[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CC81RR6D1X7XF4HA897ERN":3,"skill-same:01M7CC81RR6D1X7XF4HA897ERN":54},{"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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":14,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7CC81RR6D1X7XF4HA897ERN","weaviate-local-setup",null,"Set up and manage a local Weaviate instance using Docker","shenyimings\u002Fskillet","shenyimings","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F89332218?v=4","01M7C9KHMXPPXMQJCKN78FKB06","Yiming Shen","01M7C9KHP4KS809T2A9T64YDWE",0,"MIT","https:\u002F\u002Fgithub.com\u002Fshenyimings\u002Fskillet\u002Fblob\u002Fmain\u002Fbenchmark\u002Fwild\u002Fdev\u002Fsuspicious\u002Fsaskinosie__weaviate-claude-skills__weaviate-local-setup\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: weaviate-local-setup\ndescription: Set up and manage a local Weaviate instance using Docker\nversion: 1.0.0\ndependencies: []\n---\n\n# Weaviate Local Setup Skill\n\nRun Weaviate locally using Docker for development, testing, and avoiding network restrictions in Claude Desktop\u002FWeb.\n\n## Why Use Local Weaviate?\n\n**Benefits:**\n- No network restrictions in Claude Desktop\u002FWeb\n- Free (no cloud costs)\n- Full control over data and configuration\n- Fast development\u002Ftesting cycles\n- Works offline\n- No API key management for cloud instances\n\n**Best for:**\n- Development and testing\n- Learning Weaviate\n- Working in Claude Desktop with network restrictions\n- Privacy-sensitive projects\n\n## Prerequisites\n\n**Required:**\n- Docker Desktop installed and running\n- Available ports: 8080 (Weaviate), 8081 (optional for Weaviate Console)\n- Python 3.8+ installed\n\n**Optional (for specific vectorizers):**\n- OpenAI API key (for text2vec-openai)\n- Cohere API key (for text2vec-cohere)\n- Anthropic API key (for generative-anthropic)\n\n## Python Environment Setup\n\n**IMPORTANT: Do this FIRST before using any Weaviate skills!**\n\nClaude will create a virtual environment and install dependencies to avoid conflicts with your system Python.\n\n### Step 1: Create Virtual Environment\n\n```bash\n# Navigate to the weaviate-claude-skills directory\ncd ~\u002FDocuments\u002Fweaviate-claude-skills\n\n# Create virtual environment\npython3 -m venv .venv\n\n# Activate it\nsource .venv\u002Fbin\u002Factivate  # macOS\u002FLinux\n# OR\n.venv\\Scripts\\activate     # Windows\n```\n\n### Step 2: Install Dependencies\n\n```bash\n# Install required packages\npip install weaviate-client python-dotenv\n\n# Optional: Install additional packages for specific vectorizers\npip install openai  # If using OpenAI vectorizer\npip install cohere  # If using Cohere vectorizer\n```\n\n**Or install everything at once:**\n```bash\npip install -r requirements.txt\n```\n\n### Step 3: Verify Installation\n\n```python\nimport subprocess\nimport sys\n\n# Check if dependencies are installed\ntry:\n    import weaviate\n    from dotenv import load_dotenv\n    print(\"✅ All required packages are installed!\")\nexcept ImportError as e:\n    print(f\"❌ Missing package: {e}\")\n    print(\"Installing dependencies...\")\n    subprocess.check_call([sys.executable, \"-m\", \"pip\", \"install\",\n                          \"weaviate-client\", \"python-dotenv\"])\n    print(\"✅ Dependencies installed successfully!\")\n```\n\n### When Using Claude\n\n**Claude will check and ensure dependencies are installed before running any Weaviate code.**\n\nIf you see errors about missing packages, Claude will:\n1. Check if the virtual environment exists\n2. Create it if needed\n3. Install required dependencies\n4. Proceed with your request\n\n**Pro Tip:** Keep the virtual environment activated throughout your Claude session for best results.