deprecate open-web-ui and use anythingllm

2026-06-17 15:25:17 +02:00 · 2026-02-07 15:42:23 -08:00 · 2026-02-07 15:42:23 -08:00 · 419df11786
commit 419df11786
parent 86a89bc3e0
10 changed files with 75 additions and 50 deletions
--- a/demos/use_cases/http_filter/README.md
+++ b/demos/use_cases/http_filter/README.md
@ -47,15 +47,15 @@ This brings up:
 - RAG Agent REST server on port 10505
 - Plano listener on port 8001 (and gateway on 12000)
 - Jaeger UI for viewing traces at http://localhost:16686
- Open WebUI at http://localhost:8080 for interactive queries
+- AnythingLLM at http://localhost:3001 for interactive queries

 > Set `OPENAI_API_KEY` in your environment before running; `LLM_GATEWAY_ENDPOINT` defaults to `http://host.docker.internal:12000/v1`.

 ### 2. Test the system

-**Option A: Using Open WebUI (recommended)**
+**Option A: Using AnythingLLM (recommended)**

-Navigate to http://localhost:8080 and send queries through the chat interface.
+Navigate to http://localhost:3001 and send queries through the chat interface.

 **Option B: Using curl**
 ```bash
--- a/demos/use_cases/http_filter/docker-compose.yaml
+++ b/demos/use_cases/http_filter/docker-compose.yaml
@ -31,12 +31,17 @@ services:
      - "16686:16686"
      - "4317:4317"
      - "4318:4318"
-  open-web-ui:
-    image: dyrnq/open-webui:main
+  anythingllm:
+    image: mintplexlabs/anythingllm
    restart: always
    ports:
-      - "8080:8080"
+      - "3001:3001"
+    cap_add:
+      - SYS_ADMIN
    environment:
-      - DEFAULT_MODEL=gpt-4o-mini
-      - ENABLE_OPENAI_API=true
-      - OPENAI_API_BASE_URL=http://host.docker.internal:8001/v1
+      - STORAGE_DIR=/app/server/storage
+      - LLM_PROVIDER=generic-openai
+      - GENERIC_OPEN_AI_BASE_PATH=http://plano:8001/v1
+      - GENERIC_OPEN_AI_MODEL_PREF=gpt-4o-mini
+      - GENERIC_OPEN_AI_MODEL_TOKEN_LIMIT=128000
+      - GENERIC_OPEN_AI_API_KEY=sk-placeholder
--- a/demos/use_cases/llm_routing/docker-compose.yaml
+++ b/demos/use_cases/llm_routing/docker-compose.yaml
@ -15,15 +15,20 @@ services:
      - ./config.yaml:/app/arch_config.yaml:ro
      - /etc/ssl/cert.pem:/etc/ssl/cert.pem

-  open-web-ui:
-    image: dyrnq/open-webui:main
+  anythingllm:
+    image: mintplexlabs/anythingllm
    restart: always
    ports:
-      - "8080:8080"
+      - "3001:3001"
+    cap_add:
+      - SYS_ADMIN
    environment:
-      - DEFAULT_MODEL=gpt-4o-mini
-      - ENABLE_OPENAI_API=true
-      - OPENAI_API_BASE_URL=http://host.docker.internal:12000/v1
