Claudette Tool Use With image being returned

claudette_image.py

#!/usr/bin/env python3

import inspect
import logging
import os

os.environ["ANTHROPIC_LOG"] = "debug"

from pathlib import Path
from typing import Optional

import claudette.core
import toolslm.funccall
from claudette import Chat, contents
from claudette.core import ToolUseBlock, _mk_ns, abc, img_msg
from fastcore.utils import patch_to

empty = inspect.Parameter.empty


@patch_to(toolslm.funccall)
def _types(t: type) -> tuple[str, Optional[str]]:
    "Tuple of json schema type name and (if appropriate) array item name."
    if t is empty:
        raise TypeError("Missing type")
    tmap = {
        int: "integer",
        float: "number",
        str: "string",
        bool: "boolean",
        list: "array",
        dict: "object",
        # Bytes is assumed to be an image for now
        # We could likely add a better type to indicate this
        bytes: {
            "type": "object",
            "properties": {
                "type": {"type": "string", "enum": ["image"]},
                "source": {
                    "type": "object",
                    "properties": {
                        "type": {"type": "string", "enum": ["base64"]},
                        "media_type": {"type": "string"},
                        "data": {"type": "string"},
                    },
                    "required": ["type", "media_type", "data"],
                },
            },
        },
    }
    if getattr(t, "__origin__", None) in (list, tuple):
        return "array", tmap.get(t.__args__[0], "object")
    else:
        return tmap[t], None


@patch_to(claudette.core)
def call_func(fc: ToolUseBlock, ns: Optional[abc.Mapping] = None, obj: Optional = None):
    "Call the function in the tool response `tr`, using namespace `ns`."
    if ns is None:
        ns = globals()
    if not isinstance(ns, abc.Mapping):
        ns = _mk_ns(*ns)
    func = getattr(obj, fc.name, None)
    if not func:
        func = ns[fc.name]
    res = func(**fc.input)
    if isinstance(res, bytes):
        # If the result is bytes, assume it's an image
        return dict(type="tool_result", tool_use_id=fc.id, content=[img_msg(res)])
    return dict(type="tool_result", tool_use_id=fc.id, content=str(res))


def get_image_of_puppy() -> bytes:
    "Returns an image of a puppy"
    image: Path = Path("samples/puppy.jpeg")
    return image.read_bytes()


def get_object_and_properties() -> dict:
    "Returns a dict with a couple of integer properties called x and y"
    return {"x": 1, "y": 2}


def get_str() -> str:
    "Returns a random string"
    return "foo!"


if __name__ == "__main__":
    logging.basicConfig(level=logging.INFO)

    tools = [get_image_of_puppy, get_object_and_properties, get_str]

    chat = Chat("claude-3-5-sonnet-20240620", tools=tools)
    r = chat.toolloop(
        "Tell me what tools you have access to please, and what you expect each of them to return to you. Then, examine and describe the puppy"
    )
    print(contents(r))