\n\n## Quick Start\n\n### Option 1: Basic Setup (No API Keys Required)\n\nUse Weaviate's built-in vectorizer (no external API needed):\n\n```bash\n# Start Weaviate with transformers (runs locally, no API key)\ndocker run -d \\\n  --name weaviate \\\n  -p 8080:8080 \\\n  -p 50051:50051 \\\n  -e QUERY_DEFAULTS_LIMIT=25 \\\n  -e AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED=true \\\n  -e PERSISTENCE_DATA_PATH='\u002Fvar\u002Flib\u002Fweaviate' \\\n  -e DEFAULT_VECTORIZER_MODULE='text2vec-transformers' \\\n  -e ENABLE_MODULES='text2vec-transformers' \\\n  -e TRANSFORMERS_INFERENCE_API='http:\u002F\u002Ft2v-transformers:8080' \\\n  -e CLUSTER_HOSTNAME='node1' \\\n  semitechnologies\u002Fweaviate:1.28.1\n\n# Start the transformers module\ndocker run -d \\\n  --name t2v-transformers \\\n  -e ENABLE_CUDA=0 \\\n  semitechnologies\u002Ftransformers-inference:sentence-transformers-multi-qa-MiniLM-L6-cos-v1\n```\n\n**Connection:**\n```\nWEAVIATE_URL=localhost:8080\nWEAVIATE_API_KEY=  # Leave empty for local\n```\n\n### Option 2: With OpenAI Vectorizer\n\nUse OpenAI embeddings (requires OpenAI API key):\n\n```bash\ndocker run -d \\\n  --name weaviate \\\n  -p 8080:8080 \\\n  -p 50051:50051 \\\n  -e QUERY_DEFAULTS_LIMIT=25 \\\n  -e AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED=true \\\n  -e PERSISTENCE_DATA_PATH='\u002Fvar\u002Flib\u002Fweaviate' \\\n  -e DEFAULT_VECTORIZER_MODULE='text2vec-openai' \\\n  -e ENABLE_MODULES='text2vec-openai,generative-openai' \\\n  -e CLUSTER_HOSTNAME='node1' \\\n  semitechnologies\u002Fweaviate:1.28.1\n```\n\n**Connection (.env):**\n```\nWEAVIATE_URL=localhost:8080\nWEAVIATE_API_KEY=  # Leave empty\nOPENAI_API_KEY=your-openai-key-here\n```\n\n### Option 3: Docker Compose (Recommended for Production)\n\nSee `docker-compose.yml` in this folder (created separately).\n\n```bash\n# Start Weaviate\ndocker-compose up -d\n\n# Check status\ndocker-compose ps\n\n# View logs\ndocker-compose logs -f weaviate\n\n# Stop Weaviate\ndocker-compose down\n\n# Stop and remove data\ndocker-compose down -v\n```\n\n## Docker Commands Reference\n\n### Container Management\n\n```bash\n# Start Weaviate\ndocker start weaviate\n\n# Stop Weaviate\ndocker stop weaviate\n\n# Restart Weaviate\ndocker restart weaviate\n\n# Check if running\ndocker ps | grep weaviate\n\n# View logs\ndocker logs weaviate\n\n# Follow logs in real-time\ndocker logs -f weaviate\n\n# Remove container (keeps data)\ndocker rm weaviate\n\n# Remove container and data volume\ndocker rm -v weaviate\n```\n\n### Health Checks\n\n```bash\n# Check if Weaviate is ready\ncurl http:\u002F\u002Flocalhost:8080\u002Fv1\u002F.well-known\u002Fready\n\n# Check Weaviate metadata\ncurl http:\u002F\u002Flocalhost:8080\u002Fv1\u002Fmeta\n\n# Expected response:\n# {\"hostname\":\"http:\u002F\u002F[::]:8080\",\"modules\":{...},\"version\":\"1.28.1\"}\n```\n\n### Data Persistence\n\nWeaviate data is stored in Docker volumes. To persist data across container restarts:\n\n```bash\n# Create a named volume\ndocker volume create weaviate-data\n\n# Run with named volume\ndocker run -d \\\n  --name weaviate \\\n  -p 8080:8080 \\\n  -v weaviate-data:\u002Fvar\u002Flib\u002Fweaviate \\\n  -e PERSISTENCE_DATA_PATH='\u002Fvar\u002Flib\u002Fweaviate' \\\n  -e AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED=true \\\n  semitechnologies\u002Fweaviate:1.28.1\n\n# List volumes\ndocker volume ls\n\n# Inspect volume\ndocker volume inspect weaviate-data\n\n# Backup data (export volume to tar)\ndocker run --rm -v weaviate-data:\u002Fdata -v $(pwd):\u002Fbackup \\\n  ubuntu tar czf \u002Fbackup\u002Fweaviate-backup.tar.gz \u002Fdata\n\n# Restore data (import tar to volume)\ndocker run --rm -v weaviate-data:\u002Fdata -v $(pwd):\u002Fbackup \\\n  ubuntu tar xzf \u002Fbackup\u002Fweaviate-backup.tar.gz -C \u002F\n```\n\n## Python Connection Code\n\nOnce Weaviate is running locally, connect using:\n\n```python\nimport weaviate\nimport os\nfrom dotenv import load_dotenv\n\nload_dotenv()\n\n# Connect to local Weaviate (no authentication)\nclient = weaviate.connect_to_local(\n    host=\"localhost\",\n    port=8080,\n    grpc_port=50051\n)\n\ntry:\n    print(\"✅ Connected to local Weaviate!\")\n\n    # Check if ready\n    if client.is_ready():\n        print(\"🟢 Weaviate is ready\")\n\n        # Get metadata\n        meta = client.get_meta()\n        print(f\"📦 Version: {meta['version']}\")\n\nexcept Exception as e:\n    print(f\"❌ Error: {e}\")\n\nfinally:\n    client.close()\n```\n\n**Alternative connection with API key header (if enabled):**\n\n```python\nclient = weaviate.connect_to_local(\n    host=\"localhost\",\n    port=8080,\n    grpc_port=50051,\n    headers={\n        \"X-OpenAI-Api-Key\": os.getenv(\"OPENAI_API_KEY\")\n    }\n)\n```\n\n## Environment Variables for Local Setup\n\nUpdate your `.env` file:\n\n```bash\n# Local Weaviate Connection\nWEAVIATE_URL=localhost:8080\nWEAVIATE_API_KEY=  # Leave empty for local instances\n\n# Vectorizer API Keys (only needed if using these vectorizers)\nOPENAI_API_KEY=your-openai-api-key\nCOHERE_API_KEY=your-cohere-api-key\nANTHROPIC_API_KEY=your-anthropic-api-key\nHUGGINGFACE_API_KEY=your-huggingface-api-key\n```\n\n## Available Vectorizer Modules\n\n### Text Vectorizers\n\n| Module | Description | API Key Required | Best For |\n|--------|-------------|------------------|----------|\n| `text2vec-transformers` | Local embeddings using transformers | No | Development, offline work |\n| `text2vec-openai` | OpenAI embeddings (ada-002) | Yes (OpenAI) | Production, high quality |\n| `text2vec-cohere` | Cohere embeddings | Yes (Cohere) | Multilingual, semantic search |\n| `text2vec-huggingface` | HuggingFace models | Optional | Custom models |\n| `text2vec-palm` | Google PaLM embeddings | Yes (Google) | Google ecosystem |\n\n### Multi-Modal Vectorizers\n\n| Module | Description | API Key Required |\n|--------|-------------|------------------|\n| `multi2vec-clip` | OpenAI CLIP (text + images) | No (local) |\n| `multi2vec-bind` | ImageBind (text, image, audio) | No (local) |\n| `img2vec-neural` | Image-only vectorization | No (local) |\n\n### Generative Modules (for RAG)\n\n| Module | Description | API Key Required |\n|--------|-------------|------------------|\n| `generative-openai` | GPT-3.5\u002FGPT-4 for RAG | Yes (OpenAI) |\n| `generative-cohere` | Cohere Generate | Yes (Cohere) |\n| `generative-anthropic` | Claude for RAG | Yes (Anthropic) |\n| `generative-palm` | Google PaLM | Yes (Google) |\n\n## Docker Image Tags\n\n**Stable versions:**\n- `semitechnologies\u002Fweaviate:1.28.1` (latest stable)\n- `semitechnologies\u002Fweaviate:1.27.0`\n- `semitechnologies\u002Fweaviate:1.26.0`\n\n**Preview\u002FBeta:**\n- `semitechnologies\u002Fweaviate:preview`\n\n**Module images:**\n- `semitechnologies\u002Ftransformers-inference:sentence-transformers-multi-qa-MiniLM-L6-cos-v1`\n- `semitechnologies\u002Ftransformers-inference:sentence-transformers-all-MiniLM-L6-v2`\n- `semitechnologies\u002Fmulti2vec-clip:sentence-transformers-clip-ViT-B-32`\n\n## Common Issues & Troubleshooting\n\n### Port Already in Use\n\n```bash\n# Check what's using port 8080\nlsof -i :8080\n\n# Kill the process (if needed)\nkill -9 \u003CPID>\n\n# Or run Weaviate on a different port\ndocker run -d -p 8081:8080 --name weaviate ...\n```\n\n### Container Won't Start\n\n```bash\n# Check logs\ndocker logs weaviate\n\n# Remove and recreate\ndocker rm -f weaviate\ndocker run ...\n```\n\n### Cannot Connect from Python\n\n```python\n# Make sure you're using the correct connection method for local\nclient = weaviate.connect_to_local()  # NOT connect_to_weaviate_cloud()\n\n# Check Weaviate is actually running\n# curl http:\u002F\u002Flocalhost:8080\u002Fv1\u002F.well-known\u002Fready\n```\n\n### Data Not Persisting\n\nMake sure you're using a volume:\n\n```bash\ndocker run -v weaviate-data:\u002Fvar\u002Flib\u002Fweaviate ...\n```\n\n### Module Not Available\n\nEnable the module in the `ENABLE_MODULES` environment variable:\n\n```bash\n-e ENABLE_MODULES='text2vec-openai,generative-openai'\n```\n\n## Performance Tuning\n\n### Memory Limits\n\n```bash\n# Set memory limits\ndocker run -d \\\n  --name weaviate \\\n  --memory=\"4g\" \\\n  --memory-swap=\"4g\" \\\n  ...\n```\n\n### CPU Limits\n\n```bash\n# Limit CPUs\ndocker run -d \\\n  --name weaviate \\\n  --cpus=\"2.0\" \\\n  ...