structure saas with tools

.venv/lib/python3.10/site-packages/litellm/anthropic_interface/__init__.py

@@ -0,0 +1,6 @@
+"""
+Anthropic module for LiteLLM
+"""
+from .messages import acreate, create
+
+__all__ = ["acreate", "create"]

.venv/lib/python3.10/site-packages/litellm/anthropic_interface/messages/__init__.py

@@ -0,0 +1,117 @@
+"""
+Interface for Anthropic's messages API
+
+Use this to call LLMs in Anthropic /messages Request/Response format
+
+This is an __init__.py file to allow the following interface
+
+- litellm.messages.acreate
+- litellm.messages.create
+
+"""
+
+from typing import AsyncIterator, Dict, Iterator, List, Optional, Union
+
+from litellm.llms.anthropic.experimental_pass_through.messages.handler import (
+    anthropic_messages as _async_anthropic_messages,
+)
+from litellm.types.llms.anthropic_messages.anthropic_response import (
+    AnthropicMessagesResponse,
+)
+
+
+async def acreate(
+    max_tokens: int,
+    messages: List[Dict],
+    model: str,
+    metadata: Optional[Dict] = None,
+    stop_sequences: Optional[List[str]] = None,
+    stream: Optional[bool] = False,
+    system: Optional[str] = None,
+    temperature: Optional[float] = 1.0,
+    thinking: Optional[Dict] = None,
+    tool_choice: Optional[Dict] = None,
+    tools: Optional[List[Dict]] = None,
+    top_k: Optional[int] = None,
+    top_p: Optional[float] = None,
+    **kwargs
+) -> Union[AnthropicMessagesResponse, AsyncIterator]:
+    """
+    Async wrapper for Anthropic's messages API
+
+    Args:
+        max_tokens (int): Maximum tokens to generate (required)
+        messages (List[Dict]): List of message objects with role and content (required)
+        model (str): Model name to use (required)
+        metadata (Dict, optional): Request metadata
+        stop_sequences (List[str], optional): Custom stop sequences
+        stream (bool, optional): Whether to stream the response
+        system (str, optional): System prompt
+        temperature (float, optional): Sampling temperature (0.0 to 1.0)
+        thinking (Dict, optional): Extended thinking configuration
+        tool_choice (Dict, optional): Tool choice configuration
+        tools (List[Dict], optional): List of tool definitions
+        top_k (int, optional): Top K sampling parameter
+        top_p (float, optional): Nucleus sampling parameter
+        **kwargs: Additional arguments
+
+    Returns:
+        Dict: Response from the API
+    """
+    return await _async_anthropic_messages(
+        max_tokens=max_tokens,
+        messages=messages,
+        model=model,
+        metadata=metadata,
+        stop_sequences=stop_sequences,
+        stream=stream,
+        system=system,
+        temperature=temperature,
+        thinking=thinking,
+        tool_choice=tool_choice,
+        tools=tools,
+        top_k=top_k,
+        top_p=top_p,
+        **kwargs,
+    )
+
+
+async def create(
+    max_tokens: int,
+    messages: List[Dict],
+    model: str,
+    metadata: Optional[Dict] = None,
+    stop_sequences: Optional[List[str]] = None,
+    stream: Optional[bool] = False,
+    system: Optional[str] = None,
+    temperature: Optional[float] = 1.0,
+    thinking: Optional[Dict] = None,
+    tool_choice: Optional[Dict] = None,
+    tools: Optional[List[Dict]] = None,
+    top_k: Optional[int] = None,
+    top_p: Optional[float] = None,
+    **kwargs
+) -> Union[AnthropicMessagesResponse, Iterator]:
+    """
+    Async wrapper for Anthropic's messages API
+
+    Args:
+        max_tokens (int): Maximum tokens to generate (required)
+        messages (List[Dict]): List of message objects with role and content (required)
+        model (str): Model name to use (required)
+        metadata (Dict, optional): Request metadata
+        stop_sequences (List[str], optional): Custom stop sequences
+        stream (bool, optional): Whether to stream the response
+        system (str, optional): System prompt
+        temperature (float, optional): Sampling temperature (0.0 to 1.0)
+        thinking (Dict, optional): Extended thinking configuration
+        tool_choice (Dict, optional): Tool choice configuration
+        tools (List[Dict], optional): List of tool definitions
+        top_k (int, optional): Top K sampling parameter
+        top_p (float, optional): Nucleus sampling parameter
+        **kwargs: Additional arguments
+
+    Returns:
+        Dict: Response from the API
+    """
+    raise NotImplementedError("This function is not implemented")

