**\n- Building agent RAG pipelines with Pinecone as the vector store\n- Need persistent long-term memory across agent sessions\n- Combining retrieval with agent tool use\n- Researching or prototyping semantic search workflows\n\n**Use the mlops\u002Fpinecone skill instead when:**\n- Need a general Pinecone reference (index management, CRUD, hybrid search)\n- Working on production infrastructure without agent integration\n\n## Quick start\n\n### Setup\n\n```bash\npip install pinecone-client langchain-pinecone langchain-openai\n```\n\nSet your API key:\n```bash\nexport PINECONE_API_KEY=\"your-api-key\"\n```\n\n### Basic RAG pipeline\n\n```python\nfrom pinecone import Pinecone, ServerlessSpec\nfrom langchain_pinecone import PineconeVectorStore\nfrom langchain_openai import OpenAIEmbeddings\n\n# Initialize Pinecone\npc = Pinecone(api_key=os.environ[\"PINECONE_API_KEY\"])\n\n# Create or connect to index\nindex_name = \"agent-memory\"\nif index_name not in [i.name for i in pc.list_indexes()]:\n    pc.create_index(\n        name=index_name,\n        dimension=1536,\n        metric=\"cosine\",\n        spec=ServerlessSpec(cloud=\"aws\", region=\"us-east-1\"),\n    )\n\n# Build vector store\nvectorstore = PineconeVectorStore.from_documents(\n    documents=docs,\n    embedding=OpenAIEmbeddings(),\n    index_name=index_name,\n)\n\n# Retrieve relevant context\nretriever = vectorstore.as_retriever(search_kwargs={\"k\": 5})\nresults = retriever.invoke(\"What did the agent discuss yesterday?\")\n```\n\n### Namespace-based session memory\n\n```python\n# Store per-session memory\nvectorstore = PineconeVectorStore(\n    index=pc.Index(index_name),\n    embedding=OpenAIEmbeddings(),\n    namespace=f\"session-{session_id}\",\n)\n\n# Query across all sessions (no namespace filter)\nall_memory = PineconeVectorStore(\n    index=pc.Index(index_name),\n    embedding=OpenAIEmbeddings(),\n)\nresults = all_memory.similarity_search(\"relevant query\", k=10)\n```\n\n## Best practices\n\n1. **Namespace by session or user** — isolate data for multi-tenant agents\n2. **Batch upserts** — 100–200 vectors per batch for efficiency\n3. **Metadata filtering** — tag vectors with session ID, timestamp, topic\n4. **Prune old memory** — delete stale namespaces to control costs\n5. **Use serverless** — auto-scaling, pay-per-use pricing\n\n## Resources\n\n- **Pinecone Docs**: https:\u002F\u002Fdocs.pinecone.io\n- **LangChain Integration**: https:\u002F\u002Fpython.langchain.com\u002Fdocs\u002Fintegrations\u002Fvectorstores\u002Fpinecone\n- **Free Tier**: 1 index, 100K vectors (1536 dimensions)\n",{"name":5,"author":23,"license":14,"version":24,"metadata":25,"platforms":35,"description":7,"dependencies":39},"immuhammadfurqan","1.0.0",{"anara":26},{"tags":27},[28,29,30,31,32,33,34],"RAG","Pinecone","Memory","Research","Vector Database","Agent","Retrieval",[36,37,38],"linux","macos","windows",[40,41],"pinecone-client","langchain-pinecone","main","3e6d6b7ffb6ab43ddf3991509e5cfb5f8c90cd1a","backend\u002Foptional-skills\u002Fresearch\u002Fpinecone-research","https:\u002F\u002Fgithub.com\u002Fdwikanugraha13\u002FProject-Anara","https:\u002F\u002Fgithub.com\u002Fdwikanugraha13","2026-10-13 07:57:21",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add dwikanugraha13\u002FProject-Anara --skill pinecone-research",{"tool":54,"command":55},"bunx","bunx skills add dwikanugraha13\u002FProject-Anara --skill pinecone-research",{"tool":57,"command":58},"pnpm","pnpm dlx skills add dwikanugraha13\u002FProject-Anara --skill pinecone-research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdwikanugraha13\u002FProject-Anara\u002Fblob\u002Fmain\u002Fbackend\u002Foptional-skills\u002Fresearch\u002Fpinecone-research\u002FSKILL.md",true,[62,68],{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},"scripts\u002Fmemory_manager.py","SCRIPT","脚本",5360,"https:\u002F\u002Fgithub.com\u002Fdwikanugraha13\u002FProject-Anara\u002Fblob\u002Fmain\u002Fbackend\u002Foptional-skills\u002Fresearch\u002Fpinecone-research\u002Fscripts\u002Fmemory_manager.py",{"path":69,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":70,"sourceHtmlUrl":71},"scripts\u002Frag_pipeline.py",5374,"https:\u002F\u002Fgithub.com\u002Fdwikanugraha13\u002FProject-Anara\u002Fblob\u002Fmain\u002Fbackend\u002Foptional-skills\u002Fresearch\u002Fpinecone-research\u002Fscripts\u002Frag_pipeline.py",[73,80,87,95,102,109],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M7CVK8W5MPQ8H45A6XE6RPK1","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002Fdwikanugraha13\u002FProject-Anara\u002Fblob\u002Fmain\u002Fbackend\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M7CVK56KG9399ZZVE9KM54WS","xurl","X\u002FTwitter via xurl CLI: raw post search, posting, DM, media.","https:\u002F\u002Fgithub.com\u002Fdwikanugraha13\u002FProject-Anara\u002Fblob\u002Fmain\u002Fbackend\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":91,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":18},"01M7CVK22A44A88NPPBAC1FVQP","xlsx","Create, read, edit Excel .xlsx workbooks and CSVs.","https:\u002F\u002Fgithub.com\u002Fdwikanugraha13\u002FProject-Anara\u002Fblob\u002Fmain\u002Fbackend\u002Fskills\u002Fxlsx\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fdwikanugraha13\u002FProject-Anara\u002Fblob\u002Fmain\u002Fbackend\u002Fskills\u002Fxlsx\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":18},"01M7CVJX88C8PY2T6RQZ5GCG15","weights-and-biases","W&B: log ML experiments, sweeps, model registry, dashboards.","https:\u002F\u002Fgithub.com\u002Fdwikanugraha13\u002FProject-Anara\u002Fblob\u002Fmain\u002Fbackend\u002Fskills\u002Fweights-and-biases\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":18},"01M7CVJR3W1FBRGC56DG6BJ1Y3","weekly-review-planning","Weekly reset: commitments, stalled work, next-week plan.","https:\u002F\u002Fgithub.com\u002Fdwikanugraha13\u002FProject-Anara\u002Fblob\u002Fmain\u002Fbackend\u002Fskills\u002Fweekly-review-planning\u002FSKILL.md",[],[],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":18},"01M7CVJGPJNPQDM8S1KTTMJN7M","touchdesigner-mcp","Control TouchDesigner via twozero MCP.","https:\u002F\u002Fgithub.com\u002Fdwikanugraha13\u002FProject-Anara\u002Fblob\u002Fmain\u002Fbackend\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[]]