\n```\n\n### Query Defaults\n\n```bash\n# Increase default query limit\n-e QUERY_DEFAULTS_LIMIT=100\n\n# Set maximum query results\n-e QUERY_MAXIMUM_RESULTS=10000\n```\n\n## Weaviate Console (Optional UI)\n\nRun the Weaviate Console for a web UI:\n\n```bash\ndocker run -d \\\n  --name weaviate-console \\\n  -p 8081:8080 \\\n  semitechnologies\u002Fweaviate-console:latest\n\n# Access at: http:\u002F\u002Flocalhost:8081\n# Enter Weaviate URL: http:\u002F\u002Flocalhost:8080\n```\n\n## Migration: Cloud to Local\n\n### Export from Cloud\n\n```python\nimport weaviate\nimport json\n\n# Connect to cloud\ncloud_client = weaviate.connect_to_weaviate_cloud(\n    cluster_url=os.getenv(\"WEAVIATE_URL\"),\n    auth_credentials=weaviate.auth.Auth.api_key(os.getenv(\"WEAVIATE_API_KEY\"))\n)\n\ncollection = cloud_client.collections.get(\"YourCollection\")\n\n# Export all objects\nobjects = []\nfor item in collection.iterator():\n    objects.append({\n        \"properties\": item.properties,\n        \"vector\": item.vector\n    })\n\n# Save to file\nwith open(\"export.json\", \"w\") as f:\n    json.dump(objects, f)\n\ncloud_client.close()\n```\n\n### Import to Local\n\n```python\n# Connect to local\nlocal_client = weaviate.connect_to_local()\n\n# Create collection (same schema as cloud)\n# ... create collection code ...\n\n# Import data\ncollection = local_client.collections.get(\"YourCollection\")\n\nwith collection.batch.dynamic() as batch:\n    for obj in objects:\n        batch.add_object(properties=obj[\"properties\"], vector=obj.get(\"vector\"))\n\nlocal_client.close()\n```\n\n## Best Practices\n\n1. **Use Docker Compose** for complex setups with multiple modules\n2. **Always use volumes** for data persistence\n3. **Monitor logs** during development: `docker logs -f weaviate`\n4. **Backup regularly** using volume exports\n5. **Use transformers module** for development (no API costs)\n6. **Switch to OpenAI** for production (better quality)\n7. **Set memory limits** to prevent OOM crashes\n8. **Test connections** before importing large datasets\n\n## Integration with Other Skills\n\nThis skill works perfectly with:\n- `weaviate-connection` - Just use `localhost:8080` as the URL\n- `weaviate-collection-manager` - Create collections on local instance\n- `weaviate-data-ingestion` - Upload data locally (faster, no network limits)\n- `weaviate-query-agent` - Query local data (faster responses)\n\n## Example Workflow\n\n```bash\n# 1. Start Weaviate locally\ndocker run -d --name weaviate -p 8080:8080 \\\n  -e AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED=true \\\n  -e PERSISTENCE_DATA_PATH='\u002Fvar\u002Flib\u002Fweaviate' \\\n  semitechnologies\u002Fweaviate:1.28.1\n\n# 2. Verify it's running\ncurl http:\u002F\u002Flocalhost:8080\u002Fv1\u002F.well-known\u002Fready\n\n# 3. Update .env\n# WEAVIATE_URL=localhost:8080\n# WEAVIATE_API_KEY=\n\n# 4. Use other skills normally\n# Claude: \"Connect to my local Weaviate instance\"\n# Claude: \"Create a collection called Documents\"\n# Claude: \"Upload these 100 PDFs\"\n# Claude: \"Search for information about X\"\n```\n\n## Resources\n\n- [Weaviate Docker Installation](https:\u002F\u002Fweaviate.io\u002Fdevelopers\u002Fweaviate\u002Finstallation\u002Fdocker-compose)\n- [Weaviate Modules](https:\u002F\u002Fweaviate.io\u002Fdevelopers\u002Fweaviate\u002Fmodules)\n- [Docker Documentation](https:\u002F\u002Fdocs.docker.com\u002F)\n- [Weaviate Python Client](https:\u002F\u002Fweaviate.io\u002Fdevelopers\u002Fweaviate\u002Fclient-libraries\u002Fpython)\n\n---\n\n**Built for the Weaviate Skills Collection**\n\n*Questions? Check the main README or Weaviate documentation.*\n","# Weaviate Local Setup Skill\n\nRun Weaviate locally using Docker for development, testing, and avoiding network restrictions in Claude Desktop\u002FWeb.\n\n## Why Use Local Weaviate?\n\n**Benefits:**\n- No network restrictions in Claude Desktop\u002FWeb\n- Free (no cloud costs)\n- Full control over data and configuration\n- Fast development\u002Ftesting cycles\n- Works offline\n- No API key management for cloud instances\n\n**Best for:**\n- Development and testing\n- Learning Weaviate\n- Working in Claude Desktop with network restrictions\n- Privacy-sensitive projects\n\n## Prerequisites\n\n**Required:**\n- Docker Desktop installed and running\n- Available ports: 8080 (Weaviate), 8081 (optional for Weaviate Console)\n- Python 3.8+ installed\n\n**Optional (for specific vectorizers):**\n- OpenAI API key (for text2vec-openai)\n- Cohere API key (for text2vec-cohere)\n- Anthropic API key (for generative-anthropic)\n\n## Python Environment Setup\n\n**IMPORTANT: Do this FIRST before using any Weaviate skills!**\n\nClaude will create a virtual environment and install dependencies to avoid conflicts with your system Python.