mirror of
https://github.com/katanemo/plano.git
synced 2026-07-11 16:12:13 +02:00
more updates
This commit is contained in:
parent
03a02455e8
commit
81f50911a0
11 changed files with 269 additions and 88 deletions
31
demos/llm_routing/arch_config.yaml
Normal file
31
demos/llm_routing/arch_config.yaml
Normal file
|
|
@ -0,0 +1,31 @@
|
|||
version: "0.1-beta"
|
||||
|
||||
listener:
|
||||
address: 0.0.0.0
|
||||
port: 10000
|
||||
message_format: huggingface
|
||||
connect_timeout: 0.005s
|
||||
|
||||
llm_providers:
|
||||
- name: gpt-3.5
|
||||
access_key: $OPENAI_API_KEY
|
||||
provider: openai
|
||||
model: gpt-3.5-turbo
|
||||
|
||||
- name: gpt-4o
|
||||
access_key: $OPENAI_API_KEY
|
||||
provider: openai
|
||||
model: gpt-4o
|
||||
|
||||
- name: ministral-8b
|
||||
access_key: $MISTRAL_API_KEY
|
||||
provider: mistral
|
||||
model: ministral-8b-latest
|
||||
|
||||
- name: ministral-3b
|
||||
access_key: $MISTRAL_API_KEY
|
||||
provider: mistral
|
||||
model: ministral-3b-latest
|
||||
|
||||
tracing:
|
||||
random_sampling: 100
|
||||
12
demos/llm_routing/docker-compose.yaml
Normal file
12
demos/llm_routing/docker-compose.yaml
Normal file
|
|
@ -0,0 +1,12 @@
|
|||
services:
|
||||
|
||||
chatbot_ui:
|
||||
build:
|
||||
context: ../../chatbot_ui
|
||||
dockerfile: Dockerfile
|
||||
ports:
|
||||
- "18080:8080"
|
||||
environment:
|
||||
- CHAT_COMPLETION_ENDPOINT=http://host.docker.internal:12000/v1
|
||||
extra_hosts:
|
||||
- "host.docker.internal:host-gateway"
|
||||
Loading…
Add table
Add a link
Reference in a new issue