fix(factory.py): support image url requests for anthropic

litellm/llms/prompt_templates/factory.py

@@ -2,7 +2,7 @@ from enum import Enum
 import requests, traceback
 import json, re, xml.etree.ElementTree as ET
 from jinja2 import Template, exceptions, Environment, meta
-from typing import Optional, Any, List
+from typing import Optional, Any
 import imghdr, base64
 
 
@@ -481,6 +481,34 @@ def construct_tool_use_system_prompt(
     return tool_use_system_prompt
 
 
+def convert_url_to_base64(url):
+    import requests
+    import base64
+
+    response = requests.get(url)
+    if response.status_code == 200:
+        image_bytes = response.content
+        base64_image = base64.b64encode(image_bytes).decode("utf-8")
+
+        img_type = url.split(".")[-1].lower()
+        if img_type == "jpg" or img_type == "jpeg":
+            img_type = "image/jpeg"
+        elif img_type == "png":
+            img_type = "image/png"
+        elif img_type == "gif":
+            img_type = "image/gif"
+        elif img_type == "webp":
+            img_type = "image/webp"
+        else:
+            raise Exception(
+                f"Error: Unsupported image format. Format={img_type}. Supported types = ['image/jpeg', 'image/png', 'image/gif', 'image/webp']"
+            )
+
+        return f"data:{img_type};base64,{base64_image}"
+    else:
+        raise Exception(f"Error: Unable to fetch image from URL. url={url}")
+
+
 def convert_to_anthropic_image_obj(openai_image_url: str):
     """
     Input:
@@ -493,6 +521,9 @@ def convert_to_anthropic_image_obj(openai_image_url: str):
       "data": {base64_image},
     }
     """
+    try:
+        if openai_image_url.startswith("http"):
+            openai_image_url = convert_url_to_base64(url=openai_image_url)
         # Extract the base64 image data
         base64_data = openai_image_url.split("data:image/")[1].split(";base64,")[1]
 
@@ -504,6 +535,10 @@ def convert_to_anthropic_image_obj(openai_image_url: str):
             "media_type": f"image/{image_format}",
             "data": base64_data,
         }
+    except Exception as e:
+        raise Exception(
+            """Image url not in expected format. Example Expected input - "image_url": "data:image/jpeg;base64,{base64_image}". Supported formats - ['image/jpeg', 'image/png', 'image/gif', 'image/webp'] """
+        )
 
 
 def anthropic_messages_pt(messages: list):
@@ -586,7 +621,7 @@ def anthropic_messages_pt(messages: list):
     return new_messages
 
 
-def extract_between_tags(tag: str, string: str, strip: bool = False) -> List[str]:
+def extract_between_tags(tag: str, string: str, strip: bool = False) -> list[str]:
     ext_list = re.findall(f"<{tag}>(.+?)</{tag}>", string, re.DOTALL)
     if strip:
         ext_list = [e.strip() for e in ext_list]

litellm/tests/test_completion.py

@@ -151,8 +151,6 @@ def test_completion_claude_3_function_call():
         assert isinstance(
             response.choices[0].message.tool_calls[0].function.arguments, str
         )
-    except litellm.ServiceUnavailableError as e:
-        pass
     except Exception as e:
         pytest.fail(f"Error occurred: {e}")
 
@@ -221,6 +219,55 @@ def test_completion_claude_3_base64():
             pytest.fail(f"An exception occurred - {str(e)}")
 
 
+def test_completion_claude_3_function_plus_image():
+    litellm.set_verbose = True
+
+    image_content = [
+        {"type": "text", "text": "What’s in this image?"},
+        {
+            "type": "image_url",
+            "image_url": {
+                "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
+            },
+        },
+    ]
+    image_message = {"role": "user", "content": image_content}
+
+    tools = [
+        {
+            "type": "function",
+            "function": {
+                "name": "get_current_weather",
+                "description": "Get the current weather in a given location",
+                "parameters": {
+                    "type": "object",
+                    "properties": {
+                        "location": {
+                            "type": "text",
+                            "description": "The city and state, e.g. San Francisco, CA",
+                        },
+                        "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
+                    },
+                    "required": ["location"],
+                },
+            },
+        }
+    ]
+
+    tool_choice = {"type": "function", "function": {"name": "get_current_weather"}}
+    messages = [{"role": "user", "content": "What's the weather like in Boston today?"}]
+
+    response = completion(
+        model="claude-3-sonnet-20240229",
+        messages=[image_message],
+        tool_choice=tool_choice,
+        tools=tools,
+        stream=False,
+    )
+
+    print(response)
+
+
 def test_completion_mistral_api():
     try:
         litellm.set_verbose = True
@@ -1406,9 +1453,9 @@ def test_completion_replicate_vicuna():
 
 def test_replicate_custom_prompt_dict():
     litellm.set_verbose = True
-    model_name = "replicate/mistralai/mixtral-8x7b-instruct-v0.1"
+    model_name = "replicate/meta/llama-2-7b-chat:13c3cdee13ee059ab779f0291d29054dab00a47dad8261375654de5540165fb0"
     litellm.register_prompt_template(
-        model="replicate/mistralai/mixtral-8x7b-instruct-v0.1",
+        model="replicate/meta/llama-2-7b-chat:13c3cdee13ee059ab779f0291d29054dab00a47dad8261375654de5540165fb0",
         initial_prompt_value="You are a good assistant",  # [OPTIONAL]
         roles={
             "system": {