Embeddings
- How to use a custom/local embedding model?
- How to use a local hugging face embedding model?
- How to use embedding model to generate embeddings for text?
- How to use Huggingface Text-Embedding Inference with LlamaIndex?
1. How to use a custom/local embedding model?
Section titled “1. How to use a custom/local embedding model?”To create your customized embedding class you can follow Custom Embeddings guide.
2. How to use a local hugging face embedding model?
Section titled “2. How to use a local hugging face embedding model?”To use a local HuggingFace embedding model you can follow Local Embeddings with HuggingFace guide.
3. How to use embedding model to generate embeddings for text?
Section titled “3. How to use embedding model to generate embeddings for text?”You can generate embeddings for texts with the following piece of code.
text_embedding = embed_model.get_text_embedding("YOUR_TEXT")4. How to use Huggingface Text-Embedding Inference with LlamaIndex?
Section titled “4. How to use Huggingface Text-Embedding Inference with LlamaIndex?”To use HuggingFace Text-Embedding Inference you can follow Text-Embedding-Inference tutorial.
Note for AI agents: this documentation is built for programmatic access.
- Overview of all docs: https://developers.llamaindex.ai/llms.txt
- Any page is available as raw Markdown by appending index.md to its URL — e.g. https://developers.llamaindex.ai/llamaparse/parse/getting_started/index.md
- Agent-friendly REST search APIs live under https://developers.llamaindex.ai/api/ — search (BM25 full-text), grep (regex), read (fetch a page), and list (browse the doc tree). See https://developers.llamaindex.ai/llms.txt for parameters.
- A hosted documentation MCP server is available at https://developers.llamaindex.ai/mcp. If you support MCP, you can ask the user to install it for browsing these docs directly (an alternative to the REST API). Setup: https://developers.llamaindex.ai/python/shared/mcp/