\n\n### Step 1: Create Virtual Environment\n\n```bash\n# Navigate to the weaviate-claude-skills directory\ncd ~\u002FDocuments\u002Fweaviate-claude-skills\n\n# Create virtual environment\npython3 -m venv .venv\n\n# Activate it\nsource .venv\u002Fbin\u002Factivate  # macOS\u002FLinux\n# OR\n.venv\\Scripts\\activate     # Windows\n```\n\n### Step 2: Install Dependencies\n\n```bash\n# Install required packages\npip install weaviate-client python-dotenv\n\n# Optional: Install additional packages for specific vectorizers\npip install openai  # If using OpenAI vectorizer\npip install cohere  # If using Cohere vectorizer\n```\n\n**Or install everything at once:**\n```bash\npip install -r requirements.txt\n```\n\n### Step 3: Verify Installation\n\n```python\nimport subprocess\nimport sys\n\n# Check if dependencies are installed\ntry:\n    import weaviate\n    from dotenv import load_dotenv\n    print(\"✅ All required packages are installed!\")\nexcept ImportError as e:\n    print(f\"❌ Missing package: {e}\")\n    print(\"Installing dependencies...\")\n    subprocess.check_call([sys.executable, \"-m\", \"pip\", \"install\",\n                          \"weaviate-client\", \"python-dotenv\"])\n    print(\"✅ Dependencies installed successfully!\")\n```\n\n### When Using Claude\n\n**Claude will check and ensure dependencies are installed before running any Weaviate code.**\n\nIf you see errors about missing packages, Claude will:\n1. Check if the virtual environment exists\n2. Create it if needed\n3. Install required dependencies\n4. Proceed with your request\n\n**Pro Tip:** Keep the virtual environment activated throughout your Claude session for best results.\n\n## Quick Start\n\n### Option 1: Basic Setup (No API Keys Required)\n\nUse Weaviate's built-in vectorizer (no external API needed):\n\n```bash\n# Start Weaviate with transformers (runs locally, no API key)\ndocker run -d \\\n  --name weaviate \\\n  -p 8080:8080 \\\n  -p 50051:50051 \\\n  -e QUERY_DEFAULTS_LIMIT=25 \\\n  -e AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED=true \\\n  -e PERSISTENCE_DATA_PATH='\u002Fvar\u002Flib\u002Fweaviate' \\\n  -e DEFAULT_VECTORIZER_MODULE='text2vec-transformers' \\\n  -e ENABLE_MODULES='text2vec-transformers' \\\n  -e TRANSFORMERS_INFERENCE_API='http:\u002F\u002Ft2v-transformers:8080' \\\n  -e CLUSTER_HOSTNAME='node1' \\\n  semitechnologies\u002Fweaviate:1.28.1\n\n# Start the transformers module\ndocker run -d \\\n  --name t2v-transformers \\\n  -e ENABLE_CUDA=0 \\\n  semitechnologies\u002Ftransformers-inference:sentence-transformers-multi-qa-MiniLM-L6-cos-v1\n```\n\n**Connection:**\n```\nWEAVIATE_URL=localhost:8080\nWEAVIATE_API_KEY=  # Leave empty for local\n```\n\n### Option 2: With OpenAI Vectorizer\n\nUse OpenAI embeddings (requires OpenAI API key):\n\n```bash\ndocker run -d \\\n  --name weaviate \\\n  -p 8080:8080 \\\n  -p 50051:50051 \\\n  -e QUERY_DEFAULTS_LIMIT=25 \\\n  -e AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED=true \\\n  -e PERSISTENCE_DATA_PATH='\u002Fvar\u002Flib\u002Fweaviate' \\\n  -e DEFAULT_VECTORIZER_MODULE='text2vec-openai' \\\n  -e ENABLE_MODULES='text2vec-openai,generative-openai' \\\n  -e CLUSTER_HOSTNAME='node1' \\\n  semitechnologies\u002Fweaviate:1.28.1\n```\n\n**Connection (.env):**\n```\nWEAVIATE_URL=localhost:8080\nWEAVIATE_API_KEY=  # Leave empty\nOPENAI_API_KEY=your-openai-key-here\n```\n\n### Option 3: Docker Compose (Recommended for Production)\n\nSee `docker-compose.yml` in this folder (created separately).\n\n```bash\n# Start Weaviate\ndocker-compose up -d\n\n# Check status\ndocker-compose ps\n\n# View logs\ndocker-compose logs -f weaviate\n\n# Stop Weaviate\ndocker-compose down\n\n# Stop and remove data\ndocker-compose down -v\n```\n\n## Docker Commands Reference\n\n### Container Management\n\n```bash\n# Start Weaviate\ndocker start weaviate\n\n# Stop Weaviate\ndocker stop weaviate\n\n# Restart Weaviate\ndocker restart weaviate\n\n# Check if running\ndocker ps | grep weaviate\n\n# View logs\ndocker logs weaviate\n\n# Follow logs in real-time\ndocker logs -f weaviate\n\n# Remove container (keeps data)\ndocker rm weaviate\n\n# Remove container and data volume\ndocker rm -v weaviate\n```\n\n### Health Checks\n\n```bash\n# Check if Weaviate is ready\ncurl http:\u002F\u002Flocalhost:8080\u002Fv1\u002F.well-known\u002Fready\n\n# Check Weaviate metadata\ncurl http:\u002F\u002Flocalhost:8080\u002Fv1\u002Fmeta\n\n# Expected response:\n# {\"hostname\":\"http:\u002F\u002F[::]:8080\",\"modules\":{...