.venv/lib/python3.10/site-packages/litellm/anthropic_interface/readme.md

@@ -0,0 +1,116 @@
+## Use LLM API endpoints in Anthropic Interface
+
+Note: This is called `anthropic_interface` because `anthropic` is a known python package and was failing mypy type checking.
+
+
+## Usage 
+---
+
+### LiteLLM Python SDK 
+
+#### Non-streaming example
+```python showLineNumbers title="Example using LiteLLM Python SDK"
+import litellm
+response = await litellm.anthropic.messages.acreate(
+    messages=[{"role": "user", "content": "Hello, can you tell me a short joke?"}],
+    api_key=api_key,
+    model="anthropic/claude-3-haiku-20240307",
+    max_tokens=100,
+)
+```
+
+Example response:
+```json
+{
+  "content": [
+    {
+      "text": "Hi! this is a very short joke",
+      "type": "text"
+    }
+  ],
+  "id": "msg_013Zva2CMHLNnXjNJJKqJ2EF",
+  "model": "claude-3-7-sonnet-20250219",
+  "role": "assistant",
+  "stop_reason": "end_turn",
+  "stop_sequence": null,
+  "type": "message",
+  "usage": {
+    "input_tokens": 2095,
+    "output_tokens": 503,
+    "cache_creation_input_tokens": 2095,
+    "cache_read_input_tokens": 0
+  }
+}
+```
+
+#### Streaming example
+```python showLineNumbers title="Example using LiteLLM Python SDK"
+import litellm
+response = await litellm.anthropic.messages.acreate(
+    messages=[{"role": "user", "content": "Hello, can you tell me a short joke?"}],
+    api_key=api_key,
+    model="anthropic/claude-3-haiku-20240307",
+    max_tokens=100,
+    stream=True,
+)
+async for chunk in response:
+    print(chunk)
+```
+
+### LiteLLM Proxy Server 
+
+
+1. Setup config.yaml
+
+```yaml
+model_list:
+    - model_name: anthropic-claude
+      litellm_params:
+        model: claude-3-7-sonnet-latest
+```
+
+2. Start proxy 
+
+```bash
+litellm --config /path/to/config.yaml
+```
+
+3. Test it! 
+
+<Tabs>
+<TabItem label="Anthropic Python SDK" value="python">
+
+```python showLineNumbers title="Example using LiteLLM Proxy Server"
+import anthropic
+
+# point anthropic sdk to litellm proxy 
+client = anthropic.Anthropic(
+    base_url="http://0.0.0.0:4000",
+    api_key="sk-1234",
+)
+
+response = client.messages.create(
+    messages=[{"role": "user", "content": "Hello, can you tell me a short joke?"}],
+    model="anthropic/claude-3-haiku-20240307",
+    max_tokens=100,
+)
+```
+</TabItem>
+<TabItem label="curl" value="curl">
+
+```bash showLineNumbers title="Example using LiteLLM Proxy Server"
+curl -L -X POST 'http://0.0.0.0:4000/v1/messages' \
+-H 'content-type: application/json' \
+-H 'x-api-key: $LITELLM_API_KEY' \
+-H 'anthropic-version: 2023-06-01' \
+-d '{
+  "model": "anthropic-claude",
+  "messages": [
+    {
+      "role": "user",
+      "content": "Hello, can you tell me a short joke?"
+    }
+  ],
+  "max_tokens": 100
+}'
+```