phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-24 18:24:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

(fix) pydantic errors with response.time

Browse source
This commit is contained in:
ishaan-jaff 2023-11-20 18:28:17 -08:00
parent 3f30f93516
commit 50f883a2fb
18 changed files with 22 additions and 22 deletions
Download patch file Download diff file Expand all files Collapse all files

2
litellm/llms/ai21.py
View file

@ -180,7 +180,7 @@ def completion(
encoding.encode(model_response["choices"][0]["message"].get("content"))
)
model_response["created"] = time.time()
model_response["created"] = int(time.time())
model_response["model"] = model
model_response["usage"] = {
"prompt_tokens": prompt_tokens,

2
litellm/llms/aleph_alpha.py
View file

@ -263,7 +263,7 @@ def completion(
encoding.encode(model_response["choices"][0]["message"]["content"])
)
model_response["created"] = time.time()
model_response["created"] = int(time.time())
model_response["model"] = model
usage = Usage(
prompt_tokens=prompt_tokens,

2
litellm/llms/anthropic.py
View file

@ -172,7 +172,7 @@ def completion(
encoding.encode(model_response["choices"][0]["message"].get("content", ""))
) ##[TODO] use the anthropic tokenizer here
model_response["created"] = time.time()
model_response["created"] = int(time.time())
model_response["model"] = model
usage = Usage(
prompt_tokens=prompt_tokens,

2
litellm/llms/baseten.py
View file

@ -134,7 +134,7 @@ def completion(
encoding.encode(model_response["choices"][0]["message"]["content"])
)
model_response["created"] = time.time()
model_response["created"] = int(time.time())
model_response["model"] = model
usage = Usage(
prompt_tokens=prompt_tokens,

2
litellm/llms/bedrock.py
View file

@ -464,7 +464,7 @@ def completion(
encoding.encode(model_response["choices"][0]["message"].get("content", ""))
)
model_response["created"] = time.time()
model_response["created"] = int(time.time())
model_response["model"] = model
usage = Usage(
prompt_tokens=prompt_tokens,

2
litellm/llms/cohere.py
View file

@ -184,7 +184,7 @@ def completion(
encoding.encode(model_response["choices"][0]["message"].get("content", ""))
)
model_response["created"] = time.time()
model_response["created"] = int(time.time())
model_response["model"] = model
usage = Usage(
prompt_tokens=prompt_tokens,

2
litellm/llms/huggingface_restapi.py
View file

@ -224,7 +224,7 @@ class Huggingface(BaseLLM):
else:
completion_tokens = 0
model_response["created"] = time.time()
model_response["created"] = int(time.time())
model_response["model"] = model
usage = Usage(
prompt_tokens=prompt_tokens,

2
litellm/llms/maritalk.py
View file

@ -143,7 +143,7 @@ def completion(
encoding.encode(model_response["choices"][0]["message"].get("content", ""))
)
model_response["created"] = time.time()
model_response["created"] = int(time.time())
model_response["model"] = model
usage = Usage(
prompt_tokens=prompt_tokens,

2
litellm/llms/nlp_cloud.py
View file

@ -169,7 +169,7 @@ def completion(
prompt_tokens = completion_response["nb_input_tokens"]
completion_tokens = completion_response["nb_generated_tokens"]
model_response["created"] = time.time()
model_response["created"] = int(time.time())
model_response["model"] = model
usage = Usage(
prompt_tokens=prompt_tokens,

2
litellm/llms/oobabooga.py
View file

@ -109,7 +109,7 @@ def completion(
encoding.encode(model_response["choices"][0]["message"]["content"])
)
model_response["created"] = time.time()
model_response["created"] = int(time.time())
model_response["model"] = model
usage = Usage(
prompt_tokens=prompt_tokens,

2
litellm/llms/palm.py
View file

@ -162,7 +162,7 @@ def completion(
encoding.encode(model_response["choices"][0]["message"].get("content", ""))
)
model_response["created"] = time.time()
model_response["created"] = int(time.time())
model_response["model"] = "palm/" + model
usage = Usage(
prompt_tokens=prompt_tokens,

