phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 03:04:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

map finish reason

Browse source
This commit is contained in:
Krrish Dholakia 2023-09-13 19:22:38 -07:00
parent 1b346e0139
commit aaa57abddd
10 changed files with 64 additions and 56 deletions
Download patch file Download diff file Expand all files Collapse all files

9
litellm/llms/together_ai.py
View file

@ -104,14 +104,17 @@ def completion(
message=json.dumps(completion_response["output"]), status_code=response.status_code
)
completion_response = completion_response["output"]["choices"][0]["text"]
print(completion_response)
completion_text = completion_response["output"]["choices"][0]["text"]
## CALCULATING USAGE - baseten charges on time, not tokens - have some mapping of cost here.
prompt_tokens = len(encoding.encode(prompt))
completion_tokens = len(
encoding.encode(completion_response)
encoding.encode(completion_text)
)
model_response["choices"][0]["message"]["content"] = completion_response
model_response["choices"][0]["message"]["content"] = completion_text
if "finish_reason" in completion_response["output"]["choices"][0]:
model_response.choices[0].finish_reason = completion_response["output"]["choices"][0]["finish_reason"]
model_response["created"] = time.time()
model_response["model"] = model
model_response["usage"] = {