+      - STORAGE_DIR=/app/server/storage
+      - LLM_PROVIDER=generic-openai
+      - GENERIC_OPEN_AI_BASE_PATH=http://plano:12000/v1
+      - GENERIC_OPEN_AI_MODEL_PREF=gpt-4o-mini
+      - GENERIC_OPEN_AI_MODEL_TOKEN_LIMIT=128000
+      - GENERIC_OPEN_AI_API_KEY=sk-placeholder

  jaeger:
    build:
--- a/demos/use_cases/mcp_filter/README.md
+++ b/demos/use_cases/mcp_filter/README.md
@ -47,15 +47,15 @@ This brings up:
 - RAG Agent REST server on port 10505
 - Plano listener on port 8001 (and gateway on 12000)
 - Jaeger UI for viewing traces at http://localhost:16686
- Open WebUI at http://localhost:8080 for interactive queries
+- AnythingLLM at http://localhost:3001 for interactive queries

 > Set `OPENAI_API_KEY` in your environment before running; `LLM_GATEWAY_ENDPOINT` defaults to `http://host.docker.internal:12000/v1`.

 ### 2. Test the system

-**Option A: Using Open WebUI (recommended)**
+**Option A: Using AnythingLLM (recommended)**

-Navigate to http://localhost:8080 and send queries through the chat interface.
+Navigate to http://localhost:3001 and send queries through the chat interface.

 **Option B: Using curl**
 ```bash
--- a/demos/use_cases/mcp_filter/docker-compose.yaml
+++ b/demos/use_cases/mcp_filter/docker-compose.yaml
@ -33,12 +33,17 @@ services:
      - "16686:16686"
      - "4317:4317"
      - "4318:4318"
-  open-web-ui:
-    image: dyrnq/open-webui:main
+  anythingllm:
+    image: mintplexlabs/anythingllm
    restart: always
    ports:
-      - "8080:8080"
+      - "3001:3001"
+    cap_add:
+      - SYS_ADMIN
    environment:
-      - DEFAULT_MODEL=gpt-4o-mini
-      - ENABLE_OPENAI_API=true
-      - OPENAI_API_BASE_URL=http://host.docker.internal:8001/v1
+      - STORAGE_DIR=/app/server/storage
+      - LLM_PROVIDER=generic-openai
+      - GENERIC_OPEN_AI_BASE_PATH=http://plano:8001/v1
+      - GENERIC_OPEN_AI_MODEL_PREF=gpt-4o-mini
+      - GENERIC_OPEN_AI_MODEL_TOKEN_LIMIT=128000
+      - GENERIC_OPEN_AI_API_KEY=sk-placeholder
--- a/demos/use_cases/multi_agent_with_crewai_langchain/README.md
+++ b/demos/use_cases/multi_agent_with_crewai_langchain/README.md
@ -47,13 +47,13 @@ This starts:
 - **Plano** (ports 12000, 8001) - routing and orchestration
 - **CrewAI Flight Agent** (port 10520) - flight search
 - **LangChain Weather Agent** (port 10510) - weather forecasts
- **Open WebUI** (port 8080) - chat interface
+- **AnythingLLM** (port 3001) - chat interface
 - **Jaeger** (port 16686) - distributed tracing