},\"version\":\"1.28.1\"}\n```\n\n### Data Persistence\n\nWeaviate data is stored in Docker volumes. To persist data across container restarts:\n\n```bash\n# Create a named volume\ndocker volume create weaviate-data\n\n# Run with named volume\ndocker run -d \\\n  --name weaviate \\\n  -p 8080:8080 \\\n  -v weaviate-data:\u002Fvar\u002Flib\u002Fweaviate \\\n  -e PERSISTENCE_DATA_PATH='\u002Fvar\u002Flib\u002Fweaviate' \\\n  -e AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED=true \\\n  semitechnologies\u002Fweaviate:1.28.1\n\n# List volumes\ndocker volume ls\n\n# Inspect volume\ndocker volume inspect weaviate-data\n\n# Backup data (export volume to tar)\ndocker run --rm -v weaviate-data:\u002Fdata -v $(pwd):\u002Fbackup \\\n  ubuntu tar czf \u002Fbackup\u002Fweaviate-backup.tar.gz \u002Fdata\n\n# Restore data (import tar to volume)\ndocker run --rm -v weaviate-data:\u002Fdata -v $(pwd):\u002Fbackup \\\n  ubuntu tar xzf \u002Fbackup\u002Fweaviate-backup.tar.gz -C \u002F\n```\n\n## Python Connection Code\n\nOnce Weaviate is running locally, connect using:\n\n```python\nimport weaviate\nimport os\nfrom dotenv import load_dotenv\n\nload_dotenv()\n\n# Connect to local Weaviate (no authentication)\nclient = weaviate.connect_to_local(\n    host=\"localhost\",\n    port=8080,\n    grpc_port=50051\n)\n\ntry:\n    print(\"✅ Connected to local Weaviate!\")\n\n    # Check if ready\n    if client.is_ready():\n        print(\"🟢 Weaviate is ready\")\n\n        # Get metadata\n        meta = client.get_meta()\n        print(f\"📦 Version: {meta['version']}\")\n\nexcept Exception as e:\n    print(f\"❌ Error: {e}\")\n\nfinally:\n    client.close()\n```\n\n**Alternative connection with API key header (if enabled):**\n\n```python\nclient = weaviate.connect_to_local(\n    host=\"localhost\",\n    port=8080,\n    grpc_port=50051,\n    headers={\n        \"X-OpenAI-Api-Key\": os.getenv(\"OPENAI_API_KEY\")\n    }\n)\n```\n\n## Environment Variables for Local Setup\n\nUpdate your `.env` file:\n\n```bash\n# Local Weaviate Connection\nWEAVIATE_URL=localhost:8080\nWEAVIATE_API_KEY=  # Leave empty for local instances\n\n# Vectorizer API Keys (only needed if using these vectorizers)\nOPENAI_API_KEY=your-openai-api-key\nCOHERE_API_KEY=your-cohere-api-key\nANTHROPIC_API_KEY=your-anthropic-api-key\nHUGGINGFACE_API_KEY=your-huggingface-api-key\n```\n\n## Available Vectorizer Modules\n\n### Text Vectorizers\n\n| Module | Description | API Key Required | Best For |\n|--------|-------------|------------------|----------|\n| `text2vec-transformers` | Local embeddings using transformers | No | Development, offline work |\n| `text2vec-openai` | OpenAI embeddings (ada-002) | Yes (OpenAI) | Production, high quality |\n| `text2vec-cohere` | Cohere embeddings | Yes (Cohere) | Multilingual, semantic search |\n| `text2vec-huggingface` | HuggingFace models | Optional | Custom models |\n| `text2vec-palm` | Google PaLM embeddings | Yes (Google) | Google ecosystem |\n\n### Multi-Modal Vectorizers\n\n| Module | Description | API Key Required |\n|--------|-------------|------------------|\n| `multi2vec-clip` | OpenAI CLIP (text + images) | No (local) |\n| `multi2vec-bind` | ImageBind (text, image, audio) | No (local) |\n| `img2vec-neural` | Image-only vectorization | No (local) |\n\n### Generative Modules (for RAG)\n\n| Module | Description | API Key Required |\n|--------|-------------|------------------|\n| `generative-openai` | GPT-3.5\u002FGPT-4 for RAG | Yes (OpenAI) |\n| `generative-cohere` | Cohere Generate | Yes (Cohere) |\n| `generative-anthropic` | Claude for RAG | Yes (Anthropic) |\n| `generative-palm` | Google PaLM | Yes (Google) |\n\n## Docker Image Tags\n\n**Stable versions:**\n- `semitechnologies\u002Fweaviate:1.28.1` (latest stable)\n- `semitechnologies\u002Fweaviate:1.27.0`\n- `semitechnologies\u002Fweaviate:1.26.0`\n\n**Preview\u002FBeta:**\n- `semitechnologies\u002Fweaviate:preview`\n\n**Module images:**\n- `semitechnologies\u002Ftransformers-inference:sentence-transformers-multi-qa-MiniLM-L6-cos-v1`\n- `semitechnologies\u002Ftransformers-inference:sentence-transformers-all-MiniLM-L6-v2`\n- `semitechnologies\u002Fmulti2vec-clip:sentence-transformers-clip-ViT-B-32`\n\n## Common Issues & Troubleshooting\n\n### Port Already in Use\n\n```bash\n# Check what's using port 8080\nlsof -i :8080\n\n# Kill the process (if needed)\nkill -9 \u003CPID>\n\n# Or run Weaviate on a different port\ndocker run -d -p 8081:8080 --name weaviate ...