Contextual AI Reranker
1st reranker that follows custom instructions. Rank a list of documents according to their relevance to a query primarily and your custom instructions secondarily. We evaluated the model on instructions for recency, document type, source, and metadata, and it can generalize to other instructions as well. The reranker supports multilinguality. The total request cannot exceed 400,000 tokens. The combined length of the query, instruction and any document with its metadata must not exceed 8,000 tokens. See our blog post and code examples. Email rerank-feedback@contextual.ai with any feedback or questions.
Reactions (1)
Similar products
by description similarity
We built a better reranker and open sourced it
huggingface.coFamily of instruction-following multilingual rerankers on the cost/performance Pareto frontier across public and customer benchmarks
Ratel
github.comgive agents unlimited tools and skills without context bloat
PageIndex for Reasoning-Based RAG
vectifyai.notion.siteLarge Language Models (LLMs) are powerful tools for language understanding and generation, but they suffer from a fundamental limitation: the context window. Most LLMs can only process a limited number of tokens at a time. For instance, Claude does not allow uploading very long documents in full, which makes tasks like long document analysis or question answering particularly challenging.
Open-Source Pull Request AI Reviewer
github.comContext-aware AI reviewer for Pull Requests. Instant summary, line-by-line comments, title generation and more
Context profiler for LLMs and AI agents - used to introspect context contents and reduce token costs