[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6QE5HCS0KHHY43W16DERVXQ":3,"skill-same:01M6QE5HCS0KHHY43W16DERVXQ":86},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":26,"publishedAt":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":57,"commitSha":58,"skillDirectory":59,"forksCount":14,"repositoryHtmlUrl":60,"repositoryHomepageUrl":61,"ownerHtmlUrl":62,"ownerBlogUrl":63,"ownerDescription":64,"updatedAt":65,"install":66,"resources":79},"01M6QE5HCS0KHHY43W16DERVXQ","chroma",null,"Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.","Tashima-Tarsh\u002FDisha6.6","Tashima-Tarsh","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F269906498?v=4","01M6PBH98X03XERH0HFT4PFB1P","NITISH KUMAR","01M6PBH9DA0M6KM3Z12P848F0K",0,"MIT","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-chroma\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",[5,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"text","for","Document Retrieval","filter","full","local","self-hosted","use","filtering","rag","projects","knowledge","open","applications","open source","embeddings","vector","search","semantic search","2026-11-10 10:12:30",false,"---\nname: chroma\ndescription: Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.\nlicense: MIT\nmetadata:\n  version: 1.0.0\n  category: knowledge-and-rag\n  maintainer: Kalaris Labs\n  tags: RAG, Chroma, Vector Database, Embeddings, Semantic Search, Open Source, Self-Hosted, Document Retrieval, Metadata Filtering\n  dependencies: chromadb, sentence-transformers\n---\n\n# Chroma - Open-Source Embedding Database\n\nThe AI-native database for building LLM applications with memory.\n\n## When to use Chroma\n\n**Use Chroma when:**\n- Building RAG (retrieval-augmented generation) applications\n- Need local\u002Fself-hosted vector database\n- Want open-source solution (Apache 2.0)\n- Prototyping in notebooks\n- Semantic search over documents\n- Storing embeddings with metadata\n\n**Metrics**:\n- **1,900+ forks**\n- **v1.3.3** (stable, weekly releases)\n- **Apache 2.0 license**\n\n**Use alternatives instead**:\n- **Pinecone**: Managed cloud, auto-scaling\n- **FAISS**: Pure similarity search, no metadata\n- **Weaviate**: Production ML-native database\n- **Qdrant**: High performance, Rust-based\n\n## Quick start\n\n### Installation\n\n```bash\n# Python\npip install chromadb\n\n# JavaScript\u002FTypeScript\nnpm install chromadb @chroma-core\u002Fdefault-embed\n```\n\n### Basic usage (Python)\n\n```python\nimport chromadb\n\n# Create client\nclient = chromadb.Client()\n\n# Create collection\ncollection = client.create_collection(name=\"my_collection\")\n\n# Add documents\ncollection.add(\n    documents=[\"This is document 1\", \"This is document 2\"],\n    metadatas=[{\"source\": \"doc1\"}, {\"source\": \"doc2\"}],\n    ids=[\"id1\", \"id2\"]\n)\n\n# Query\nresults = collection.query(\n    query_texts=[\"document about topic\"],\n    n_results=2\n)\n\nprint(results)\n```\n\n## Core operations\n\n### 1. Create collection\n\n```python\n# Simple collection\ncollection = client.create_collection(\"my_docs\")\n\n# With custom embedding function\nfrom chromadb.utils import embedding_functions\n\nopenai_ef = embedding_functions.OpenAIEmbeddingFunction(\n    api_key=\"your-key\",\n    model_name=\"text-embedding-3-small\"\n)\n\ncollection = client.create_collection(\n    name=\"my_docs\",\n    embedding_function=openai_ef\n)\n\n# Get existing collection\ncollection = client.get_collection(\"my_docs\")\n\n# Delete collection\nclient.delete_collection(\"my_docs\")\n```\n\n### 2. Add documents\n\n```python\n# Add with auto-generated IDs\ncollection.add(\n    documents=[\"Doc 1\", \"Doc 2\", \"Doc 3\"],\n    metadatas=[\n        {\"source\": \"web\", \"category\": \"tutorial\"},\n        {\"source\": \"pdf\", \"page\": 5},\n        {\"source\": \"api\", \"timestamp\": \"2025-01-01\"}\n    ],\n    ids=[\"id1\", \"id2\", \"id3\"]\n)\n\n# Add with custom embeddings\ncollection.add(\n    embeddings=[[0.1, 0.2, ...], [0.3, 0.4, ...]],\n    documents=[\"Doc 1\", \"Doc 2\"],\n    ids=[\"id1\", \"id2\"]\n)\n```\n\n### 3. Query (similarity search)\n\n```python\n# Basic query\nresults = collection.query(\n    query_texts=[\"machine learning tutorial\"],\n    n_results=5\n)\n\n# Query with filters\nresults = collection.query(\n    query_texts=[\"Python programming\"],\n    n_results=3,\n    where={\"source\": \"web\"}\n)\n\n# Query with metadata filters\nresults = collection.query(\n    query_texts=[\"advanced topics\"],\n    where={\n        \"$and\": [\n            {\"category\": \"tutorial\"},\n            {\"difficulty\": {\"$gte\": 3}}\n        ]\n    }\n)\n\n# Access results\nprint(results[\"documents\"])      # List of matching documents\nprint(results[\"metadatas\"])      # Metadata for each doc\nprint(results[\"distances\"])      # Similarity scores\nprint(results[\"ids\"])            # Document IDs\n```\n\n### 4. Get documents\n\n```python\n# Get by IDs\ndocs = collection.get(\n    ids=[\"id1\", \"id2\"]\n)\n\n# Get with filters\ndocs = collection.get(\n    where={\"category\": \"tutorial\"},\n    limit=10\n)\n\n# Get all documents\ndocs = collection.get()\n```\n\n### 5. Update documents\n\n```python\n# Update document content\ncollection.update(\n    ids=[\"id1\"],\n    documents=[\"Updated content\"],\n    metadatas=[{\"source\": \"updated\"}]\n)\n```\n\n### 6. Delete documents\n\n```python\n# Delete by IDs\ncollection.delete(ids=[\"id1\", \"id2\"])\n\n# Delete with filter\ncollection.delete(\n    where={\"source\": \"outdated\"}\n)\n```\n\n## Persistent storage\n\n```python\n# Persist to disk\nclient = chromadb.PersistentClient(path=\".\u002Fchroma_db\")\n\ncollection = client.create_collection(\"my_docs\")\ncollection.add(documents=[\"Doc 1\"], ids=[\"id1\"])\n\n# Data persisted automatically\n# Reload later with same path\nclient = chromadb.PersistentClient(path=\".\u002Fchroma_db\")\ncollection = client.get_collection(\"my_docs\")\n```\n\n## Embedding functions\n\n### Default (Sentence Transformers)\n\n```python\n# Uses sentence-transformers by default\ncollection = client.create_collection(\"my_docs\")\n# Default model: all-MiniLM-L6-v2\n```\n\n### OpenAI\n\n```python\nfrom chromadb.utils import embedding_functions\n\nopenai_ef = embedding_functions.OpenAIEmbeddingFunction(\n    api_key=\"your-key\",\n    model_name=\"text-embedding-3-small\"\n)\n\ncollection = client.create_collection(\n    name=\"openai_docs\",\n    embedding_function=openai_ef\n)\n```\n\n### HuggingFace\n\n```python\nhuggingface_ef = embedding_functions.HuggingFaceEmbeddingFunction(\n    api_key=\"your-key\",\n    model_name=\"sentence-transformers\u002Fall-mpnet-base-v2\"\n)\n\ncollection = client.create_collection(\n    name=\"hf_docs\",\n    embedding_function=huggingface_ef\n)\n```\n\n### Custom embedding function\n\n```python\nfrom chromadb import Documents, EmbeddingFunction, Embeddings\n\nclass MyEmbeddingFunction(EmbeddingFunction):\n    def __call__(self, input: Documents) -> Embeddings:\n        # Your embedding logic\n        return embeddings\n\nmy_ef = MyEmbeddingFunction()\ncollection = client.create_collection(\n    name=\"custom_docs\",\n    embedding_function=my_ef\n)\n```\n\n## Metadata filtering\n\n```python\n# Exact match\nresults = collection.query(\n    query_texts=[\"query\"],\n    where={\"category\": \"tutorial\"}\n)\n\n# Comparison operators\nresults = collection.query(\n    query_texts=[\"query\"],\n    where={\"page\": {\"$gt\": 10}}  # $gt, $gte, $lt, $lte, $ne\n)\n\n# Logical operators\nresults = collection.query(\n    query_texts=[\"query\"],\n    where={\n        \"$and\": [\n            {\"category\": \"tutorial\"},\n            {\"difficulty\": {\"$lte\": 3}}\n        ]\n    }  # Also: $or\n)\n\n# Contains\nresults = collection.query(\n    query_texts=[\"query\"],\n    where={\"tags\": {\"$in\": [\"python\", \"ml\"]}}\n)\n```\n\n## LangChain integration\n\n```python\nfrom langchain_chroma import Chroma\nfrom langchain_openai import OpenAIEmbeddings\nfrom langchain.text_splitter import RecursiveCharacterTextSplitter\n\n# Split documents\ntext_splitter = RecursiveCharacterTextSplitter(chunk_size=1000)\ndocs = text_splitter.split_documents(documents)\n\n# Create Chroma vector store\nvectorstore = Chroma.from_documents(\n    documents=docs,\n    embedding=OpenAIEmbeddings(),\n    persist_directory=\".\u002Fchroma_db\"\n)\n\n# Query\nresults = vectorstore.similarity_search(\"machine learning\", k=3)\n\n# As retriever\nretriever = vectorstore.as_retriever(search_kwargs={\"k\": 5})\n```\n\n## LlamaIndex integration\n\n```python\nfrom llama_index.vector_stores.chroma import ChromaVectorStore\nfrom llama_index.core import VectorStoreIndex, StorageContext\nimport chromadb\n\n# Initialize Chroma\ndb = chromadb.PersistentClient(path=\".\u002Fchroma_db\")\ncollection = db.get_or_create_collection(\"my_collection\")\n\n# Create vector store\nvector_store = ChromaVectorStore(chroma_collection=collection)\nstorage_context = StorageContext.from_defaults(vector_store=vector_store)\n\n# Create index\nindex = VectorStoreIndex.from_documents(\n    documents,\n    storage_context=storage_context\n)\n\n# Query\nquery_engine = index.as_query_engine()\nresponse = query_engine.query(\"What is machine learning?\")\n```\n\n## Server mode\n\n```python\n# Run Chroma server\n# Terminal: chroma run --path .\u002Fchroma_db --port 8000\n\n# Connect to server\nimport chromadb\nfrom chromadb.config import Settings\n\nclient = chromadb.HttpClient(\n    host=\"localhost\",\n    port=8000,\n    settings=Settings(anonymized_telemetry=False)\n)\n\n# Use as normal\ncollection = client.get_or_create_collection(\"my_docs\")\n```\n\n## Best practices\n\n1. **Use persistent client** - Don't lose data on restart\n2. **Add metadata** - Enables filtering and tracking\n3. **Batch operations** - Add multiple docs at once\n4. **Choose right embedding model** - Balance speed\u002Fquality\n5. **Use filters** - Narrow search space\n6. **Unique IDs** - Avoid collisions\n7. **Regular backups** - Copy chroma_db directory\n8. **Monitor collection size** - Scale up if needed\n9. **Test embedding functions** - Ensure quality\n10. **Use server mode for production** - Better for multi-user\n\n## Performance\n\n| Operation | Latency | Notes |\n|-----------|---------|-------|\n| Add 100 docs | ~1-3s | With embedding |\n| Query (top 10) | ~50-200ms | Depends on collection size |\n| Metadata filter | ~10-50ms | Fast with proper indexing |\n\n## Resources\n\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fchroma-core\u002Fchroma ⭐ 24,300+\n- **Docs**: https:\u002F\u002Fdocs.trychroma.com\n- **Discord**: https:\u002F\u002Fdiscord.gg\u002FMMeYNTmh3x\n- **Version**: 1.3.3+\n- **License**: Apache 2.0\n\n## Agent operating procedure\n\n1. **Check the environment.** Confirm the corpus, embedding model and vector store versions, and where the index will live.\n2. **Pin down the inputs.** Confirm formats, identifiers and parameters from the data or the user. Ask rather than guess any value that changes the result.\n3. **Run a small version first.** Index a small subset and test retrieval on known question-passage pairs.\n4. **Execute the full task** using the instructions and references above.\n5. **Validate the result.** Measure recall@k on a labeled set; answers cite retrieved passages only.\n6. **Report.** State what was run (versions, commands, parameters), what was checked, and what is still uncertain.