raphaelrk/clip-batch
Compute CLIP embeddings for batches of text and images. Accept multiple newline-separated inputs and return one vector e...
Found 51 models (showing 41-51)
Compute CLIP embeddings for batches of text and images. Accept multiple newline-separated inputs and return one vector e...
Compute semantic similarity scores for input sentences. Takes a list of sentences, encodes them into sentence embeddings...
Convert text to vector embeddings for semantic search, RAG, and pgvector-based retrieval. Accepts a string or an array o...
Generates text responses from text prompts, messages, and images with multimodal capabilities. Processes both text and v...
Generates text responses from prompts with ultra-low latency and fast response times. Supports up to 1 million token con...
Generate text and analyze images with Anthropic's most advanced language model, featuring state-of-the-art coding, reaso...
Advanced multimodal language model that processes text, images, videos, and audio to generate text responses. Features t...
Generates text responses with advanced reasoning capabilities based on textual prompts. Excels at mathematical problem-s...
Reranks search results by scoring query-document pairs for improved retrieval accuracy in RAG pipelines. Uses a cross-en...
Generates text based on text prompts and optional image inputs. Handles multimodal tasks combining text and image analys...
Generate text based on text prompts and optional image inputs. This multimodal language model handles both text and imag...