khoj vs vectra

Indexes user documents (markdown, PDFs, web pages) into PostgreSQL with vector embeddings, enabling semantic search via cosine similarity matching. Uses a content processing pipeline that extracts, chunks, and embeds documents through configurable embedding models, then retrieves contextually relevant passages to augment chat responses. The search engine supports multiple content sources (local files, web URLs, Obsidian vaults) with unified indexing through database adapters.

Unique: Combines multi-source content indexing (local files, web URLs, Obsidian vaults) with PostgreSQL vector search and configurable embedding models, allowing users to maintain a unified searchable knowledge base across heterogeneous document sources without cloud dependency. Uses content processing pipeline with pluggable extractors and chunking strategies.

vs alternatives: Offers self-hosted semantic search with multi-source indexing and local embedding support, whereas Pinecone/Weaviate require cloud infrastructure and don't natively integrate with Obsidian/local file systems.

Routes chat requests through a provider-agnostic conversation pipeline that supports OpenAI (GPT), Anthropic (Claude), Google Gemini, and local LLMs (Llama, Qwen, Mistral via Ollama/LlamaCPP). The chat processor retrieves relevant context from the semantic search index, constructs a system prompt with retrieved passages, and streams responses back to clients. Implements conversation history management via Django ORM with per-user conversation threads and message persistence.

Unique: Implements provider-agnostic chat routing through a unified conversation processor that abstracts OpenAI, Anthropic, Google Gemini, and local LLM APIs, allowing seamless provider switching without application changes. Integrates semantic search context augmentation directly into the chat pipeline via system prompt injection with retrieved passages.

vs alternatives: Supports both cloud and local LLMs in a single system with automatic context augmentation from personal documents, whereas LangChain requires explicit chain composition and most chat UIs lock users into single providers.

Provides an Obsidian plugin that indexes the user's vault into Khoj's knowledge base and enables semantic search within Obsidian. The plugin watches for file changes and incrementally updates the index, supporting live synchronization of new notes. Implements bidirectional integration: users can search their vault from Khoj chat, and Khoj can suggest related notes from the vault. The plugin uses Obsidian's API for file access and the Khoj backend API for indexing and search.

Unique: Integrates Obsidian vaults directly into Khoj's knowledge base with live file watching and incremental indexing, enabling semantic search of vault notes from both Obsidian and Khoj interfaces. Uses Obsidian's native API for file access and change detection.

vs alternatives: Provides native Obsidian integration with live sync and bidirectional search, whereas most AI tools require manual vault exports or don't support Obsidian at all.

Provides an Emacs plugin that enables inline chat and search within Emacs buffers. Users can select text, ask Khoj questions about it, and receive responses inline. The plugin supports semantic search of indexed documents and integrates with Emacs' completion and buffer management systems. Implements streaming response rendering in Emacs buffers with syntax highlighting for code blocks.

Unique: Integrates Khoj chat and search directly into Emacs buffers with streaming response rendering and syntax highlighting, enabling AI interaction without leaving the editor. Uses Emacs' native buffer and completion APIs for seamless integration.

vs alternatives: Provides native Emacs integration with inline chat and streaming responses, whereas most AI tools are web-only or require external windows.

Provides Docker and Docker Compose configurations for self-hosted deployment of the full Khoj stack (backend, PostgreSQL, frontend). Includes environment-based configuration management through .env files and Django settings, supporting customization of LLM providers, embedding models, search engines, and other services. The deployment supports both development (docker-compose.yml) and production (prod.Dockerfile) configurations with Gunicorn WSGI server for production.

Unique: Provides complete Docker-based self-hosted deployment with environment-based configuration management supporting customization of LLM providers, embedding models, and external services. Includes both development and production configurations with Gunicorn WSGI server.

vs alternatives: Offers full self-hosted deployment with Docker support and environment-based configuration, whereas many AI tools are cloud-only or require complex manual setup.