\n\n| If this happens | Do this |\n|---|---|\n| Retrieval returns irrelevant chunks | Revisit chunking, add BM25\u002Fhybrid search, or re-rank before changing the generator. |\n| A function, flag or endpoint in these instructions is missing in the installed version | Check the installed version's own documentation (`help()`, `--help`, official docs), adapt, and tell the user. Never invent an API. |\n| A required input, identifier or parameter is ambiguous | Ask the user, or state the assumption explicitly before running. |\n\n**Integrity rules**\n\n- Never fabricate results, parameters, identifiers, citations or statistics. If something cannot be run or verified, say so plainly.\n- Answers must come from retrieved text; say when the corpus does not contain the answer.\n- Treat version-specific details here as possibly outdated: confirm them against the official documentation for the installed version.\n- Ask before actions that cost money, consume shared GPUs or cloud quota, touch personal or patient data, or cannot be undone.\n\n## Related skills\n\n- `llamaindex`: Data framework for building LLM applications with RAG.\n- `langchain`: Framework for building LLM-powered applications with agents, chains, and RAG.\n- `qdrant-vector-search`: High-performance vector similarity search engine for RAG and semantic search.\n","# Chroma - Open-Source Embedding Database\n\nThe AI-native database for building LLM applications with memory.\n\n## When to use Chroma\n\n**Use Chroma when:**\n- Building RAG (retrieval-augmented generation) applications\n- Need local\u002Fself-hosted vector database\n- Want open-source solution (Apache 2.0)\n- Prototyping in notebooks\n- Semantic search over documents\n- Storing embeddings with metadata\n\n**Metrics**:\n- **1,900+ forks**\n- **v1.3.3** (stable, weekly releases)\n- **Apache 2.0 license**\n\n**Use alternatives instead**:\n- **Pinecone**: Managed cloud, auto-scaling\n- **FAISS**: Pure similarity search, no metadata\n- **Weaviate**: Production ML-native database\n- **Qdrant**: High performance, Rust-based\n\n## Quick start\n\n### Installation\n\n```bash\n# Python\npip install chromadb\n\n# JavaScript\u002FTypeScript\nnpm install chromadb @chroma-core\u002Fdefault-embed\n```\n\n### Basic usage (Python)\n\n```python\nimport chromadb\n\n# Create client\nclient = chromadb.Client()\n\n# Create collection\ncollection = client.create_collection(name=\"my_collection\")\n\n# Add documents\ncollection.add(\n    documents=[\"This is document 1\", \"This is document 2\"],\n    metadatas=[{\"source\": \"doc1\"}, {\"source\": \"doc2\"}],\n    ids=[\"id1\", \"id2\"]\n)\n\n# Query\nresults = collection.query(\n    query_texts=[\"document about topic\"],\n    n_results=2\n)\n\nprint(results)\n```\n\n## Core operations\n\n### 1. Create collection\n\n```python\n# Simple collection\ncollection = client.create_collection(\"my_docs\")\n\n# With custom embedding function\nfrom chromadb.utils import embedding_functions\n\nopenai_ef = embedding_functions.OpenAIEmbeddingFunction(\n    api_key=\"your-key\",\n    model_name=\"text-embedding-3-small\"\n)\n\ncollection = client.create_collection(\n    name=\"my_docs\",\n    embedding_function=openai_ef\n)\n\n# Get existing collection\ncollection = client.get_collection(\"my_docs\")\n\n# Delete collection\nclient.delete_collection(\"my_docs\")\n```\n\n### 2. Add documents\n\n```python\n# Add with auto-generated IDs\ncollection.add(\n    documents=[\"Doc 1\", \"Doc 2\", \"Doc 3\"],\n    metadatas=[\n        {\"source\": \"web\", \"category\": \"tutorial\"},\n        {\"source\": \"pdf\", \"page\": 5},\n        {\"source\": \"api\", \"timestamp\": \"2025-01-01\"}\n    ],\n    ids=[\"id1\", \"id2\", \"id3\"]\n)\n\n# Add with custom embeddings\ncollection.add(\n    embeddings=[[0.1, 0.2, ...], [0.3, 0.4, ...]],\n    documents=[\"Doc 1\", \"Doc 2\"],\n    ids=[\"id1\", \"id2\"]\n)\n```\n\n### 