apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-05-04 05:12:55 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Use intent model from archfc to pick prompt gateway (#328)

Browse source
This commit is contained in:
Shuguang Chen 2024-12-20 13:25:01 -08:00 • committed by GitHub
parent 67b8fd635e
commit ba7279becb
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
151 changed files with 8642 additions and 10932 deletions
Download patch file Download diff file Expand all files Collapse all files

77
e2e_tests/api_llm_gateway.rest
View file

@ -1,77 +0,0 @@
@llm_endpoint = http://localhost:12000
@openai_endpoint = https://api.openai.com
@access_key = {{$dotenv OPENAI_API_KEY}}
### openai request
POST {{openai_endpoint}}/v1/chat/completions HTTP/1.1
Content-Type: application/json
Authorization: Bearer {{access_key}}
{
"messages": [
{
"role": "user",
"content": "hello"
}
],
"model": "gpt-4o-mini",
"stream": true
}
### openai request (streaming)
POST {{openai_endpoint}}/v1/chat/completions HTTP/1.1
Content-Type: application/json
Authorization: Bearer {{access_key}}
{
"messages": [
{
"role": "user",
"content": "hello"
}
],
"model": "gpt-4o-mini",
"stream": true
}
### llm gateway request
POST {{llm_endpoint}}/v1/chat/completions HTTP/1.1
Content-Type: application/json
{
"messages": [
{
"role": "user",
"content": "hello"
}
]
}
### llm gateway request (streaming)
POST {{llm_endpoint}}/v1/chat/completions HTTP/1.1
Content-Type: application/json
{
"messages": [
{
"role": "user",
"content": "hello"
}
],
"stream": true
}
### llm gateway request (provider hint)
POST {{llm_endpoint}}/v1/chat/completions HTTP/1.1
Content-Type: application/json
x-arch-llm-provider-hint: gpt-3.5-turbo-0125
{
"messages": [
{
"role": "user",
"content": "hello"
}
]
}