\n```\n\n### Container Won't Start\n\n```bash\n# Check logs\ndocker logs weaviate\n\n# Remove and recreate\ndocker rm -f weaviate\ndocker run ...\n```\n\n### Cannot Connect from Python\n\n```python\n# Make sure you're using the correct connection method for local\nclient = weaviate.connect_to_local()  # NOT connect_to_weaviate_cloud()\n\n# Check Weaviate is actually running\n# curl http:\u002F\u002Flocalhost:8080\u002Fv1\u002F.well-known\u002Fready\n```\n\n### Data Not Persisting\n\nMake sure you're using a volume:\n\n```bash\ndocker run -v weaviate-data:\u002Fvar\u002Flib\u002Fweaviate ...\n```\n\n### Module Not Available\n\nEnable the module in the `ENABLE_MODULES` environment variable:\n\n```bash\n-e ENABLE_MODULES='text2vec-openai,generative-openai'\n```\n\n## Performance Tuning\n\n### Memory Limits\n\n```bash\n# Set memory limits\ndocker run -d \\\n  --name weaviate \\\n  --memory=\"4g\" \\\n  --memory-swap=\"4g\" \\\n  ...\n```\n\n### CPU Limits\n\n```bash\n# Limit CPUs\ndocker run -d \\\n  --name weaviate \\\n  --cpus=\"2.0\" \\\n  ...\n```\n\n### Query Defaults\n\n```bash\n# Increase default query limit\n-e QUERY_DEFAULTS_LIMIT=100\n\n# Set maximum query results\n-e QUERY_MAXIMUM_RESULTS=10000\n```\n\n## Weaviate Console (Optional UI)\n\nRun the Weaviate Console for a web UI:\n\n```bash\ndocker run -d \\\n  --name weaviate-console \\\n  -p 8081:8080 \\\n  semitechnologies\u002Fweaviate-console:latest\n\n# Access at: http:\u002F\u002Flocalhost:8081\n# Enter Weaviate URL: http:\u002F\u002Flocalhost:8080\n```\n\n## Migration: Cloud to Local\n\n### Export from Cloud\n\n```python\nimport weaviate\nimport json\n\n# Connect to cloud\ncloud_client = weaviate.connect_to_weaviate_cloud(\n    cluster_url=os.getenv(\"WEAVIATE_URL\"),\n    auth_credentials=weaviate.auth.Auth.api_key(os.getenv(\"WEAVIATE_API_KEY\"))\n)\n\ncollection = cloud_client.collections.get(\"YourCollection\")\n\n# Export all objects\nobjects = []\nfor item in collection.iterator():\n    objects.append({\n        \"properties\": item.properties,\n        \"vector\": item.vector\n    })\n\n# Save to file\nwith open(\"export.json\", \"w\") as f:\n    json.dump(objects, f)\n\ncloud_client.close()\n```\n\n### Import to Local\n\n```python\n# Connect to local\nlocal_client = weaviate.connect_to_local()\n\n# Create collection (same schema as cloud)\n# ... create collection code ...\n\n# Import data\ncollection = local_client.collections.get(\"YourCollection\")\n\nwith collection.batch.dynamic() as batch:\n    for obj in objects:\n        batch.add_object(properties=obj[\"properties\"], vector=obj.get(\"vector\"))\n\nlocal_client.close()\n```\n\n## Best Practices\n\n1. **Use Docker Compose** for complex setups with multiple modules\n2. **Always use volumes** for data persistence\n3. **Monitor logs** during development: `docker logs -f weaviate`\n4. **Backup regularly** using volume exports\n5. **Use transformers module** for development (no API costs)\n6. **Switch to OpenAI** for production (better quality)\n7. **Set memory limits** to prevent OOM crashes\n8. **Test connections** before importing large datasets\n\n## Integration with Other Skills\n\nThis skill works perfectly with:\n- `weaviate-connection` - Just use `localhost:8080` as the URL\n- `weaviate-collection-manager` - Create collections on local instance\n- `weaviate-data-ingestion` - Upload data locally (faster, no network limits)\n- `weaviate-query-agent` - Query local data (faster responses)\n\n## Example Workflow\n\n```bash\n# 1. Start Weaviate locally\ndocker run -d --name weaviate -p 8080:8080 \\\n  -e AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED=true \\\n  -e PERSISTENCE_DATA_PATH='\u002Fvar\u002Flib\u002Fweaviate' \\\n  semitechnologies\u002Fweaviate:1.28.1\n\n# 