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

Merge branch 'BerriAI:main' into ollama-image-handling

Browse source
This commit is contained in:
frob 2024-04-21 01:49:10 +02:00 • committed by GitHub
commit b986fbfa13
53 changed files with 1198 additions and 694 deletions
Download patch file Download diff file Expand all files Collapse all files

4
litellm/llms/ollama.py
View file

@ -253,7 +253,7 @@ def get_ollama_response(
model_response["choices"][0]["message"]["content"] = response_json["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
prompt_tokens = response_json.get("prompt_eval_count", len(encoding.encode(prompt, disallowed_special=()))) # type: ignore
completion_tokens = response_json.get("eval_count", len(response_json.get("message",dict()).get("content", "")))
model_response["usage"] = litellm.Usage(
prompt_tokens=prompt_tokens,
@ -355,7 +355,7 @@ 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
prompt_tokens = response_json.get("prompt_eval_count", len(encoding.encode(data["prompt"], disallowed_special=()))) # type: ignore
completion_tokens = response_json.get("eval_count", len(response_json.get("message",dict()).get("content", "")))
model_response["usage"] = litellm.Usage(
prompt_tokens=prompt_tokens,