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 anthropic streaming

Browse source
This commit is contained in:
Krrish Dholakia 2023-08-26 18:54:49 -07:00
parent 45b984cb79
commit 0ac17646d9
4 changed files with 66 additions and 58 deletions
Download patch file Download diff file Expand all files Collapse all files

BIN
litellm/__pycache__/main.cpython-311.pyc
View file

Binary file not shown.

BIN
litellm/__pycache__/utils.cpython-311.pyc
View file

Binary file not shown.

9
litellm/llms/anthropic.py
View file

@ -92,12 +92,15 @@ class AnthropicLLM:
additional_args={"complete_input_dict": data},
)
## COMPLETION CALL
response = requests.post(
self.completion_url, headers=self.headers, data=json.dumps(data)
)
if "stream" in optional_params and optional_params["stream"] == True:
response = requests.post(
self.completion_url, headers=self.headers, data=json.dumps(data), stream=optional_params["stream"]
)
return response.iter_lines()
else:
response = requests.post(
self.completion_url, headers=self.headers, data=json.dumps(data)
)
## LOGGING
self.logging_obj.post_call(
input=prompt,

115
litellm/tests/test_streaming.py
View file

@ -24,41 +24,41 @@ user_message = "Hello, how are you?"
messages = [{"content": user_message, "role": "user"}]
# test on openai completion call
try:
response = completion(
model="gpt-3.5-turbo", messages=messages, stream=True, logger_fn=logger_fn
)
response = ""
start_time = time.time()
for chunk in response:
chunk_time = time.time()
print(f"time since initial request: {chunk_time - start_time:.2f}")
print(chunk["choices"][0]["delta"])
response += chunk["choices"][0]["delta"]
if response == "":
raise Exception("Empty response received")
except:
print(f"error occurred: {traceback.format_exc()}")
pass
# try:
# response = completion(
# model="gpt-3.5-turbo", messages=messages, stream=True, logger_fn=logger_fn
# )
# complete_response = ""
# start_time = time.time()
# for chunk in response:
# chunk_time = time.time()
# print(f"time since initial request: {chunk_time - start_time:.5f}")
# print(chunk["choices"][0]["delta"])
# complete_response += chunk["choices"][0]["delta"]["content"]
# if complete_response == "":
# raise Exception("Empty response received")
# except:
# print(f"error occurred: {traceback.format_exc()}")
# pass
# test on azure completion call
try:
response = completion(
model="azure/chatgpt-test", messages=messages, stream=True, logger_fn=logger_fn
)
response = ""
start_time = time.time()
for chunk in response:
chunk_time = time.time()
print(f"time since initial request: {chunk_time - start_time:.2f}")
print(chunk["choices"][0]["delta"])
response += chunk["choices"][0]["delta"]
if response == "":
raise Exception("Empty response received")
except:
print(f"error occurred: {traceback.format_exc()}")
pass
# # test on azure completion call
# try:
# response = completion(
# model="azure/chatgpt-test", messages=messages, stream=True, logger_fn=logger_fn
# )
# response = ""
# start_time = time.time()
# for chunk in response:
# chunk_time = time.time()
# print(f"time since initial request: {chunk_time - start_time:.2f}")
# print(chunk["choices"][0]["delta"])
# response += chunk["choices"][0]["delta"]
# if response == "":
# raise Exception("Empty response received")
# except:
# print(f"error occurred: {traceback.format_exc()}")
# pass
# test on anthropic completion call
@ -66,15 +66,20 @@ try:
response = completion(
model="claude-instant-1", messages=messages, stream=True, logger_fn=logger_fn
)
response = ""
complete_response = ""
start_time = time.time()
time_since_initial_request = []
for chunk in response:
chunk_time = time.time()
print(f"time since initial request: {chunk_time - start_time:.2f}")
chunk_time = time.time()
time_since_initial_request.append(chunk_time - start_time)
print(f"time since initial request: {chunk_time - start_time:.5f}")
print(chunk["choices"][0]["delta"])
response += chunk["choices"][0]["delta"]
if response == "":
complete_response += chunk["choices"][0]["delta"]["content"]
if complete_response == "":
raise Exception("Empty response received")
print(f"set(time_since_initial_request): {set(time_since_initial_request)}")
if len(set(time_since_initial_request)) == 1:
raise Exception("All time since initial request is the same")
except:
print(f"error occurred: {traceback.format_exc()}")
pass
@ -99,23 +104,23 @@ except:
# pass
# test on together ai completion call
try:
start_time = time.time()
response = completion(
model="Replit-Code-3B", messages=messages, logger_fn=logger_fn, stream= True
)
complete_response = ""
print(f"returned response object: {response}")
for chunk in response:
chunk_time = time.time()
print(f"time since initial request: {chunk_time - start_time:.2f}")
print(chunk["choices"][0]["delta"])
complete_response += chunk["choices"][0]["delta"]["content"] if len(chunk["choices"][0]["delta"].keys()) > 0 else ""
if complete_response == "":
raise Exception("Empty response received")
except:
print(f"error occurred: {traceback.format_exc()}")
pass
# try:
# start_time = time.time()
# response = completion(
# model="Replit-Code-3B", messages=messages, logger_fn=logger_fn, stream= True
# )
# complete_response = ""
# print(f"returned response object: {response}")
# for chunk in response:
# chunk_time = time.time()
# print(f"time since initial request: {chunk_time - start_time:.2f}")
# print(chunk["choices"][0]["delta"])
# complete_response += chunk["choices"][0]["delta"]["content"] if len(chunk["choices"][0]["delta"].keys()) > 0 else ""
# if complete_response == "":
# raise Exception("Empty response received")
# except:
# print(f"error occurred: {traceback.format_exc()}")
# pass
# # test on azure completion call