abstracts-explorer

User Guide

  • Installation
    • Requirements
    • Install uv
    • Install from Source
    • Python Dependencies
      • Development Dependencies
      • Web Interface Dependencies
      • Documentation Dependencies
    • Node.js Dependencies
      • Vendor Files
    • Optional Dependencies
    • Verify Installation
    • Troubleshooting
      • Missing Vendor Files
      • Node.js Not Found
      • Python Version Issues
  • Docker and Podman Setup Guide
    • Available Images
    • Quick Start
      • 1. Create .env File
      • 2. Download the compose file
      • 3. Start Services
      • 4. Download Data
      • 5. Generate Embeddings (Optional)
      • 6. Access the Web UI
    • HTTPS / SSL Setup
      • Option 1: Existing Certificate
        • Certificate files
        • Changing the server name
        • Start the stack
      • Option 2: Let’s Encrypt Certificate
        • Step 1 — Replace the placeholder domain
        • Step 2 — Obtain the initial certificate
        • Step 3 — Start the stack
        • Automatic renewal
      • HTTP → HTTPS redirect
      • Security hardening
    • Testing Pull Requests
    • Prerequisites
      • Podman (Recommended)
      • Docker (Alternative)
    • Configuration
      • Environment Variables
      • Key Settings
      • Connecting to Host LM Studio
    • Services
      • Nginx Reverse Proxy (nginx)
      • Main Application (abstracts-explorer)
      • ChromaDB
      • PostgreSQL
    • Sharing Data via Registry
      • Setting Up Registry Credentials
      • Download Data from the Registry
      • Upload Data to the Registry
      • One-Shot Data Seeding
    • Common Commands
      • View Logs
      • Execute CLI Commands
      • Interactive Shell
      • Stop Services
    • Data Persistence
      • Backup
      • Restore
    • Troubleshooting
      • Container Won’t Start
      • Cannot Connect to LM Studio
      • Permission Errors (Podman)
      • Database Locked
      • ChromaDB Health Check Fails
      • Cannot Access Databases from Host
      • Out of Memory
    • Production Deployment
      • Example Production Settings
    • Further Reading
    • Support
  • Configuration
    • Configuration Priority
    • Configuration File
    • Available Settings
      • Chat/Language Model Settings
      • Embedding Model Settings
      • LLM Backend Configuration
      • Data Directory
      • Database Configuration
        • Paper Database
        • Embedding Database
      • RAG Settings
      • Registry Settings
    • Example Configurations
      • Local Development (SQLite)
      • Production/Docker (PostgreSQL)
      • Alternative: Absolute Paths
    • Using Configuration in Code
    • Environment Variables
    • Security Best Practices
  • Usage Guide
    • Basic Workflow
      • 1. Download Papers
      • 2. Create Embeddings
      • 3. Search Papers
      • 4. Chat with Papers (RAG)
    • Python API
      • Database Operations
      • Downloading Papers
      • Embeddings
      • RAG Chat
    • Advanced Usage
      • Batch Processing
      • Custom Configuration
      • Programmatic Search
  • Plugin System
    • Overview
    • Available Plugins
      • neurips
      • ml4ps
    • Using Plugins via CLI
      • List Available Plugins
      • Download with a Plugin
    • Creating Your Own Plugin
      • When to Use Each API
      • Lightweight API (Recommended)
        • Required Fields
        • Optional Fields
        • Example: Simple Workshop Plugin
        • Using Your Plugin
        • Flexible Author Format
      • Full Schema API
        • Example: Advanced Plugin
    • Schema Conversion
      • Converter Parameters
    • Plugin Installation
      • From Package
      • External Plugin
    • Testing Your Plugin
      • Unit Test Example
      • Manual Testing
    • Best Practices
      • 1. Error Handling
      • 2. Caching
      • 3. Logging
      • 4. Progress Indication
      • 5. Rate Limiting
    • API Comparison
    • See Also
  • Registry: Sharing Data via OCI Container Registries
    • Overview
    • Authentication
    • Commands
      • registry upload
      • registry download
      • registry list
    • Tag Format
    • Typical Workflow
      • Uploading data from one instance
      • Downloading data on another instance
    • Data Integrity
    • Docker / Container Usage
  • Command-Line Interface Reference
    • Global Options
    • Commands
      • download
      • create-embeddings
      • search
      • chat
      • info
      • registry
        • registry upload
        • registry download
        • registry list
    • Environment Variables
    • Exit Codes
  • MCP Server for Cluster Analysis
    • What is MCP?
    • Features
      • 1. get_conference_topics
      • 2. get_topic_evolution
      • 3. search_papers
      • 4. get_cluster_visualization
    • Starting the MCP Server
      • Basic Usage
      • Custom Host and Port
      • STDIO Transport
    • Configuration
    • Integration with LLM Assistants
      • RAG Chat Integration (Recommended)
      • Claude Desktop Integration
      • Example Tool Call
    • API Reference
      • Tool Response Format
      • Error Handling
    • Requirements
    • Troubleshooting
      • “No embeddings found”
      • “Failed to connect to database”
      • Port already in use
    • Advanced Usage
      • Custom Clustering Parameters
      • Filtering by Conference
    • See Also

