mirror of
https://github.com/katanemo/plano.git
synced 2026-05-03 21:02:56 +02:00
fix model warning and use openwebui for preference based router demo
This commit is contained in:
parent
fffa837a06
commit
176f039bbc
4 changed files with 18 additions and 16 deletions
|
|
@ -1,7 +1,7 @@
|
|||
version: "0.1-beta"
|
||||
|
||||
routing:
|
||||
model: gpt-4o
|
||||
model: archgw-v1-router-model
|
||||
|
||||
listeners:
|
||||
egress_traffic:
|
||||
|
|
@ -14,7 +14,7 @@ llm_providers:
|
|||
|
||||
- name: archgw-v1-router-model
|
||||
provider_interface: openai
|
||||
model: cotran2/llama-4-epoch
|
||||
model: cotran2/qwen-4-epoch-2600
|
||||
base_url: http://34.46.85.85:8000/v1
|
||||
|
||||
- name: gpt-4o
|
||||
|
|
|
|||
|
|
@ -1,17 +1,14 @@
|
|||
services:
|
||||
|
||||
chatbot_ui:
|
||||
build:
|
||||
context: ../../shared/chatbot_ui
|
||||
dockerfile: Dockerfile
|
||||
open-web-ui:
|
||||
image: ghcr.io/open-webui/open-webui:main
|
||||
restart: always
|
||||
ports:
|
||||
- "18080:8080"
|
||||
- "8080:8080"
|
||||
environment:
|
||||
- CHAT_COMPLETION_ENDPOINT=http://host.docker.internal:12000/v1
|
||||
extra_hosts:
|
||||
- "host.docker.internal:host-gateway"
|
||||
volumes:
|
||||
- ./arch_config.yaml:/app/arch_config.yaml
|
||||
- DEFAULT_MODEL=gpt-4o-mini
|
||||
- ENABLE_OPENAI_API=true
|
||||
- OPENAI_API_BASE_URL=http://host.docker.internal:12000/v1
|
||||
|
||||
jaeger:
|
||||
build:
|
||||
|
|
|
|||
|
|
@ -1,10 +1,10 @@
|
|||
@arch_llm_router_endpoint = http://35.192.87.187:8000
|
||||
|
||||
POST {{arch_llm_router_endpoint}}/v1/chat/completions HTTP/1.1
|
||||
POST http://34.46.85.85:8000/v1/chat/completions HTTP/1.1
|
||||
Content-Type: application/json
|
||||
|
||||
{
|
||||
"model": "cotran2/llama-1b-4-26",
|
||||
"model": "cotran2/qwen-4-epoch-2600",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue