phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 18:54:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(ollama_chat.py): fix ollama chat completion token counting

Browse source
This commit is contained in:
Krrish Dholakia 2024-02-06 07:22:54 -08:00
parent 47bed68c7f
commit 2e3748e6eb
2 changed files with 6 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

8
litellm/llms/ollama_chat.py
View file

@ -320,11 +320,15 @@ async def ollama_acompletion(url, data, model_response, encoding, logging_obj):
model_response["choices"][0]["message"] = message
else:
model_response["choices"][0]["message"] = response_json["message"]
model_response["created"] = int(time.time())
model_response["model"] = "ollama/" + data["model"]
model_response["model"] = "ollama_chat/" + data["model"]
prompt_tokens = response_json.get("prompt_eval_count", litellm.token_counter(messages=data["messages"])) # type: ignore
completion_tokens = response_json.get(
"eval_count", litellm.token_counter(text=response_json["message"])
"eval_count",
litellm.token_counter(
text=response_json["message"]["content"], count_response_tokens=True
),
)
model_response["usage"] = litellm.Usage(
prompt_tokens=prompt_tokens,