3. Query (similarity search)\n\n```python\n# Basic query\nresults = collection.query(\n    query_texts=[\"machine learning tutorial\"],\n    n_results=5\n)\n\n# Query with filters\nresults = collection.query(\n    query_texts=[\"Python programming\"],\n    n_results=3,\n    where={\"source\": \"web\"}\n)\n\n# Query with metadata filters\nresults = collection.query(\n    query_texts=[\"advanced topics\"],\n    where={\n        \"$and\": [\n            {\"category\": \"tutorial\"},\n            {\"difficulty\": {\"$gte\": 3}}\n        ]\n    }\n)\n\n# Access results\nprint(results[\"documents\"])      # List of matching documents\nprint(results[\"metadatas\"])      # Metadata for each doc\nprint(results[\"distances\"])      # Similarity scores\nprint(results[\"ids\"])            # Document IDs\n```\n\n### 4. Get documents\n\n```python\n# Get by IDs\ndocs = collection.get(\n    ids=[\"id1\", \"id2\"]\n)\n\n# Get with filters\ndocs = collection.get(\n    where={\"category\": \"tutorial\"},\n    limit=10\n)\n\n# Get all documents\ndocs = collection.get()\n```\n\n### 5. Update documents\n\n```python\n# Update document content\ncollection.update(\n    ids=[\"id1\"],\n    documents=[\"Updated content\"],\n    metadatas=[{\"source\": \"updated\"}]\n)\n```\n\n### 6. Delete documents\n\n```python\n# Delete by IDs\ncollection.delete(ids=[\"id1\", \"id2\"])\n\n# Delete with filter\ncollection.delete(\n    where={\"source\": \"outdated\"}\n)\n```\n\n## Persistent storage\n\n```python\n# Persist to disk\nclient = chromadb.PersistentClient(path=\".\u002Fchroma_db\")\n\ncollection = client.create_collection(\"my_docs\")\ncollection.add(documents=[\"Doc 1\"], ids=[\"id1\"])\n\n# Data persisted automatically\n# Reload later with same path\nclient = chromadb.PersistentClient(path=\".\u002Fchroma_db\")\ncollection = client.get_collection(\"my_docs\")\n```\n\n## Embedding functions\n\n### Default (Sentence Transformers)\n\n```python\n# Uses sentence-transformers by default\ncollection = client.create_collection(\"my_docs\")\n# Default model: all-MiniLM-L6-v2\n```\n\n### OpenAI\n\n```python\nfrom chromadb.utils import embedding_functions\n\nopenai_ef = embedding_functions.OpenAIEmbeddingFunction(\n    api_key=\"your-key\",\n    model_name=\"text-embedding-3-small\"\n)\n\ncollection = client.create_collection(\n    name=\"openai_docs\",\n    embedding_function=openai_ef\n)\n```\n\n### HuggingFace\n\n```python\nhuggingface_ef = embedding_functions.HuggingFaceEmbeddingFunction(\n    api_key=\"your-key\",\n    model_name=\"sentence-transformers\u002Fall-mpnet-base-v2\"\n)\n\ncollection = client.create_collection(\n    name=\"hf_docs\",\n    embedding_function=huggingface_ef\n)\n```\n\n### Custom embedding function\n\n```python\nfrom chromadb import Documents, EmbeddingFunction, Embeddings\n\nclass MyEmbeddingFunction(EmbeddingFunction):\n    def __call__(self, input: Documents) -> Embeddings:\n        # Your embedding logic\n        return embeddings\n\nmy_ef = MyEmbeddingFunction()\ncollection = client.create_collection(\n    name=\"custom_docs\",\n    embedding_function=my_ef\n)\n```\n\n## Metadata filtering\n\n```python\n# Exact match\nresults = collection.query(\n    query_texts=[\"query\"],\n    where={\"category\": \"tutorial\"}\n)\n\n# Comparison operators\nresults = collection.query(\n    query_texts=[\"query\"],\n    where={\"page\": {\"$gt\": 10}}  # $gt, $gte, $lt, $lte, $ne\n)\n\n# Logical operators\nresults = collection.query(\n    query_texts=[\"query\"],\n    where={\n        \"$and\": [\n            {\"category\": \"tutorial\"},\n            {\"difficulty\": {\"$lte\": 3}}\n        ]\n    }  # Also: $or\n)\n\n# Contains\nresults = collection.query(\n    query_texts=[\"query\"],\n    where={\"tags\": {\"$in\": [\"python\", \"ml\"]}}\n)\n```\n\n## LangChain integration\n\n```python\nfrom langchain_chroma import Chroma\nfrom langchain_openai import OpenAIEmbeddings\nfrom langchain.text_splitter import RecursiveCharacterTextSplitter\n\n# Split documents\ntext_splitter = RecursiveCharacterTextSplitter(chunk_size=1000)\ndocs = text_splitter.split_documents(documents)\n\n# Create Chroma vector store\nvectorstore = Chroma.from_documents(\n    documents=docs,\n    embedding=OpenAIEmbeddings(),\n    persist_directory=\".