vision-agent 0.2.65__py3-none-any.whl → 0.2.67__py3-none-any.whl

vision_agent/agent/vision_agent_prompts.py

@@ -179,6 +179,8 @@ This is the documentation for the functions you have access to. You may call any
 8. DO NOT use try except block to handle the error, let the error be raised if the code is incorrect.
 9. DO NOT import the testing function as it will available in the testing environment.
 10. Print the output of the function that is being tested.
+11. Use the output of the function that is being tested as the return value of the testing function.
+12. Run the testing function in the end and don't assign a variable to its output.
 """
 
 

vision_agent/lmm/__init__.py

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

vision_agent/lmm/lmm.py

@@ -6,6 +6,7 @@ from abc import ABC, abstractmethod
 from pathlib import Path
 from typing import Any, Callable, Dict, List, Optional, Union, cast
 
+import requests
 from openai import AzureOpenAI, OpenAI
 
 import vision_agent.tools as T
@@ -267,3 +268,84 @@ class AzureOpenAILMM(OpenAILMM):
         if json_mode:
             kwargs["response_format"] = {"type": "json_object"}
         self.kwargs = kwargs
+
+
+class OllamaLMM(LMM):
+    r"""An LMM class for the ollama."""
+
+    def __init__(
+        self,
+        model_name: str = "llava",
+        base_url: Optional[str] = "http://localhost:11434/api",
+        json_mode: bool = False,
+        **kwargs: Any,
+    ):
+        self.url = base_url
+        self.model_name = model_name
+        self.json_mode = json_mode
+        self.stream = False
+
+    def __call__(
+        self,
+        input: Union[str, List[Message]],
+    ) -> str:
+        if isinstance(input, str):
+            return self.generate(input)
+        return self.chat(input)
+
+    def chat(
+        self,
+        chat: List[Message],
+    ) -> str:
+        """Chat with the LMM model.
+
+        Parameters:
+            chat (List[Dict[str, str]]): A list of dictionaries containing the chat
+                messages. The messages can be in the format:
+                [{"role": "user", "content": "Hello!"}, ...]
+                or if it contains media, it should be in the format:
+                [{"role": "user", "content": "Hello!", "media": ["image1.jpg", ...]}, ...]
+        """
+        fixed_chat = []
+        for message in chat:
+            if "media" in message:
+                message["images"] = [encode_image(m) for m in message["media"]]
+                del message["media"]
+            fixed_chat.append(message)
+        url = f"{self.url}/chat"
+        model = self.model_name
+        messages = fixed_chat
+        data = {"model": model, "messages": messages, "stream": self.stream}
+        json_data = json.dumps(data)
+        response = requests.post(url, data=json_data)
+        if response.status_code != 200:
+            raise ValueError(f"Request failed with status code {response.status_code}")
+        response = response.json()
+        return response["message"]["content"]  # type: ignore
+
+    def generate(
+        self,
+        prompt: str,
+        media: Optional[List[Union[str, Path]]] = None,
+    ) -> str:
+
+        url = f"{self.url}/generate"
+        data = {
+            "model": self.model_name,
+            "prompt": prompt,
+            "images": [],
+            "stream": self.stream,
+        }
+
+        json_data = json.dumps(data)
+        if media and len(media) > 0:
+            for m in media:
+                data["images"].append(encode_image(m))  # type: ignore
+
+        response = requests.post(url, data=json_data)
+
+        if response.status_code != 200:
+            raise ValueError(f"Request failed with status code {response.status_code}")
+
+        response = response.json()
+        return response["response"]  # type: ignore

vision_agent/utils/execute.py

@@ -309,6 +309,21 @@ class Execution(BaseModel):
         """
         return self.error is None
 
+    def get_main_result(self) -> Optional[Result]:
+        """
+        Get the main result of the execution.
+        An execution may have multiple results, e.g. intermediate outputs. The main result is the last output of the cell execution.
+        """
+        if not self.success:
+            _LOGGER.info("Result is not available as the execution was not successful.")
+            return None
+        if not self.results or not any(res.is_main_result for res in self.results):
+            _LOGGER.info("Execution was successful but there is no main result.")
+            return None
+        main_result = self.results[-1]
+        assert main_result.is_main_result, "The last result should be the main result."
+        return main_result
+
     def to_json(self) -> str:
         """
         Returns the JSON representation of the Execution object.
@@ -411,11 +426,11 @@ class E2BCodeInterpreter(CodeInterpreter):
             """
 import platform
 import sys
-import pkg_resources
+import importlib.metadata
 
 print(f"Python version: {sys.version}")
 print(f"OS version: {platform.system()} {platform.release()} ({platform.architecture()})")
-va_version = pkg_resources.get_distribution("vision-agent").version
+va_version = importlib.metadata.version("vision-agent")
 print(f"Vision Agent version: {va_version}")"""
         )
         sys_versions = "\n".join(result.logs.stdout)