FullLog.txt

[2024-06-24 09:51:28 - httpx:80 - DEBUG] load_ssl_context verify=True cert=None trust_env=True http2=False
[2024-06-24 09:51:28 - httpx:146 - DEBUG] load_verify_locations cafile='blahblah/cacert.pem'
[2024-06-24 09:51:28 - anthropic._base_client:447 - DEBUG] Request options: {'method': 'post', 'url': '/v1/messages', 'timeout': 600, 'files': None, 'json_data': {'max_tokens': 4096, 'messages': [{'role': 'user', 'content': [{'type': 'text', 'text': 'Tell me what tools you have access to please, and what you expect each of them to return to you. Then, examine and describe the puppy'}]}], 'model': 'claude-3-5-sonnet-20240620', 'system': '', 'temperature': 0, 'tools': [{'name': 'get_image_of_puppy', 'description': "Returns an image of a puppy\n\nReturns:\n- type: {'type': 'object', 'properties': {'type': {'type': 'string', 'enum': ['image']}, 'source': {'type': 'object', 'properties': {'type': {'type': 'string', 'enum': ['base64']}, 'media_type': {'type': 'string'}, 'data': {'type': 'string'}}, 'required': ['type', 'media_type', 'data']}}}", 'input_schema': {'type': 'object', 'properties': {}, 'required': []}}, {'name': 'get_object_and_properties', 'description': 'Returns a dict with a couple of integer properties called x and y\n\nReturns:\n- type: object', 'input_schema': {'type': 'object', 'properties': {}, 'required': []}}, {'name': 'get_str', 'description': 'Returns a random string\n\nReturns:\n- type: string', 'input_schema': {'type': 'object', 'properties': {}, 'required': []}}]}}
[2024-06-24 09:51:28 - anthropic._base_client:959 - DEBUG] Sending HTTP Request: POST https://api.anthropic.com/v1/messages
[2024-06-24 09:51:32 - httpx:1026 - INFO] HTTP Request: POST https://api.anthropic.com/v1/messages "HTTP/1.1 200 OK"
[2024-06-24 09:51:32 - anthropic._base_client:998 - DEBUG] HTTP Response: POST https://api.anthropic.com/v1/messages "200 OK" Headers({'date': 'Mon, 24 Jun 2024 14:51:32 GMT', 'content-type': 'application/json', 'transfer-encoding': 'chunked', 'connection': 'keep-alive', 'anthropic-ratelimit-requests-limit': '50', 'anthropic-ratelimit-requests-remaining': '49', 'anthropic-ratelimit-requests-reset': '2024-06-24T14:52:03Z', 'anthropic-ratelimit-tokens-limit': '40000', 'anthropic-ratelimit-tokens-remaining': '39000', 'anthropic-ratelimit-tokens-reset': '2024-06-24T14:52:03Z', 'request-id': 'req_012SiSLg33sPArj64gfHxE2n', 'x-cloud-trace-context': '2898c5f3f55e57927bd57900e680ac1c', 'via': '1.1 google', 'cf-cache-status': 'DYNAMIC', 'server': 'cloudflare', 'cf-ray': '898d8940f8404df4-MCI', 'content-encoding': 'gzip'})
[2024-06-24 09:51:32 - anthropic._base_client:447 - DEBUG] Request options: {'method': 'post', 'url': '/v1/messages', 'timeout': 600, 'files': None, 'json_data': {'max_tokens': 4096, 'messages': [{'role': 'user', 'content': [{'type': 'text', 'text': 'Tell me what tools you have access to please, and what you expect each of them to return to you. Then, examine and describe the puppy'}]}, {'role': 'assistant', 'content': [{'text': "Certainly! I'll first list the tools I have access to and what I expect them to return, then I'll proceed to examine and describe the puppy for you.\n\nTools available:\n\n1. get_image_of_puppy\n   Expected return: An object containing an image of a puppy. The image will be in base64 format with associated media type.\n\n2. get_object_and_properties\n   Expected return: An object with integer properties 'x' and 'y'.\n\n3. get_str\n   Expected return: A random string.\n\nNow, let's examine and describe the puppy using the appropriate tool.", 'type': 'text'}, {'id': 'toolu_01819JdMFmbAdP21jHryKaXo', 'input': {}, 'name': 'get_image_of_puppy', 'type': 'tool_use'}]}, {'role': 'user', 'content': [{'type': 'tool_result', 'tool_use_id': 'toolu_01819JdMFmbAdP21jHryKaXo', 'content': [{'type': 'image', 'source': {'type': 'base64', 'media_type': 'image/jpeg', 'data': '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'}}]}]}], 'model': 'claude-3-5-sonnet-20240620', 'system': '', 'temperature': 0, 'tools': [{'name': 'get_image_of_puppy', 'description': "Returns an image of a puppy\n\nReturns:\n- type: {'type': 'object', 'properties': {'type': {'type': 'string', 'enum': ['image']}, 'source': {'type': 'object', 'properties': {'type': {'type': 'string', 'enum': ['base64']}, 'media_type': {'type': 'string'}, 'data': {'type': 'string'}}, 'required': ['type', 'media_type', 'data']}}}", 'input_schema': {'type': 'object', 'properties': {}, 'required': []}}, {'name': 'get_object_and_properties', 'description': 'Returns a dict with a couple of integer properties called x and y\n\nReturns:\n- type: object', 'input_schema': {'type': 'object', 'properties': {}, 'required': []}}, {'name': 'get_str', 'description': 'Returns a random string\n\nReturns:\n- type: string', 'input_schema': {'type': 'object', 'properties': {}, 'required': []}}]}}
[2024-06-24 09:51:32 - anthropic._base_client:959 - DEBUG] Sending HTTP Request: POST https://api.anthropic.com/v1/messages
[2024-06-24 09:51:43 - httpx:1026 - INFO] HTTP Request: POST https://api.anthropic.com/v1/messages "HTTP/1.1 200 OK"
[2024-06-24 09:51:43 - anthropic._base_client:998 - DEBUG] HTTP Response: POST https://api.anthropic.com/v1/messages "200 OK" Headers({'date': 'Mon, 24 Jun 2024 14:51:43 GMT', 'content-type': 'application/json', 'transfer-encoding': 'chunked', 'connection': 'keep-alive', 'anthropic-ratelimit-requests-limit': '50', 'anthropic-ratelimit-requests-remaining': '48', 'anthropic-ratelimit-requests-reset': '2024-06-24T14:52:03Z', 'anthropic-ratelimit-tokens-limit': '40000', 'anthropic-ratelimit-tokens-remaining': '38000', 'anthropic-ratelimit-tokens-reset': '2024-06-24T14:52:03Z', 'request-id': 'req_01Cy14A6Kt5mwA8yUoUMG2oz', 'x-cloud-trace-context': 'fc2a0fcc5d894a0d920dbad4289868e3', 'via': '1.1 google', 'cf-cache-status': 'DYNAMIC', 'server': 'cloudflare', 'cf-ray': '898d8955c9444df4-MCI', 'content-encoding': 'gzip'})
Thank you for providing the image. Let me describe the puppy for you:

The image shows an adorable Cavalier King Charles Spaniel puppy. This charming little dog is lying on grass, with its head slightly raised, looking directly at the camera with big, expressive eyes.

The puppy has a distinctive coat coloration typical of the breed:
- Its face is predominantly white, with a large brown patch covering one eye and ear.
- The body visible in the image appears to be mostly white.
- The ears are long and floppy, with beautiful reddish-brown fur.

The puppy's eyes are dark and soulful, giving it a sweet and gentle expression. Its nose is small and black.

The setting adds to the puppy's charm:
- The puppy is resting on lush green grass, which provides a nice contrast to its fur.
- In the background, you can see purple flowers, which appear to be some type of aster or daisy-like blooms. These flowers add a lovely splash of color to the scene.
- There's also what looks like a wooden structure or fence visible behind the flowers, suggesting this might be a garden setting.

Overall, this image captures the essence of puppy cuteness, showcasing the Cavalier King Charles Spaniel's characteristic "sweet" expression and beautiful coat. The combination of the adorable puppy, vibrant flowers, and natural setting makes for a very appealing and heartwarming photograph.