Experience hybrid search combining vector embeddings and full-text search, unified through Reciprocal Rank Fusion for unparalleled retrieval precision.
PDF, DOCX, TXT
1536 Dimensions
Vector + Text + RRF
Streaming via AI SDK
From document upload to AI-powered answers in four seamless steps, each optimized for maximum retrieval accuracy.
Upload your documents in any format. Our processor automatically extracts and chunks content for optimal retrieval.
Each chunk is transformed into a high-dimensional vector using OpenAI's latest embedding model for semantic understanding.
Your queries trigger both vector similarity search and full-text search, combined using Reciprocal Rank Fusion.
The retrieved context is passed to an LLM which generates accurate, contextual responses streamed in real-time.
Our dual-path architecture combines the semantic understanding of vector search with the precision of full-text matching.
Finds semantically similar content using 1536-dimensional embeddings and cosine similarity. Great for understanding intent and context.
Matches exact keywords and phrases using Lucene's BM25 algorithm. Perfect for specific terms and acronyms.
Combines rankings using 1/(K+rank) formula where K=60. This weighting creates balanced, highly accurate results.
Autonomous AI agents that reason, plan, and adapt. Our agentic harness transforms simple retrieval into intelligent, multi-step problem-solving.
Autonomous planning and decomposition of complex queries into manageable sub-tasks, enabling sophisticated problem-solving across multiple retrieval cycles.
Dynamic integration with external tools, APIs, and databases. The agent decides which tools to invoke based on query requirements.
Continuous reflection and refinement of outputs. When initial results are insufficient, the agent iterates until quality thresholds are met.
Adaptive retrieval strategies that consider conversation history, user intent, and document relevance to deliver precise results.
The agent harness is the complete architectural system surrounding an LLM—everything except the model itself. It manages the entire context lifecycle: planning queries, orchestrating tool calls, maintaining memory, and verifying outputs.
Think of it as the "operating system" for your AI agent. While the LLM provides reasoning capabilities, the harness provides structure, control, and reliability.
Breaks complex queries into executable steps
Maintains context across conversation turns
Ensures output quality and safety constraints
Orchestrates connections to external systems
See how agentic capabilities transform the retrieval experience from simple question-answering to intelligent problem-solving.
One query, one search, one response
Fixed chunk retrieval without adaptation
Cannot identify or fix retrieval failures
Cannot leverage external tools or APIs
Iterative retrieval with query refinement
Adapts retrieval strategy per query
Detects gaps and re-queries as needed
Integrates databases, APIs, calculators
Agent breaks query into sub-tasks: retrieve Q3 data, compare to Q2, identify patterns
Queries vector DB, calls SQL database, fetches external market data
Checks completeness, identifies gaps in regional data, performs additional retrieval
Combines insights into actionable recommendations with cited sources
Enhance retrieval accuracy by combining vector search with knowledge graph traversal. Entity relationships provide contextual depth that traditional RAG cannot achieve.
Automatically identifies key entities from retrieved documents: people, organisations, technologies, concepts, and locations for graph-based analysis.
Neo4j's native graph database stores entity relationships with index-free adjacency, enabling up to 1000x faster traversal than relational queries.
Results are re-ranked using entity connection strength with a 30% boost weight, surfacing contextually related content that pure vector search misses.
Both approaches excel in different scenarios. Choose based on your data structure and query patterns.
GraphRAG excels when understanding relationships between entities is critical.
Patient records, treatment relationships, drug interactions
Organisational structures, project dependencies, expertise mapping
Citation networks, author collaborations, concept evolution
Transaction patterns, network analysis, anomaly detection
Enterprise-grade technologies working together to deliver fast, accurate, and scalable RAG experiences.
Every component optimized for speed, accuracy, and reliability. Real metrics from real-world testing.
Hybrid search with RRF achieves near-perfect context retrieval
High-dimensional embeddings capture semantic nuance
First token delivered within 2 seconds of query
Optimized fusion constant for balanced ranking
Upload your documents and experience the power of hybrid search with Reciprocal Rank Fusion firsthand.
Learn more about how the RAG Agent demo works and the technology behind it.
RAG (Retrieval-Augmented Generation) combines document search with AI to answer questions based on your uploaded documents. It retrieves relevant content and uses an LLM to generate accurate, contextual responses.
The demo supports PDF, DOCX, TXT, and Markdown files. Documents are processed, chunked into 500-token segments, and stored with 1536-dimensional vector embeddings for semantic search.
We use a combination of vector search (semantic similarity via cosine distance) and full-text search (keyword matching via Lucene/BM25), merged using Reciprocal Rank Fusion (RRF) with K=60 for optimal ranking.
RRF is a rank aggregation algorithm that combines multiple ranked lists into a single ranking. Each result receives a score of 1/(K+rank) from each list, where K=60 is a constant that balances the contribution of different ranking positions.
The hybrid approach achieves ~98% retrieval accuracy because it combines the semantic understanding of vector search with the precision of lexical matching. Vector search catches paraphrases and related concepts, while text search ensures exact term matches aren't missed.
Yes. All documents are isolated by Clerk user ID using MongoDB's Row-Level Security equivalent via query filters. Data is stored securely in MongoDB Atlas with encryption at rest. This is a demo application - for production, additional security measures may be needed.