huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-23 16:02:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add tests for all aliases

Browse Source
This commit is contained in:
Alex Weston 2025-01-30 14:11:05 -05:00 committed by drbh
parent d9cac33231
commit d278d3cf4c
1 changed files with 45 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

41
integration-tests/models/test_grammar_response_format_llama.py
View File

@ -29,11 +29,7 @@ async def test_grammar_response_format_llama_json(llama_grammar, response_snapsh
unit: str
temperature: List[int]
# send the request
response = requests.post(
f"{llama_grammar.base_url}/v1/chat/completions",
headers=llama_grammar.headers,
json={
json_payload={
"model": "tgi",
"messages": [
{
@ -48,7 +44,40 @@ async def test_grammar_response_format_llama_json(llama_grammar, response_snapsh
"seed": 42,
"max_tokens": 500,
"response_format": {"type": "json_object", "value": Weather.schema()},
},
}
# send the request
response = requests.post(
f"{llama_grammar.base_url}/v1/chat/completions",
headers=llama_grammar.headers,
json=json_payload,
)
chat_completion = response.json()
called = chat_completion["choices"][0]["message"]["content"]
assert response.status_code == 200
assert called == '{ "unit": "fahrenheit", "temperature": [ 72, 79, 88 ] }'
assert chat_completion == response_snapshot
json_payload["response_format"]["type"] = "json"
response = requests.post(
f"{llama_grammar.base_url}/v1/chat/completions",
headers=llama_grammar.headers,
json=json_payload,
)
chat_completion = response.json()
called = chat_completion["choices"][0]["message"]["content"]
assert response.status_code == 200
assert called == '{ "unit": "fahrenheit", "temperature": [ 72, 79, 88 ] }'
assert chat_completion == response_snapshot
json_payload["response_format"]["type"] = "json_schema"
response = requests.post(
f"{llama_grammar.base_url}/v1/chat/completions",
headers=llama_grammar.headers,
json=json_payload,
)
chat_completion = response.json()