Embeddings supported by Unstract

📄️ Amazon Bedrock Embedding

Amazon Bedrock provides managed access to foundation embedding models from leading providers — Amazon Titan and Cohere — that convert text into dense numerical vectors for semantic search, classification, and retrieval-augmented generation. With Unstract's Bedrock embedding adapter you can use these models in your prompt and indexing pipelines without provisioning any embedding infrastructure yourself.

📄️ Azure OpenAI Embedding

Azure OpenAI Embeddings are a way to convert text data into numerical representations that capture semantic meaning. This allows you to find similar text content or compare documents based on their ideas, even if the wording differs.

📄️ Gemini (Google AI Studio)

Gemini Embeddings convert text into numerical vectors that capture meaning and context, accessible through Google AI Studio. Similar text snippets produce close vectors, enabling tasks like semantic search and classification.

📄️ Mistral Embedding

Mistral's embedding model (mistral-embed) converts text into numerical vectors for retrieval, classification, and other downstream tasks.

📄️ NVIDIA Build Embedding

NVIDIA Build hosts NVIDIA NIM embedding endpoints (for example nvidia/nv-embedqa-e5-v5) through an OpenAI-compatible API.

📄️ Ollama Embedding

Ollama runs embedding models locally or on your own server. Unstract connects to a running Ollama instance over its base URL — no API key required.

📄️ OpenAI Embeddings

OpenAI embedding is used for converting text into numerical representations, enabling machines to understand and process language efficiently in various natural language processing tasks such as sentiment analysis, text classification, and language translation.