{vision_agent-0.2.65.dist-info → vision_agent-0.2.67.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vision-agent
-Version: 0.2.65
+Version: 0.2.67
 Summary: Toolset for Vision Agent
 Author: Landing AI
 Author-email: dev@landing.ai

{vision_agent-0.2.65.dist-info → vision_agent-0.2.67.dist-info}/RECORD

@@ -2,22 +2,22 @@ vision_agent/__init__.py,sha256=EAb4-f9iyuEYkBrX4ag1syM8Syx8118_t0R6_C34M9w,57
 vision_agent/agent/__init__.py,sha256=IUwfbPMcT8X_rnXMLmI8gJ4ltsHy_XSs9eLiKURJxeY,81
 vision_agent/agent/agent.py,sha256=ZK-5lOtd9-eD9aWcXssJpnOyvZuO7_5hAmnb-6sWVe8,569
 vision_agent/agent/vision_agent.py,sha256=HC63BP4jPiR4lJLEkKQ-zMV5C5JwjnuZvc7hVjjS2uk,25284
-vision_agent/agent/vision_agent_prompts.py,sha256=bMXdZYf6kbikHn__tCGrYE1QvXC88EmpMpM_97V6szA,8472
+vision_agent/agent/vision_agent_prompts.py,sha256=jpGJjrxDrxZej5SSgsTEK1sSYttgkTiZqxZAU1jWfvk,8656
 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=3ro5lCIoS3DgEghOy0SPFrEhYvFnWZpVC5S5kSnIx6A,57
-vision_agent/lmm/lmm.py,sha256=ihmLYL_291HnELyMtfFKTCnPWnmuoEH2DDFmc4ynMG8,8945
+vision_agent/lmm/__init__.py,sha256=bw24xyQJHGzmph5e-bKCiTh9AX6tRFI2OUd0mofxjZI,68
+vision_agent/lmm/lmm.py,sha256=V7jfU94HwA-SiQLY14USHrSGtagVKCNGjZhW5MyKipo,11547
 vision_agent/tools/__init__.py,sha256=aE1O8cMeLDPO50Sc-CuAQ_Akh0viz7vBxDcVeZNqsA0,1604
 vision_agent/tools/prompts.py,sha256=V1z4YJLXZuUl_iZ5rY0M5hHc_2tmMEUKr0WocXKGt4E,1430
 vision_agent/tools/tool_utils.py,sha256=wzRacbUpqk9hhfX_Y08rL8qP0XCN2w-8IZoYLi3Upn4,869
 vision_agent/tools/tools.py,sha256=Qzwm_wu6KJh-3DSoNmZ4Lv8jCCNJMwKIPBFxxN6FmDo,31397
 vision_agent/utils/__init__.py,sha256=CW84HnhqI6XQVuxf2KifkLnSuO7EOhmuL09-gAymAak,219
-vision_agent/utils/execute.py,sha256=GqoAodxtwTPBr1nujPTsWiZO2rBGvWVXTe8lgxY4d_g,20603
+vision_agent/utils/execute.py,sha256=QImS69SN00logF-E68aNpT7YsJVRQOhZYlNLmCNEfro,21337
 vision_agent/utils/image_utils.py,sha256=_cdiS5YrLzqkq_ZgFUO897m5M4_SCIThwUy4lOklfB8,7700
 vision_agent/utils/sim.py,sha256=ci6Eta73dDgLP1Ajtknbgmf1g8aAvBHqlVQvBuLMKXQ,4427
 vision_agent/utils/type_defs.py,sha256=BlI8ywWHAplC7kYWLvt4AOdnKpEW3qWEFm-GEOSkrFQ,1792
 vision_agent/utils/video.py,sha256=rNmU9KEIkZB5-EztZNlUiKYN0mm_55A_2VGUM0QpqLA,8779
-vision_agent-0.2.65.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-vision_agent-0.2.65.dist-info/METADATA,sha256=MnlqbmIs4PRO4Y1qaR2abmD0RueZnIYUEnGGcuJ1wHA,8363
-vision_agent-0.2.65.dist-info/WHEEL,sha256=7Z8_27uaHI_UZAc4Uox4PpBhQ9Y5_modZXWMxtUi4NU,88
-vision_agent-0.2.65.dist-info/RECORD,,
+vision_agent-0.2.67.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+vision_agent-0.2.67.dist-info/METADATA,sha256=BZKENJv_iaNU-XDqc5z4Ygx7k2jR4_7BbIdGoJE3voA,8363
+vision_agent-0.2.67.dist-info/WHEEL,sha256=7Z8_27uaHI_UZAc4Uox4PpBhQ9Y5_modZXWMxtUi4NU,88
+vision_agent-0.2.67.dist-info/RECORD,,