{
 "schema_version": 1,
 "generated": "2026-10-23",
 "id": "vllm-project-vllm--create-text-embeddings-with-served-models",
 "repo": "vllm-project/vllm",
 "repo_url": "https://github.com/vllm-project/vllm",
 "repo_slug": "vllm-project-vllm",
 "title": "Create text embeddings from a served retrieval model",
 "page_title": "How to create text embeddings from a served retrieval model with vLLM",
 "summary": "Use an embedding model served by vLLM to turn documents and queries into vectors.",
 "who": "A researcher or developer building a search or retrieval feature who needs embeddings from an open model.",
 "problem": "Building a search index needs vectors from a model, and a generic LLM endpoint does not return them.",
 "outcome": "Embedding vectors for your documents and queries, ready to store in a vector index.",
 "steps": [
  "Install vLLM with `uv pip install vllm`.",
  "Serve an embedding model such as E5-Mistral or GTE, following the supported models list in the docs. (inferred, check the README)",
  "Send your documents and queries to the embedding endpoint as described in the official documentation. (inferred, check the README)",
  "Save the returned vectors with the document IDs they belong to.",
  "Run one query and check that the closest document is a relevant match."
 ],
 "agent_prompt": "Using the vllm-project/vllm repo, serve the embedding model <embedding-model-id> and create vectors for the documents in <documents-file>. Run the query <query-text> and return the top three documents by similarity. Verify that the top result is relevant to the query.",
 "agents": [
  "any"
 ],
 "difficulty": "Advanced",
 "time": "1 hour 30 minutes",
 "basis": "readme",
 "caveat": "The README lists E5-Mistral, GTE and ColBERT as examples, but the embedding request format is not shown and must be checked in the docs.",
 "category": "Software and DevOps",
 "tags": [
  "Software and DevOps"
 ],
 "lang": "python",
 "requirements": [
  "Python with uv or pip installed",
  "A supported NVIDIA, AMD or Intel GPU, or an x86, ARM or PowerPC CPU",
  "A Hugging Face model you are allowed to download and use"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": false,
 "score": 0.7,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/vllm-project-vllm/create-text-embeddings-with-served-models/",
 "md": "https://dedupedai.com/use-cases/vllm-project-vllm/create-text-embeddings-with-served-models/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/vllm-project-vllm--create-text-embeddings-with-served-models.json",
 "api_version": "v1"
}