vision-agent 0.2.83__py3-none-any.whl → 0.2.84__py3-none-any.whl

vision_agent/lmm/__init__.py

@@ -1 +1 @@
-from .lmm import LMM, AzureOpenAILMM, Message, OllamaLMM, OpenAILMM
+from .lmm import LMM, AzureOpenAILMM, ClaudeSonnetLMM, Message, OllamaLMM, OpenAILMM

vision_agent/lmm/lmm.py

@@ -7,7 +7,9 @@ from abc import ABC, abstractmethod
 from pathlib import Path
 from typing import Any, Callable, Dict, List, Optional, Union, cast
 
+import anthropic
 import requests
+from anthropic.types import ImageBlockParam, MessageParam, TextBlockParam
 from openai import AzureOpenAI, OpenAI
 from PIL import Image
 
@@ -375,3 +377,92 @@ class OllamaLMM(LMM):
 
         response = response.json()
         return response["response"]  # type: ignore
+
+
+class ClaudeSonnetLMM(LMM):
+    r"""An LMM class for Anthropic's Claude Sonnet model."""
+
+    def __init__(
+        self,
+        api_key: Optional[str] = None,
+        model_name: str = "claude-3-sonnet-20240229",
+        max_tokens: int = 4096,
+        temperature: float = 0.7,
+        **kwargs: Any,
+    ):
+        self.client = anthropic.Anthropic(api_key=api_key)
+        self.model_name = model_name
+        self.max_tokens = max_tokens
+        self.temperature = temperature
+        self.kwargs = kwargs
+
+    def __call__(
+        self,
+        input: Union[str, List[Dict[str, Any]]],
+    ) -> str:
+        if isinstance(input, str):
+            return self.generate(input)
+        return self.chat(input)
+
+    def chat(
+        self,
+        chat: List[Dict[str, Any]],
+    ) -> str:
+        messages: List[MessageParam] = []
+        for msg in chat:
+            content: List[Union[TextBlockParam, ImageBlockParam]] = [
+                TextBlockParam(type="text", text=msg["content"])
+            ]
+            if "media" in msg:
+                for media_path in msg["media"]:
+                    encoded_media = encode_media(media_path)
+                    content.append(
+                        ImageBlockParam(
+                            type="image",
+                            source={
+                                "type": "base64",
+                                "media_type": "image/png",
+                                "data": encoded_media,
+                            },
+                        )
+                    )
+            messages.append({"role": msg["role"], "content": content})
+
+        response = self.client.messages.create(
+            model=self.model_name,
+            max_tokens=self.max_tokens,
+            temperature=self.temperature,
+            messages=messages,
+            **self.kwargs,
+        )
+        return cast(str, response.content[0].text)
+
+    def generate(
+        self,
+        prompt: str,
+        media: Optional[List[Union[str, Path]]] = None,
+    ) -> str:
+        content: List[Union[TextBlockParam, ImageBlockParam]] = [
+            TextBlockParam(type="text", text=prompt)
+        ]
+        if media:
+            for m in media:
+                encoded_media = encode_media(m)
+                content.append(
+                    ImageBlockParam(
+                        type="image",
+                        source={
+                            "type": "base64",
+                            "media_type": "image/png",
+                            "data": encoded_media,
+                        },
+                    )
+                )
+        response = self.client.messages.create(
+            model=self.model_name,
+            max_tokens=self.max_tokens,
+            temperature=self.temperature,
+            messages=[{"role": "user", "content": content}],
+            **self.kwargs,
+        )
+        return cast(str, response.content[0].text)

{vision_agent-0.2.83.dist-info → vision_agent-0.2.84.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vision-agent
-Version: 0.2.83
+Version: 0.2.84
 Summary: Toolset for Vision Agent
 Author: Landing AI
 Author-email: dev@landing.ai
@@ -9,6 +9,7 @@ Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
+Requires-Dist: anthropic (>=0.31.0,<0.32.0)
 Requires-Dist: e2b (>=0.17.1,<0.18.0)
 Requires-Dist: e2b-code-interpreter (==0.0.11a2)
 Requires-Dist: ipykernel (>=6.29.4,<7.0.0)

{vision_agent-0.2.83.dist-info → vision_agent-0.2.84.dist-info}/RECORD

@@ -5,8 +5,8 @@ vision_agent/agent/vision_agent.py,sha256=fLCkqYJzk9SNtu8TzKBk0TLZrXDMTCqgI3FI-z
 vision_agent/agent/vision_agent_prompts.py,sha256=brBV-SmzyzTG5M9nfV3R5xdYT_BUYOKzxNFmTa2Sp-o,11049
 vision_agent/fonts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 vision_agent/fonts/default_font_ch_en.ttf,sha256=1YM0Z3XqLDjSNbF7ihQFSAIUdjF9m1rtHiNC_6QosTE,1594400
-vision_agent/lmm/__init__.py,sha256=bw24xyQJHGzmph5e-bKCiTh9AX6tRFI2OUd0mofxjZI,68
-vision_agent/lmm/lmm.py,sha256=UtUl3k2TiN4gbdlqE16rexQ72WFE7FGru0yguyJ4jAE,12129
+vision_agent/lmm/__init__.py,sha256=j9mQsIXQOYfW6nFd47uTwuBe1ranpEbwW308qLfCWN0,85
+vision_agent/lmm/lmm.py,sha256=035uONyp6_jD3PVdNdSg2PMHOG1voqnpsn2IyybUENs,15147
 vision_agent/tools/__init__.py,sha256=k69hvcy2FWjDqVA0klzybKeoToOH_bom5NTVSliA0Og,1838
 vision_agent/tools/prompts.py,sha256=V1z4YJLXZuUl_iZ5rY0M5hHc_2tmMEUKr0WocXKGt4E,1430
 vision_agent/tools/tool_utils.py,sha256=6z0jrvUnesJEFqDHZoAvbXPic8rzh0KfILL07tu0uRo,2205
@@ -18,7 +18,7 @@ vision_agent/utils/image_utils.py,sha256=_cdiS5YrLzqkq_ZgFUO897m5M4_SCIThwUy4lOk
 vision_agent/utils/sim.py,sha256=1HTaiVaBiKeyXIy21IYGXlPw0TipOyw9FPOJDfyLI94,4409
 vision_agent/utils/type_defs.py,sha256=QeQRRIlklZMWzxROcCn5ELxP89nYdXGydy1rAiSpZZw,1384
 vision_agent/utils/video.py,sha256=rNmU9KEIkZB5-EztZNlUiKYN0mm_55A_2VGUM0QpqLA,8779
-vision_agent-0.2.83.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-vision_agent-0.2.83.dist-info/METADATA,sha256=SPanaWYdrDs5gulJR79jVU3pk6alRN9nu7RpwqEJzDU,9433
-vision_agent-0.2.83.dist-info/WHEEL,sha256=7Z8_27uaHI_UZAc4Uox4PpBhQ9Y5_modZXWMxtUi4NU,88
-vision_agent-0.2.83.dist-info/RECORD,,
+vision_agent-0.2.84.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+vision_agent-0.2.84.dist-info/METADATA,sha256=mZM17x03oCnI8tp4g7psZzonwNlS0fqN0f78dWbob-o,9477
+vision_agent-0.2.84.dist-info/WHEEL,sha256=7Z8_27uaHI_UZAc4Uox4PpBhQ9Y5_modZXWMxtUi4NU,88
+vision_agent-0.2.84.dist-info/RECORD,,