phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 11:43:54 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(ollama_chat.py): use tiktoken as backup for prompt token counting

Browse source
This commit is contained in:
puffo 2024-01-18 10:47:24 -06:00
parent 58ba7fa1b2
commit d451aaca0c
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
litellm/llms/ollama_chat.py
View file

@ -220,7 +220,7 @@ def get_ollama_response(
model_response["choices"][0]["message"] = response_json["message"]
model_response["created"] = int(time.time())
model_response["model"] = "ollama/" + model
prompt_tokens = response_json["prompt_eval_count"] # type: ignore
prompt_tokens = response_json.get("prompt_eval_count", len(encoding.encode(prompt))) # type: ignore
completion_tokens = response_json["eval_count"]
model_response["usage"] = litellm.Usage(
prompt_tokens=prompt_tokens,
@ -320,7 +320,7 @@ async def ollama_acompletion(url, data, model_response, encoding, logging_obj):
model_response["choices"][0]["message"] = response_json["message"]
model_response["created"] = int(time.time())
model_response["model"] = "ollama/" + data["model"]
prompt_tokens = response_json["prompt_eval_count"] # type: ignore
prompt_tokens = response_json.get("prompt_eval_count", len(encoding.encode(prompt))) # type: ignore
completion_tokens = response_json["eval_count"]
model_response["usage"] = litellm.Usage(
prompt_tokens=prompt_tokens,