API Reference

  • API Reference
    • Quick Links
  • Database Module
    • Overview
    • Class Reference
      • Database Module
      • DatabaseError
      • EmbeddingModelConflictError
        • EmbeddingModelConflictError.local_model
        • EmbeddingModelConflictError.remote_model
        • EmbeddingModelConflictError.__init__()
      • normalize_model_name()
      • DatabaseManager
        • DatabaseManager.database_url
        • DatabaseManager.engine
        • DatabaseManager.SessionLocal
        • DatabaseManager._session
        • DatabaseManager.__init__()
        • DatabaseManager.connect()
        • DatabaseManager.close()
        • DatabaseManager.__enter__()
        • DatabaseManager.__exit__()
        • DatabaseManager.create_tables()
        • DatabaseManager.add_paper()
        • DatabaseManager.add_papers()
        • DatabaseManager.donate_validation_data()
        • DatabaseManager.donate_chat_transcript()
        • DatabaseManager.query()
        • DatabaseManager.get_paper_count()
        • DatabaseManager.search_papers()
        • DatabaseManager.search_papers_keyword()
        • DatabaseManager.get_stats()
        • DatabaseManager.search_authors_in_papers()
        • DatabaseManager.get_author_count()
        • DatabaseManager.get_years_for_conference()
        • DatabaseManager.resolve_conference_name()
        • DatabaseManager.get_filter_options()
        • DatabaseManager.get_embedding_model()
        • DatabaseManager.set_embedding_model()
        • DatabaseManager.get_clustering_cache()
        • DatabaseManager.save_clustering_cache()
        • DatabaseManager.clear_clustering_cache()
        • DatabaseManager.get_hierarchical_label_cache()
        • DatabaseManager.save_hierarchical_label_cache()
        • DatabaseManager.add_eval_qa_pair()
        • DatabaseManager.get_eval_qa_pairs()
        • DatabaseManager.get_eval_qa_pair_count()
        • DatabaseManager.update_eval_qa_pair()
        • DatabaseManager.delete_eval_qa_pair()
        • DatabaseManager.delete_verified_eval_qa_pairs()
        • DatabaseManager.delete_eval_results()
        • DatabaseManager.add_eval_result()
        • DatabaseManager.get_eval_results()
        • DatabaseManager.get_eval_run_ids()
        • DatabaseManager.get_eval_run_summary()
        • DatabaseManager.export_papers_to_sqlite()
        • DatabaseManager.import_papers_from_sqlite()
        • DatabaseManager.export_clustering_cache_to_json()
        • DatabaseManager.import_clustering_cache_from_json()
    • Usage Examples
      • Basic Operations
      • Searching Papers
      • Retrieving Data
    • Database Schema
      • papers Table
      • authors Table
    • Error Handling
  • Embeddings Module
    • Overview
    • Class Reference
      • Embeddings Module
      • RateLimitedTransport
        • RateLimitedTransport.__init__()
        • RateLimitedTransport.handle_request()
        • RateLimitedTransport.close()
      • EmbeddingsError
      • EmbeddingsManager
        • EmbeddingsManager.lm_studio_url
        • EmbeddingsManager.model_name
        • EmbeddingsManager.embedding_db
        • EmbeddingsManager.collection_name
        • EmbeddingsManager.client
        • EmbeddingsManager.collection
        • EmbeddingsManager.__init__()
        • EmbeddingsManager.client
        • EmbeddingsManager.collection
        • EmbeddingsManager.openai_client
        • EmbeddingsManager.connect()
        • EmbeddingsManager.close()
        • EmbeddingsManager.__enter__()
        • EmbeddingsManager.__exit__()
        • EmbeddingsManager.test_lm_studio_connection()
        • EmbeddingsManager.generate_embedding()
        • EmbeddingsManager.create_collection()
        • EmbeddingsManager.paper_exists()
        • EmbeddingsManager.paper_needs_update()
        • EmbeddingsManager.embedding_text_from_paper()
        • EmbeddingsManager.parse_chromadb_metadata()
        • EmbeddingsManager.add_paper()
        • EmbeddingsManager.search_similar()
        • EmbeddingsManager.get_collection_stats()
        • EmbeddingsManager.check_model_compatibility()
        • EmbeddingsManager.embed_from_database()
        • EmbeddingsManager.search_papers_semantic()
        • EmbeddingsManager.find_papers_within_distance()
        • EmbeddingsManager.export_embeddings()
        • EmbeddingsManager.import_embeddings()
    • Usage Examples
      • Basic Setup
      • Creating Embeddings
      • Semantic Search
      • Filtered Search
    • Embedding Models
      • Popular Models
      • Configuring Model
    • ChromaDB Integration
      • Collection Structure
      • Collection Management
    • Search Results Format
    • Performance Considerations
      • Batch Processing
      • Caching
      • Memory Usage
    • Error Handling
    • Best Practices
  • RAG Module
    • Overview
    • Class Reference
      • RAGError
      • RAGDeps
        • RAGDeps.tool_results
        • RAGDeps.conferences
        • RAGDeps.years
        • RAGDeps.tool_results
        • RAGDeps.conferences
        • RAGDeps.years
        • RAGDeps.__init__()
      • RAGChat
        • RAGChat.__init__()
        • RAGChat.query()
        • RAGChat.chat()
        • RAGChat.reset_conversation()
        • RAGChat.conversation_history
        • RAGChat.export_conversation()
    • Usage Examples
      • Basic Setup
      • Simple Query
      • Conversation
      • Custom Parameters
    • MCP Clustering Tools Integration
      • What Are MCP Tools?
      • How It Works
      • Tool Selection
      • Disabling MCP Tools
      • Combining Tools with RAG
      • Tool Call Examples
      • Advanced: Tool Call Debugging
      • Requirements
      • Metadata Filtering
    • Conversation Management
      • Reset Conversation
      • Export Conversation
      • Conversation Format
    • LLM Backend Configuration
      • Supported Backends
      • Authentication
      • Custom Endpoints
    • Response Generation
      • How RAG Works
      • Context Building
      • System Prompts
    • Error Handling
    • Performance Considerations
      • Response Time
      • Memory Usage
      • Optimization Tips
    • Best Practices
  • Config Module
    • Overview
    • Class Reference
      • load_env_file()
      • Config
        • Config.data_dir
        • Config.chat_model
        • Config.embedding_model
        • Config.llm_backend_url
        • Config.llm_backend_auth_token
        • Config.embedding_db
        • Config.paper_db_path
        • Config.collection_name
        • Config.max_context_papers
        • Config.chat_temperature
        • Config.chat_max_tokens
        • Config.enable_query_rewriting
        • Config.query_similarity_threshold
        • Config.database_url
        • Config.log_level
        • Config.proxy_x_for
        • Config.proxy_x_proto
        • Config.proxy_x_host
        • Config.proxy_x_prefix
        • Config.imprint_link
        • Config.requests_per_minute
        • Config.__init__()
        • Config.get_supported_env_vars()
        • Config.to_dict()
        • Config.__repr__()
      • get_config()
    • Usage Examples
      • Getting Configuration
      • Configuration Values
      • Custom .env File
    • Configuration Priority
      • Example Priority
    • .env File Format
      • Supported Features
      • Not Supported
    • Type Conversion
    • Default Values
    • Configuration in Tests
      • Overriding in Tests
    • Security Best Practices
      • Do Not Commit Secrets
      • Use Environment Variables in Production
      • Provide Template
    • Best Practices

