Navigate:
All Reposopen-webui
~$OPENWE0.2%

Open WebUI: Self-hosted AI chat interface

Extensible multi-LLM chat platform with RAG pipeline.

LIVE RANKINGS • 06:52 AM • STEADY
TOP 25TOP 25TOP 25TOP 25TOP 25TOP 25TOP 25TOP 25TOP 25TOP 25TOP 25TOP 25
OVERALL
#18
4
AI & ML
#9
5
30 DAY RANKING TREND
ovr#18
·AI#9
STARS
120.1K
FORKS
16.9K
DOWNLOADS
14
7D STARS
+269
7D FORKS
+40
Tags:
See Repo:
Share:

Learn more about open-webui

Open WebUI is a self-hosted web application that provides a chat interface for multiple LLM backends and services. It operates as a containerized application deployable via Docker or Kubernetes, supporting both CPU and GPU execution through tagged image variants. The platform includes a built-in RAG engine for document processing, integrates with external APIs for web search, and offers administrative controls for user management and permissions. Common deployment scenarios include local Ollama instances, cloud-hosted API services, and enterprise environments with identity provider integration.


1

Unified Multi-Backend Interface

Connects to Ollama, OpenAI, and OpenAI-compatible endpoints through configurable API URLs. Switch between local and remote LLM sources without changing the chat interface or redeploying.

2

Built-in RAG Pipeline

Processes local documents and web search results directly within the application. Injects context into chat through command syntax without external vector databases or API dependencies.

3

SCIM 2.0 Provisioning

Automates user and group synchronization with enterprise identity providers like Okta and Azure AD. Provides role-based access control for multi-tenant deployments without manual account management.


from open_webui.tools import Tool

class WeatherTool(Tool):
    def __init__(self):
        self.name = "weather"
        self.description = "Get current weather for a location"
    
    async def run(self, location: str) -> dict:
        # Tool logic to fetch weather data
        return {"location": location, "temp": 72, "condition": "sunny"}

vv0.6.36

Fixes critical tool-calling regression and adds OAuth group separator config; no breaking changes reported.

  • Set OAUTH_GROUPS_SEPARATOR env var if using semicolon-delimited group claims from providers like CILogon.
  • Tool calling now works again after async function handling was corrected in parameter updates.
vv0.6.35

Breaking: SSE event emission from direct-connected model servers now blocked to fix code injection vulnerability; image generation overhauled with editing support.

  • Remove reliance on event emitters from direct model servers; arbitrary JavaScript execution via SSE is now prevented.
  • Configure ELEVENLABS_API_BASE_URL for EU endpoints or OAUTH_ROLES_SEPARATOR for LDAP roles containing commas if needed.
vv0.6.34

JWT tokens now expire after 4 weeks by default (previously unlimited); admins see security warnings if set to unlimited.

  • Review JWT_EXPIRES_IN setting; tokens now default to 4-week expiration with warnings logged for unlimited configurations.
  • Add MinerU document parser support for local or managed API deployments to expand parsing backend options.

See how people are using open-webui

Loading tweets...


[ EXPLORE MORE ]

Related Repositories

Discover similar tools and frameworks used by developers