vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

server : add OAI compat for /v1/completions (#10974)

Browse source 
* server : add OAI compat for /v1/completions

* add test

* add docs

* better docs
This commit is contained in:
Xuan Son Nguyen 2024-12-31 12:34:13 +01:00 • committed by GitHub
parent bc7b1f8632
commit 5896c65232
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 400 additions and 146 deletions
Download patch file Download diff file Expand all files Collapse all files

6
examples/server/tests/unit/test_chat_completion.py
View file

@ -83,7 +83,7 @@ def test_chat_completion_stream(system_prompt, user_prompt, max_tokens, re_conte
def test_chat_completion_with_openai_library():
global server
server.start()
client = OpenAI(api_key="dummy", base_url=f"http://{server.server_host}:{server.server_port}")
client = OpenAI(api_key="dummy", base_url=f"http://{server.server_host}:{server.server_port}/v1")
res = client.chat.completions.create(
model="gpt-3.5-turbo-instruct",
messages=[
@ -170,7 +170,7 @@ def test_chat_completion_with_timings_per_token():
def test_logprobs():
global server
server.start()
client = OpenAI(api_key="dummy", base_url=f"http://{server.server_host}:{server.server_port}")
client = OpenAI(api_key="dummy", base_url=f"http://{server.server_host}:{server.server_port}/v1")
res = client.chat.completions.create(
model="gpt-3.5-turbo-instruct",
temperature=0.0,
@ -197,7 +197,7 @@ def test_logprobs():
def test_logprobs_stream():
global server
server.start()
client = OpenAI(api_key="dummy", base_url=f"http://{server.server_host}:{server.server_port}")
client = OpenAI(api_key="dummy", base_url=f"http://{server.server_host}:{server.server_port}/v1")
res = client.chat.completions.create(
model="gpt-3.5-turbo-instruct",
temperature=0.0,