gmakstutis/openrag
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix max_tokens error on gpt 4o

Browse source
This commit is contained in:
Lucas Oliveira 2025-11-14 18:02:56 -03:00
parent a2e5baa665
commit 2f38b0b190
1 changed files with 14 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
src/api/provider_validation.py
View file

@ -112,7 +112,7 @@ async def _test_openai_completion_with_tools(api_key: str, llm_model: str) -> No
}
# Simple tool calling test
payload = {
base_payload = {
"model": llm_model,
"messages": [
{"role": "user", "content": "What tools do you have available?"}
@ -136,10 +136,11 @@ async def _test_openai_completion_with_tools(api_key: str, llm_model: str) -> No
}
}
],
"max_tokens": 50,
}
async with httpx.AsyncClient() as client:
# Try with max_tokens first
payload = {**base_payload, "max_tokens": 50}
response = await client.post(
"https://api.openai.com/v1/chat/completions",
headers=headers,
@ -147,6 +148,17 @@ async def _test_openai_completion_with_tools(api_key: str, llm_model: str) -> No
timeout=30.0,
)
# If max_tokens doesn't work, try with max_completion_tokens
if response.status_code != 200:
logger.info("max_tokens parameter failed, trying max_completion_tokens instead")
payload = {**base_payload, "max_completion_tokens": 50}
response = await client.post(
"https://api.openai.com/v1/chat/completions",
headers=headers,
json=payload,
timeout=30.0,
)
if response.status_code != 200:
logger.error(f"OpenAI completion test failed: {response.status_code} - {response.text}")
raise Exception(f"OpenAI API error: {response.status_code}")