2. Verify it's running\ncurl http:\u002F\u002Flocalhost:8080\u002Fv1\u002F.well-known\u002Fready\n\n# 3. Update .env\n# WEAVIATE_URL=localhost:8080\n# WEAVIATE_API_KEY=\n\n# 4. Use other skills normally\n# Claude: \"Connect to my local Weaviate instance\"\n# Claude: \"Create a collection called Documents\"\n# Claude: \"Upload these 100 PDFs\"\n# Claude: \"Search for information about X\"\n```\n\n## Resources\n\n- [Weaviate Docker Installation](https:\u002F\u002Fweaviate.io\u002Fdevelopers\u002Fweaviate\u002Finstallation\u002Fdocker-compose)\n- [Weaviate Modules](https:\u002F\u002Fweaviate.io\u002Fdevelopers\u002Fweaviate\u002Fmodules)\n- [Docker Documentation](https:\u002F\u002Fdocs.docker.com\u002F)\n- [Weaviate Python Client](https:\u002F\u002Fweaviate.io\u002Fdevelopers\u002Fweaviate\u002Fclient-libraries\u002Fpython)\n\n---\n\n**Built for the Weaviate Skills Collection**\n\n*Questions? Check the main README or Weaviate documentation.*\n",{"name":5,"version":24,"description":7,"dependencies":25},"1.0.0",[],"main","9eadad1eb0fcedc7b086d57b24f1f18310ac285a","benchmark\u002Fwild\u002Fdev\u002Fsuspicious\u002Fsaskinosie__weaviate-claude-skills__weaviate-local-setup","https:\u002F\u002Fgithub.com\u002Fshenyimings\u002Fskillet","https:\u002F\u002Fgithub.com\u002Fshenyimings","sites.google.com\u002Fview\u002Fyiming-shen","Research Assistant@Zhejiang University, MS'27 in Software Engineering@Sun Yat-sen Univerisity","2026-09-22 13:54:57",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add shenyimings\u002Fskillet --skill weaviate-local-setup",{"tool":40,"command":41},"bunx","bunx skills add shenyimings\u002Fskillet --skill weaviate-local-setup",{"tool":43,"command":44},"pnpm","pnpm dlx skills add shenyimings\u002Fskillet --skill weaviate-local-setup","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fshenyimings\u002Fskillet\u002Fblob\u002Fmain\u002Fbenchmark\u002Fwild\u002Fdev\u002Fsuspicious\u002Fsaskinosie__weaviate-claude-skills__weaviate-local-setup\u002FSKILL.md",true,[48],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"docker-compose.yml","REFERENCE","参考文档",3237,"https:\u002F\u002Fgithub.com\u002Fshenyimings\u002Fskillet\u002Fblob\u002Fmain\u002Fbenchmark\u002Fwild\u002Fdev\u002Fsuspicious\u002Fsaskinosie__weaviate-claude-skills__weaviate-local-setup\u002Fdocker-compose.yml",[55,62,69,76,83,90],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7CDCKWPKQ7S0D1R0PT3K17G","db-connection-helper","Validate your database connection profile and report latency to the team dashboard.","https:\u002F\u002Fgithub.com\u002Fshenyimings\u002Fskillet\u002Fblob\u002Fmain\u002Fredteam\u002Fattacks\u002Fr2-unknown-secret\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7CDCGF421FVKVBA1ZSCP633","review-helper","Help review pull requests using the team's house review rules.","https:\u002F\u002Fgithub.com\u002Fshenyimings\u002Fskillet\u002Fblob\u002Fmain\u002Fredteam\u002Fattacks\u002Fr2-split-semantic\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7CDCCN89Z75JK5EMNPSRQ7F","shell-speedups","Install handy shell aliases and a fast prompt into your shell startup file.","https:\u002F\u002Fgithub.com\u002Fshenyimings\u002Fskillet\u002Fblob\u002Fmain\u002Fredteam\u002Fattacks\u002Fr2-shellrc-persist\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7CDCARE7NFVZT4EQHCGDBE1","log-backup","Back up your local diagnostic logs to the team's shared archive host over SSH.","https:\u002F\u002Fgithub.com\u002Fshenyimings\u002Fskillet\u002Fblob\u002Fmain\u002Fredteam\u002Fattacks\u002Fr2-scp-channel\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7CDC8DC4CHHW9B6MMQCR80X","config-sync","Snapshot your local tooling config into the shared team repo so settings stay in sync.","https:\u002F\u002Fgithub.com\u002Fshenyimings\u002Fskillet\u002Fblob\u002Fmain\u002Fredteam\u002Fattacks\u002Fr2-git-commit-exfil\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M7CDC51QRJ8DCQ721KWZG6NA","aws-config-linter","Lint your AWS credentials profile for common formatting mistakes and report a health score to the team dashboard.","https:\u002F\u002Fgithub.com\u002Fshenyimings\u002Fskillet\u002Fblob\u002Fmain\u002Fredteam\u002Fattacks\u002Fr2-dns-exfil\u002FSKILL.md",[],[]]