2
litellm/llms/petals.py
View file

@ -174,7 +174,7 @@ def completion(
encoding.encode(model_response["choices"][0]["message"].get("content"))
)
model_response["created"] = time.time()
model_response["created"] = int(time.time())
model_response["model"] = model
usage = Usage(
prompt_tokens=prompt_tokens,

2
litellm/llms/replicate.py
View file

@ -229,7 +229,7 @@ def completion(
## Step1: Start Prediction: gets a prediction url
## Step2: Poll prediction url for response
## Step2: is handled with and without streaming
model_response["created"] = time.time() # for pricing this must remain right before calling api
model_response["created"] = int(time.time()) # for pricing this must remain right before calling api
prediction_url = start_prediction(version_id, input_data, api_key, api_base, logging_obj=logging_obj, print_verbose=print_verbose)
print_verbose(prediction_url)

2
litellm/llms/sagemaker.py
View file

@ -170,7 +170,7 @@ def completion(
encoding.encode(model_response["choices"][0]["message"].get("content", ""))
)
model_response["created"] = time.time()
model_response["created"] = int(time.time())
model_response["model"] = model
usage = Usage(
prompt_tokens=prompt_tokens,

2
litellm/llms/together_ai.py
View file

@ -183,7 +183,7 @@ def completion(
)
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["created"] = int(time.time())
model_response["model"] = model
usage = Usage(
prompt_tokens=prompt_tokens,

2
litellm/llms/vertex_ai.py
View file

@ -144,7 +144,7 @@ def completion(
"content"
] = str(completion_response)
model_response["choices"][0]["message"]["content"] = str(completion_response)
model_response["created"] = time.time()
model_response["created"] = int(time.time())
model_response["model"] = model
## CALCULATING USAGE
prompt_tokens = len(

4
litellm/llms/vllm.py
View file

@ -90,7 +90,7 @@ def completion(
prompt_tokens = len(outputs[0].prompt_token_ids)
completion_tokens = len(outputs[0].outputs[0].token_ids)
model_response["created"] = time.time()
model_response["created"] = int(time.time())
model_response["model"] = model
usage = Usage(
prompt_tokens=prompt_tokens,
@ -173,7 +173,7 @@ def batch_completions(
prompt_tokens = len(output.prompt_token_ids)
completion_tokens = len(output.outputs[0].token_ids)
model_response["created"] = time.time()
model_response["created"] = int(time.time())
model_response["model"] = model
usage = Usage(
prompt_tokens=prompt_tokens,

8
litellm/main.py
View file

@ -228,7 +228,7 @@ def mock_completion(model: str, messages: List, stream: Optional[bool] = False,
return response
model_response["choices"][0]["message"]["content"] = mock_response
model_response["created"] = time.time()
model_response["created"] = int(time.time())
model_response["model"] = model
return model_response
@ -388,7 +388,7 @@ def completion(
api_base = "https://proxy.litellm.ai"
custom_llm_provider = "openai"
api_key = model_api_key
# check if user passed in any of the OpenAI optional params
optional_params = get_optional_params(
functions=functions,
@ -1245,7 +1245,7 @@ def completion(
## RESPONSE OBJECT
model_response["choices"][0]["message"]["content"] = response_string
model_response["created"] = time.time()
model_response["created"] = int(time.time())
model_response["model"] = "ollama/" + model
prompt_tokens = len(encoding.encode(prompt)) # type: ignore
completion_tokens = len(encoding.encode(response_string))
@ -1371,7 +1371,7 @@ def completion(
string_response = response_json['data'][0]['output'][0]
## RESPONSE OBJECT
model_response["choices"][0]["message"]["content"] = string_response
model_response["created"] = time.time()
model_response["created"] = int(time.time())
model_response["model"] = model
response = model_response
else: