LITELLM: Remove requests library usage (#7235)

* 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

litellm/main.py

@@ -2645,45 +2645,24 @@ def completion(  # type: ignore # noqa: PLR0915
                 or get_secret("OLLAMA_API_BASE")
                 or "http://localhost:11434"
             )
-            custom_prompt_dict = custom_prompt_dict or litellm.custom_prompt_dict
-            if model in custom_prompt_dict:
-                # check if the model has a registered custom prompt
-                model_prompt_details = custom_prompt_dict[model]
-                ollama_prompt = custom_prompt(
-                    role_dict=model_prompt_details["roles"],
-                    initial_prompt_value=model_prompt_details["initial_prompt_value"],
-                    final_prompt_value=model_prompt_details["final_prompt_value"],
-                    messages=messages,
-                )
-            else:
-                modified_prompt = ollama_pt(model=model, messages=messages)
-                if isinstance(modified_prompt, dict):
-                    # for multimode models - ollama/llava prompt_factory returns a dict {
-                    #     "prompt": prompt,
-                    #     "images": images
-                    # }
-                    ollama_prompt, images = (
-                        modified_prompt["prompt"],
-                        modified_prompt["images"],
-                    )
-                    optional_params["images"] = images
-                else:
-                    ollama_prompt = modified_prompt
-            ## LOGGING
-            generator = ollama.get_ollama_response(
-                api_base=api_base,
+            response = base_llm_http_handler.completion(
                 model=model,
-                prompt=ollama_prompt,
-                optional_params=optional_params,
-                logging_obj=logging,
+                stream=stream,
+                messages=messages,
                 acompletion=acompletion,
+                api_base=api_base,
                 model_response=model_response,
+                optional_params=optional_params,
+                litellm_params=litellm_params,
+                custom_llm_provider="ollama",
+                timeout=timeout,
+                headers=headers,
                 encoding=encoding,
+                api_key=api_key,
+                logging_obj=logging,  # model call logging done inside the class as we make need to modify I/O to fit aleph alpha's requirements
+                client=client,
             )
-            if acompletion is True or optional_params.get("stream", False) is True:
-                return generator
 
-            response = generator
         elif custom_llm_provider == "ollama_chat":
             api_base = (
                 litellm.api_base
@@ -2833,8 +2812,6 @@ def completion(  # type: ignore # noqa: PLR0915
                 return response
             response = model_response
         elif custom_llm_provider == "custom":
-            import requests
-
             url = litellm.api_base or api_base or ""
             if url is None or url == "":
                 raise ValueError(
@@ -2843,7 +2820,7 @@ def completion(  # type: ignore # noqa: PLR0915
 
             """
             assume input to custom LLM api bases follow this format:
-            resp = requests.post(
+            resp = litellm.module_level_client.post(
                 api_base,
                 json={
                     'model': 'meta-llama/Llama-2-13b-hf', # model name
@@ -2859,7 +2836,7 @@ def completion(  # type: ignore # noqa: PLR0915
 
             """
             prompt = " ".join([message["content"] for message in messages])  # type: ignore
-            resp = requests.post(
+            resp = litellm.module_level_client.post(
                 url,
                 json={
                     "model": model,
@@ -2871,7 +2848,6 @@ def completion(  # type: ignore # noqa: PLR0915
                         "top_k": kwargs.get("top_k", 40),
                     },
                 },
-                verify=litellm.ssl_verify,
             )
             response_json = resp.json()
             """