\u002Fchroma_db\"\n)\n\n# Query\nresults = vectorstore.similarity_search(\"machine learning\", k=3)\n\n# As retriever\nretriever = vectorstore.as_retriever(search_kwargs={\"k\": 5})\n```\n\n## LlamaIndex integration\n\n```python\nfrom llama_index.vector_stores.chroma import ChromaVectorStore\nfrom llama_index.core import VectorStoreIndex, StorageContext\nimport chromadb\n\n# Initialize Chroma\ndb = chromadb.PersistentClient(path=\".\u002Fchroma_db\")\ncollection = db.get_or_create_collection(\"my_collection\")\n\n# Create vector store\nvector_store = ChromaVectorStore(chroma_collection=collection)\nstorage_context = StorageContext.from_defaults(vector_store=vector_store)\n\n# Create index\nindex = VectorStoreIndex.from_documents(\n    documents,\n    storage_context=storage_context\n)\n\n# Query\nquery_engine = index.as_query_engine()\nresponse = query_engine.query(\"What is machine learning?\")\n```\n\n## Server mode\n\n```python\n# Run Chroma server\n# Terminal: chroma run --path .\u002Fchroma_db --port 8000\n\n# Connect to server\nimport chromadb\nfrom chromadb.config import Settings\n\nclient = chromadb.HttpClient(\n    host=\"localhost\",\n    port=8000,\n    settings=Settings(anonymized_telemetry=False)\n)\n\n# Use as normal\ncollection = client.get_or_create_collection(\"my_docs\")\n```\n\n## Best practices\n\n1. **Use persistent client** - Don't lose data on restart\n2. **Add metadata** - Enables filtering and tracking\n3. **Batch operations** - Add multiple docs at once\n4. **Choose right embedding model** - Balance speed\u002Fquality\n5. **Use filters** - Narrow search space\n6. **Unique IDs** - Avoid collisions\n7. **Regular backups** - Copy chroma_db directory\n8. **Monitor collection size** - Scale up if needed\n9. **Test embedding functions** - Ensure quality\n10. **Use server mode for production** - Better for multi-user\n\n## Performance\n\n| Operation | Latency | Notes |\n|-----------|---------|-------|\n| Add 100 docs | ~1-3s | With embedding |\n| Query (top 10) | ~50-200ms | Depends on collection size |\n| Metadata filter | ~10-50ms | Fast with proper indexing |\n\n## Resources\n\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fchroma-core\u002Fchroma ⭐ 24,300+\n- **Docs**: https:\u002F\u002Fdocs.trychroma.com\n- **Discord**: https:\u002F\u002Fdiscord.gg\u002FMMeYNTmh3x\n- **Version**: 1.3.3+\n- **License**: Apache 2.0\n\n## Agent operating procedure\n\n1. **Check the environment.** Confirm the corpus, embedding model and vector store versions, and where the index will live.\n2. **Pin down the inputs.** Confirm formats, identifiers and parameters from the data or the user. Ask rather than guess any value that changes the result.\n3. **Run a small version first.** Index a small subset and test retrieval on known question-passage pairs.\n4. **Execute the full task** using the instructions and references above.\n5. **Validate the result.** Measure recall@k on a labeled set; answers cite retrieved passages only.\n6. **Report.** State what was run (versions, commands, parameters), what was checked, and what is still uncertain.\n\n| If this happens | Do this |\n|---|---|\n| Retrieval returns irrelevant chunks | Revisit chunking, add BM25\u002Fhybrid search, or re-rank before changing the generator. |\n| A function, flag or endpoint in these instructions is missing in the installed version | Check the installed version's own documentation (`help()`, `--help`, official docs), adapt, and tell the user. Never invent an API. |\n| A required input, identifier or parameter is ambiguous | Ask the user, or state the assumption explicitly before running. |\n\n**Integrity rules**\n\n- Never fabricate results, parameters, identifiers, citations or statistics. If something cannot be run or verified, say so plainly.\n- Answers must come from retrieved text; say when the corpus does not contain the answer.\n- Treat version-specific details here as possibly outdated: confirm them against the official documentation for the installed version.\n- Ask before actions that cost money, consume shared GPUs or cloud quota, touch personal or patient data, or cannot be undone.\n\n## Related skills\n\n- `llamaindex`: Data framework for building LLM applications with RAG.\n- `langchain`: Framework for building LLM-powered applications with agents, chains, and RAG.\n- `qdrant-vector-search`: High-performance vector similarity search engine for RAG and semantic search.\n",{"name":5,"license":15,"metadata":51,"description":7},{"tags":52,"version":53,"category":54,"maintainer":55,"dependencies":56},"RAG, Chroma, Vector Database, Embeddings, Semantic Search, Open Source, Self-Hosted, Document Retrieval, Metadata Filtering","1.0.0","knowledge-and-rag","Kalaris Labs","chromadb, sentence-transformers","main","0da4485785ee599388900be50db1635489d53056",".agents\u002Fskills\u002Fkal-chroma","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6","https:\u002F\u002Fdisha6.6.thenitishkr.in\u002F","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh","www.thenitishkr","thenitishkr | AI • Cyber-security • Research\r\n","2026-11-08 03:33:25",{"source":8,"skillName":5,"commands":67,"prompt":77,"zipAvailable":78},[68,71,74],{"tool":69,"command":70},"npx","npx skills add Tashima-Tarsh\u002FDisha6.6 --skill chroma",{"tool":72,"command":73},"bunx","bunx skills add Tashima-Tarsh\u002FDisha6.6 --skill chroma",{"tool":75,"command":76},"pnpm","pnpm dlx skills add Tashima-Tarsh\u002FDisha6.6 --skill chroma","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-chroma\u002FSKILL.md",true,[80],{"path":81,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Fintegration.md","REFERENCE","参考文档",771,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-chroma\u002Freferences\u002Fintegration.md",[87,114,138,165,190,214],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":96,"publishedAt":46},"01M6QRD07D4TGNDK6VJ4EHF8BV","youtube-full","Use when the user needs YouTube transcripts, video search, channel browsing, playlist extraction, or content monitoring. Trigger phrases: 'get the transcript for', 'search YouTube for', 'what are the latest videos on', 'list this playlist', 'monitor this channel', or any request involving a YouTube URL, video ID, or @handle. Do NOT use for downloading video or audio files, YouTube engagement data (likes, comments), or private\u002Fage-restricted videos.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fyoutube-full\u002FSKILL.md",[93],{"categoryNo":94,"categoryName":95,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[97,98,31,99,44,100,101,102,103,104,105,106,107,108,109,110,28,111,112,113],"youtube full","youtube","transcript","monitoring","data","Video","Audio","list","files","do","get","age","trigger","URL","browsing","request","youtube transcripts",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":46},"01M6QRCJ3112VYPA97YG7KGMC2","x-twitter-growth","X\u002FTwitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X\u002FTwitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fx-twitter-growth\u002FSKILL.md",[],[121,122,123,124,44,125,126,127,128,129,130,131,132,133,34,134,135,136,137,28],"twitter","x twitter growth","growth","research","content","engineering","plan","web search","competitors","analyze","engine","write","strategy","platform","grow","posting","competitive",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":147,"publishedAt":46},"01M6QRBN3EHQNJY42RERP7A149","write-a-skill","Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, build, or author a new skill.