scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-23 00:41:40 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 81

created defaults for response["eval_count"]

Browse source 
there is no way in litellm to disable the cache in ollama that is removing the eval_count response keys from the json.
This PR allows the code to create sensible defaults for when the response is empty
see 
- https://github.com/ollama/ollama/issues/1573
- https://github.com/ollama/ollama/issues/2023
This commit is contained in:
Gregory Nwosu 2024-04-08 02:03:54 +01:00 • committed by GitHub
parent b4b882c5d6
commit 559a4cde23
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
litellm/llms/ollama.py
View file

@ -229,7 +229,7 @@ def get_ollama_response(
model_response["created"] = int(time.time())
model_response["model"] = "ollama/" + model
prompt_tokens = response_json.get("prompt_eval_count", len(encoding.encode(prompt))) # type: ignore
completion_tokens = response_json["eval_count"]
completion_tokens = response_json.get("eval_count", len(response_json.get("message",dict()).get("content", "")))
model_response["usage"] = litellm.Usage(
prompt_tokens=prompt_tokens,
completion_tokens=completion_tokens,
@ -331,7 +331,7 @@ async def ollama_acompletion(url, data, model_response, encoding, logging_obj):
model_response["created"] = int(time.time())
model_response["model"] = "ollama/" + data["model"]
prompt_tokens = response_json.get("prompt_eval_count", len(encoding.encode(data["prompt"]))) # type: ignore
completion_tokens = response_json["eval_count"]
completion_tokens = response_json.get("eval_count", len(response_json.get("message",dict()).get("content", "")))
model_response["usage"] = litellm.Usage(
prompt_tokens=prompt_tokens,
completion_tokens=completion_tokens,