skills.rest
air-gapped
air-gappedOFFICIAL
Explore all skills by this author →
GitHub

open-webui-embeddings

Wire HuggingFace TEI embeddings and reranking into Open WebUI via LiteLLM.

5|1|Updated Apr 19, 2026
Search Tags:#embeddings#rag#translation#rerank#litellm#open-webui#tei
One-click install
npx skills add https://github.com/air-gapped/skills --skill open-webui-embeddings
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: open-webui-embeddings
Source: https://github.com/air-gapped/skills/tree/main/.claude/skills/open-webui-embeddings
Command: npx skills add https://github.com/air-gapped/skills --skill open-webui-embeddings

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Open WebUI's retrieval-augmented generation (RAG) stack often requires correct wiring of TEI embeddings and reranking to TEI-compatible endpoints. This skill provides an operator-focused blueprint for connecting HuggingFace TEI embeddings through LiteLLM to TEI/Open WebUI, including exact wire shapes, necessary configuration, and error-handling considerations.

Core Features & Use Cases

  • Wire TEI embeddings via OpenAI-compatible /v1/embeddings path with proper model wiring.
  • Rerank through Cohere↔TEI translation for the /rerank endpoint and the associated data shapes.
  • Use Case: Deploy a robust TEI-backed Open WebUI RAG for enterprise search and knowledge retrieval.

Quick Start

Configure TEI endpoints, LiteLLM, and Open WebUI with the correct embedding and rerank paths to enable end-to-end TEI-backed Open WebUI RAG.

Frequently Asked Questions about open-webui-embeddings

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I wire HuggingFace TEI embeddings into Open WebUI's RAG pipeline?▼

Wire TEI embeddings into Open WebUI's RAG by routing requests through a LiteLLM proxy, ensuring Open WebUI payloads match TEI's /v1/embeddings endpoints and required environment variable mappings for consistent end-to-end operation.

What is the correct way to configure reranking with TEI in Open WebUI?▼

Configuring TEI reranking in Open WebUI requires a Cohere-to-TEI translation for the /rerank endpoint, ensuring the associated data shapes match correctly across LiteLLM and the Open WebUI RAG pipeline.

Does Open WebUI support HuggingFace TEI endpoints natively for retrieval?▼

Open WebUI requires a LiteLLM proxy to properly support HuggingFace TEI endpoints, translating Open WebUI payloads to match TEI's expected embedding and reranking data shapes for robust enterprise retrieval.

How do I set up the LiteLLM proxy for TEI embeddings and reranking?▼

Setting up the LiteLLM proxy for TEI involves configuring exact manifests, environment variables, and endpoint mappings to bridge Open WebUI's RAG pipeline with TEI's embedding and rerank paths.

Why does my Open WebUI RAG pipeline fail when connecting to TEI rerank endpoints?▼

Open WebUI RAG pipelines fail with TEI when the Cohere-to-TEI translation for the /rerank endpoint is incorrectly wired, causing payload mismatches between LiteLLM and the expected TEI data shapes.

Related Skills

Explore More Software Engineering Skills→
jayll1303jayll1303
17

text-embeddings-inference

Deploy HuggingFace TEI Docker images for embedding and re-ranking inference.

Community
Advanced
qiphonqiphon
2

AgentDB Vector Search

Rank documents by vector similarity for semantic retrieval in RAG pipelines.

Community
Intermediate
bugrabilgebugrabilge
10

rag-engineer

Design and optimize RAG systems for LLM applications.

Community
Advanced
NVIDIA-AI-IOTNVIDIA-AI-IOT
110

jetson-llm-serve

Deploy OpenAI-compatible LLM or VLM serving endpoints on Jetson devices.

Official
Advanced