Implements a content processing pipeline with pluggable extractors for different file types (PDF, markdown, HTML, plain text, Obsidian). Each extractor converts the source format to normalized text, which is then chunked and embedded. The pipeline supports custom extractors through a plugin interface, allowing users to add support for new file types. Chunking strategies are configurable (fixed size, semantic, sliding window) with metadata preservation (source, timestamp, section).

Unique: Implements content processing through pluggable extractors with configurable chunking strategies and metadata preservation, supporting multiple file types (PDF, markdown, HTML, Obsidian) through a unified pipeline. Allows custom extractors via plugin interface without modifying core.

vs alternatives: Provides pluggable content extraction with metadata preservation and configurable chunking, whereas most RAG systems use fixed extraction logic and don't support custom extractors.

Implements streaming response delivery through both HTTP Server-Sent Events (SSE) and WebSocket protocols, enabling real-time response rendering on clients. The streaming processor chunks LLM responses and sends them incrementally, reducing perceived latency and enabling progressive rendering. Supports streaming for chat responses, search results, and agent execution logs. Clients can subscribe to response streams and render content as it arrives.

Unique: Implements dual streaming protocols (SSE and WebSocket) with chunked response delivery and progressive rendering support, enabling real-time response visualization and agent execution log streaming. Integrates streaming directly into the chat and agent pipelines.

vs alternatives: Provides both SSE and WebSocket streaming with agent execution log support, whereas most chat APIs only support SSE and don't stream agent intermediate steps.

Implements an agent system that decomposes user requests into subtasks, selects appropriate tools (web search, code execution, image generation, MCP servers), and executes them in sequence with result aggregation. The agent uses the LLM to reason about tool selection via function-calling APIs (OpenAI, Anthropic native support) or prompt-based tool selection for other providers. Tool execution is sandboxed through subprocess isolation for code execution and API-based execution for external tools, with results fed back into the agent loop for iterative refinement.

Unique: Combines LLM-based agent reasoning with pluggable tool execution (web search, code execution, image generation, MCP servers) through a unified tool registry that abstracts provider-specific function-calling APIs. Uses subprocess isolation for code execution and supports both native function-calling (OpenAI, Anthropic) and prompt-based tool selection for other LLMs.

vs alternatives: Offers integrated agent execution with sandboxed code running and MCP server support in a single system, whereas LangChain agents require explicit chain composition and most frameworks don't natively support MCP or code sandboxing.

Stores vector embeddings and metadata in JSON files on disk while maintaining an in-memory index for fast similarity search. Uses a hybrid architecture where the file system serves as the persistent store and RAM holds the active search index, enabling both durability and performance without requiring a separate database server. Supports automatic index persistence and reload cycles.

Unique: Combines file-backed persistence with in-memory indexing, avoiding the complexity of running a separate database service while maintaining reasonable performance for small-to-medium datasets. Uses JSON serialization for human-readable storage and easy debugging.

vs alternatives: Lighter weight than Pinecone or Weaviate for local development, but trades scalability and concurrent access for simplicity and zero infrastructure overhead.

Implements vector similarity search using cosine distance calculation on normalized embeddings, with support for alternative distance metrics. Performs brute-force similarity computation across all indexed vectors, returning results ranked by distance score. Includes configurable thresholds to filter results below a minimum similarity threshold.

Unique: Implements pure cosine similarity without approximation layers, making it deterministic and debuggable but trading performance for correctness. Suitable for datasets where exact results matter more than speed.

vs alternatives: More transparent and easier to debug than approximate methods like HNSW, but significantly slower for large-scale retrieval compared to Pinecone or Milvus.

Accepts vectors of configurable dimensionality and automatically normalizes them for cosine similarity computation. Validates that all vectors have consistent dimensions and rejects mismatched vectors. Supports both pre-normalized and unnormalized input, with automatic L2 normalization applied during insertion.