Document search

Models 6

• Gen 7 LFM
  LFM2.5 Embedding 350M

  By Liquid AI

  350M-parameter bidirectional multilingual bi-encoder that maps each document to a single dense vector for fast, cost-efficient multilingual and cross-lingual search. Supports 11 languages. Built from LFM2.5-350M-Base. Produces the smallest, cheapest index among LFM2.5 retrieval models. Available in GGUF format for CPU and edge deployment.

  🔍Information retrieval🔍Document search🔍Conceptual search
  NewText

  Released 9d ago
• Gen 7 LFM
  LFM2.5 ColBERT 350M

  By Liquid AI

  350M-parameter bidirectional multilingual retrieval model using per-token ColBERT-style late interaction (MaxSim) for accurate multilingual and cross-lingual search. Supports 11 languages. Built from LFM2.5-350M-Base with bidirectional attention and non-causal convolutions. Available in GGUF format for CPU and edge deployment.

  🔍Information retrieval🔍Document search🔍Conceptual search
  NewText

  Released 9d ago
• Gen 7
  pplx embed context v1 0.6b

  By Perplexity

  A 0.6B-parameter contextual text embedding model for RAG pipelines. Unlike standard embedding models, it takes full document chunks together so each chunk's embedding reflects surrounding context. Produces 1024-dimensional int8-quantized vectors with a 32K token context window. Supports binary quantization and MRL. Multilingual and instruction-free. Available via Perplexity API and as open weights.

  🔍Information retrieval📚Knowledge bases🔍Document search🔢Vector indexes
  Text

  Released 4mo ago
• Gen 7
  pplx embed context v1 4B

  By Perplexity

  A 4B-parameter contextual text embedding model built on diffusion-pretrained Qwen3, designed for RAG pipelines where document chunks benefit from surrounding context. Produces 2560-dimensional INT8/BINARY-quantized embeddings with a 32K context window and MRL support. No instruction prefixes required. MIT-licensed with open weights.

  🔍Information retrieval🔍Document search🗄️Vector databases🔢Vector indexes
  Text

  Released 4mo ago
• Gen 7 Qwen
  Qwen3 Coder

  By Alibaba

  Qwen3 Coder is Alibaba’s code-focused Qwen3 variant. It handles repo-aware generation, completion, debugging, and test creation, with long context, tool and function calling, and strict JSON or diff outputs for IDEs and agents.

  💻Coding🔎Problem solving🐞Debugging🔍Document search
  Text

  Released 11mo ago
• Gen 7 Rerank
  Rerank 2 lite

  By Voyage AI

  rerank-2-lite is a lightweight multilingual cross-encoder reranker from Voyage AI. It scores and reorders candidate documents by relevance to a query, optimized for low latency while maintaining strong retrieval quality. Supports an 8K-token combined context length per query-document pair and natively handles 31+ languages.

  🔍Information retrieval🔍Document search🔍Conceptual search
  Text

  Released 1y ago