phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 03:34:10 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

LITELLM: Remove requests library usage (#7235)

Browse source 
* fix(generic_api_callback.py): remove requests lib usage

* fix(budget_manager.py): remove requests lib usgae

* fix(main.py): cleanup requests lib usage

* fix(utils.py): remove requests lib usage

* fix(argilla.py): fix argilla test

* fix(athina.py): replace 'requests' lib usage with litellm module

* fix(greenscale.py): replace 'requests' lib usage with httpx

* fix: remove unused 'requests' lib import + replace usage in some places

* fix(prompt_layer.py): remove 'requests' lib usage from prompt layer

* fix(ollama_chat.py): remove 'requests' lib usage

* fix(baseten.py): replace 'requests' lib usage

* fix(codestral/): replace 'requests' lib usage

* fix(predibase/): replace 'requests' lib usage

* refactor: cleanup unused 'requests' lib imports

* fix(oobabooga.py): cleanup 'requests' lib usage

* fix(invoke_handler.py): remove unused 'requests' lib usage

* refactor: cleanup unused 'requests' lib import

* fix: fix linting errors

* refactor(ollama/): move ollama to using base llm http handler

removes 'requests' lib dep for ollama integration

* fix(ollama_chat.py): fix linting errors

* fix(ollama/completion/transformation.py): convert non-jpeg/png image to jpeg/png before passing to ollama
This commit is contained in:
Krish Dholakia 2024-12-17 12:50:04 -08:00 • committed by GitHub
parent f628290ce7
commit 03e711e3e4
46 changed files with 523 additions and 612 deletions
Download patch file Download diff file Expand all files Collapse all files

40
litellm/litellm_core_utils/streaming_handler.py
View file

@ -570,40 +570,6 @@ class CustomStreamWrapper:
)
return ""
def handle_ollama_stream(self, chunk):
try:
if isinstance(chunk, dict):
json_chunk = chunk
else:
json_chunk = json.loads(chunk)
if "error" in json_chunk:
raise Exception(f"Ollama Error - {json_chunk}")
text = ""
is_finished = False
finish_reason = None
if json_chunk["done"] is True:
text = ""
is_finished = True
finish_reason = "stop"
return {
"text": text,
"is_finished": is_finished,
"finish_reason": finish_reason,
}
elif json_chunk["response"]:
print_verbose(f"delta content: {json_chunk}")
text = json_chunk["response"]
return {
"text": text,
"is_finished": is_finished,
"finish_reason": finish_reason,
}
else:
raise Exception(f"Ollama Error - {json_chunk}")
except Exception as e:
raise e
def handle_ollama_chat_stream(self, chunk):
# for ollama_chat/ provider
try:
@ -1111,12 +1077,6 @@ class CustomStreamWrapper:
new_chunk = self.completion_stream[:chunk_size]
completion_obj["content"] = new_chunk
self.completion_stream = self.completion_stream[chunk_size:]
elif self.custom_llm_provider == "ollama":
response_obj = self.handle_ollama_stream(chunk)
completion_obj["content"] = response_obj["text"]
print_verbose(f"completion obj content: {completion_obj['content']}")
if response_obj["is_finished"]:
self.received_finish_reason = response_obj["finish_reason"]
elif self.custom_llm_provider == "ollama_chat":
response_obj = self.handle_ollama_chat_stream(chunk)
completion_obj["content"] = response_obj["text"]