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwrite-a-skill\u002FSKILL.md",[144],{"categoryNo":145,"categoryName":146,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[148,132,149,150,151,152,153,154,34,155,156,57,157,158,159,160,161,162,163,164],"write a skill","github","create","https","productivity","matt pocock","direct","example","build","new skill","structure","new agent","resources","with","tree","progressive disclosure","author",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":171,"publishedAt":46},"01M6QRB6G8P33PNGAF9Y69EJ9T","wrap-up","Close out a launched Claude Managed Agent — recap every primitive the founder now owns, regenerate the single-file overview page, and suggest the next 1-2 upgrades. Use when the user says \"wrap up\", \"close this out\", \"what do I own now\", \"give me the summary\", \"recap the agent\", or when the orchestrator routes phase=wrap-up. primitives_inventory.py tables everything owned (agent, environment, session, memory, outcome, deployment); overview_page.py regenerates a self-contained .\u002Fmy-agent\u002Fagent-overview.html; upgrade_suggester.py ranks the next moves from recorded deferrals plus standing hardening steps. Companion to run-without-you; the last stop before phase=done.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwrap-up\u002FSKILL.md",[],[172,173,174,175,176,177,178,179,180,34,181,106,182,183,184,185,186,187,188,189],"wrap up","up","wrap","gemini","deployment","run","file","hardening","closeout","stop","upgrade","founder","close","companion","you","tables","directions","phase",{"skillNo":191,"name":192,"nameZh":6,"description":193,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":194,"categories":195,"keywords":197,"publishedAt":46},"01M6QRA5AYC1RBFZ39GTWGS3N8","workflow-builder","Design and write deterministic multi-agent workflow scripts (.js files in .claude\u002Fworkflows\u002F) for Claude Code's Workflow tool. Use when a user wants to build, create, author, scaffold, or run a custom Claude Code workflow, orchestrate sub-agents (fan-out, pipeline, loop, judge-panel), or automate a repeatable multi-step task across fresh-context agents.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fworkflow-builder\u002FSKILL.md",[196],{"categoryNo":145,"categoryName":146,"taxonomyType":21,"taxonomyTypeDesc":22},[198,199,200,201,202,150,177,203,204,205,206,207,132,208,105,209,210,211,212,213],"workflow","workflow builder","builder","design","workflows","code","orchestrate","pipeline","loop","multi-agent","context","across","fresh","scripts","judge","claude code workflow",{"skillNo":215,"name":216,"nameZh":6,"description":217,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":218,"categories":219,"keywords":220,"publishedAt":46},"01M6QR7QMCZESKQA0ERW1E657M","weekly-review","Use when someone wants to run a weekly review, close open loops, audit stalled projects and commitments, get their system back to trusted, restart a lapsed review habit, or says \"\u002Fcs:weekly-review\". Walks David Allen's three-phase loop — GET CLEAR, GET CURRENT, GET CREATIVE — with deterministic scripts that inventory open loops, gate the checklist with named gaps, and score commitment health 0-100.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweekly-review\u002FSKILL.md",[],[221,222,223,224,225,226,227,39,228,206,37,229,230,231,232,233,107,234,235,189],"review","weekly review","weekly","deterministic scripts","reflect","feeds","inventory","team","project-management","scanner","conversation","back","project","sprint","cadence"]