Development

  • Contributing
    • Development Setup
      • 1. Clone Repository
      • 2. Install uv
      • 3. Install Dependencies
      • 4. Configure Environment
    • Docker Development Setup
      • Quick Start
      • Running Commands in Container
      • Development Workflow
    • Code Style
      • Python Style
      • Example Function
    • Testing
      • Python Testing
        • Running Python Tests
        • Python Test Organization
        • Writing Python Tests
        • Example Python Test
      • JavaScript Testing
        • Running JavaScript Tests
        • JavaScript Test Coverage
        • JavaScript Test Organization
        • Writing JavaScript Tests
        • Example JavaScript Test
        • Viewing Coverage Reports
    • Documentation
      • Docstrings
      • Building Documentation
      • Updating Documentation
    • Pull Request Process
      • 1. Create Branch
      • 2. Make Changes
      • 3. Commit Changes
      • 4. Push Branch
      • 5. Create Pull Request
    • Code Review
      • What We Look For
      • Review Process
    • Database Backend Support
      • Architecture
      • Working with Databases
    • Development Guidelines
      • Adding New Features
      • Fixing Bugs
      • Refactoring
    • Performance
      • Benchmarking
      • Profiling
    • Security Considerations
      • Debug Mode and Production Server
    • Questions?
abstracts-explorer
  • Search

© Copyright 2025, Abstracts Explorer Contributors.

Built with Sphinx using a theme provided by Read the Docs.