 ### Try It Out

 1. **Open the Chat Interface**
-   - Navigate to [http://localhost:8080](http://localhost:8080)
+   - Navigate to [http://localhost:3001](http://localhost:3001)
   - Create an account (stored locally)

 2. **Ask Multi-Agent Questions**
@ -75,9 +75,9 @@ This starts:
 ## Architecture

 ```
-┌─────────────┐
-│  Open WebUI │ (Chat Interface)
-└──────┬──────┘
+┌──────────────┐
+│ AnythingLLM  │ (Chat Interface)
+└──────┬───────┘
       │
       v
 ┌─────────────┐
--- a/demos/use_cases/preference_based_routing/README.md
+++ b/demos/use_cases/preference_based_routing/README.md
@ -6,7 +6,7 @@ This demo shows how you can use user preferences to route user prompts to approp
 Make sure your machine is up to date with [latest version of plano]([url](https://github.com/katanemo/plano/tree/main?tab=readme-ov-file#prerequisites)). And you have activated the virtual environment.


-1. start the openwebui
+1. start anythingllm
 ```bash
 (venv) $ cd demos/use_cases/preference_based_routing
 (venv) $ docker compose up -d
@ -24,7 +24,7 @@ Make sure your machine is up to date with [latest version of plano]([url](https:
 ...
 ```

-3. open openwebui http://localhost:8080/
+3. open AnythingLLM http://localhost:3001/

 # Testing out preference based routing

--- a/demos/use_cases/preference_based_routing/docker-compose.yaml
+++ b/demos/use_cases/preference_based_routing/docker-compose.yaml
@ -18,15 +18,20 @@ services:
      - ./config.yaml:/app/arch_config.yaml:ro
      - /etc/ssl/cert.pem:/etc/ssl/cert.pem

-  # open-web-ui:
-  #   image: dyrnq/open-webui:main
-  #   restart: always
-  #   ports:
-  #     - "8080:8080"
-  #   environment:
-  #     - DEFAULT_MODELS=gpt-4o-mini
-  #     - ENABLE_OPENAI_API=true
-  #     - OPENAI_API_BASE_URL=http://host.docker.internal:12000/v1
+  anythingllm:
+    image: mintplexlabs/anythingllm
+    restart: always
+    ports:
+      - "3001:3001"
+    cap_add:
+      - SYS_ADMIN
+    environment:
+      - STORAGE_DIR=/app/server/storage
+      - LLM_PROVIDER=generic-openai
+      - GENERIC_OPEN_AI_BASE_PATH=http://plano:12000/v1
+      - GENERIC_OPEN_AI_MODEL_PREF=gpt-4o-mini
+      - GENERIC_OPEN_AI_MODEL_TOKEN_LIMIT=128000
+      - GENERIC_OPEN_AI_API_KEY=sk-placeholder

  jaeger:
    build:
--- a/demos/use_cases/travel_agents/README.md
+++ b/demos/use_cases/travel_agents/README.md
@ -52,7 +52,7 @@ docker compose up --build
 This starts:
 - Weather Agent on port 10510
 - Flight Agent on port 10520
- Open WebUI on port 8080
+- AnythingLLM on port 3001

 ### 3. Start Plano Orchestrator

@ -68,7 +68,7 @@ The gateway will start on port 8001 and route requests to the appropriate agents

 ### 4. Test the System

-**Option 1**: Use Open WebUI at http://localhost:8080
+**Option 1**: Use AnythingLLM at http://localhost:3001

 **Option 2**: Send requests directly to Plano Orchestrator:

@ -183,14 +183,14 @@ Defines the two agents, their descriptions, and routing configuration. The agent
 Orchestrates the deployment of:
 - Weather Agent (builds from Dockerfile)
 - Flight Agent (builds from Dockerfile)
- Open WebUI (for testing)
+- AnythingLLM (for testing)
 - Jaeger (for distributed tracing)

 ## Troubleshooting

 **Docker containers won't start**
 - Verify Docker and Docker Compose are installed
- Check that ports 10510, 10520, 8080 are available
+- Check that ports 10510, 10520, 3001 are available
 - Review container logs: `docker compose logs weather-agent` or `docker compose logs flight-agent`

 **Plano won't start**
--- a/demos/use_cases/travel_agents/docker-compose.yaml
+++ b/demos/use_cases/travel_agents/docker-compose.yaml
@ -40,15 +40,20 @@ services:
    command: ["uv", "run", "python", "src/travel_agents/flight_agent.py"]
    extra_hosts:
      - "host.docker.internal:host-gateway"
-  open-web-ui:
-    image: dyrnq/open-webui:main
+  anythingllm:
+    image: mintplexlabs/anythingllm
    restart: always
    ports:
-      - "8080:8080"
+      - "3001:3001"
+    cap_add:
+      - SYS_ADMIN
    environment:
-      - DEFAULT_MODEL=gpt-4o-mini
-      - ENABLE_OPENAI_API=true
-      - OPENAI_API_BASE_URL=http://host.docker.internal:8001/v1
+      - STORAGE_DIR=/app/server/storage
+      - LLM_PROVIDER=generic-openai
+      - GENERIC_OPEN_AI_BASE_PATH=http://plano:8001/v1
+      - GENERIC_OPEN_AI_MODEL_PREF=gpt-4o-mini
+      - GENERIC_OPEN_AI_MODEL_TOKEN_LIMIT=128000
+      - GENERIC_OPEN_AI_API_KEY=sk-placeholder
    depends_on:
      - weather-agent
      - flight-agent