prompt-caller 0.1.3__tar.gz → 0.2.0__tar.gz

{prompt_caller-0.1.3 → prompt_caller-0.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: prompt_caller
-Version: 0.1.3
+Version: 0.2.0
 Summary: This package is responsible for calling prompts in a specific format. It uses LangChain and OpenAI API
 Home-page: https://github.com/ThiNepo/prompt-caller
 Author: Thiago Nepomuceno
@@ -11,11 +11,13 @@ Classifier: Operating System :: OS Independent
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: pyyaml>=6.0.2
-Requires-Dist: python-dotenv>=1.0.1
+Requires-Dist: python-dotenv>=1.2.1
 Requires-Dist: Jinja2>=3.1.4
-Requires-Dist: langchain-openai>=0.3.5
-Requires-Dist: openai>=1.63.0
-Requires-Dist: pillow>=11.0.0
+Requires-Dist: langchain-core>=1.2.7
+Requires-Dist: langchain-openai>=1.1.7
+Requires-Dist: langchain-google-genai>=4.2.0
+Requires-Dist: openai>=2.16.0
+Requires-Dist: pillow>=12.1.0
 
 # PromptCaller
 

prompt_caller-0.2.0/prompt_caller/prompt_caller.py

@@ -0,0 +1,283 @@
+import os
+import re
+import ast
+
+import requests
+import yaml
+from dotenv import load_dotenv
+from jinja2 import Template
+from langgraph.types import Command
+from langchain_core.tools import tool
+from langchain_core.messages import HumanMessage, SystemMessage, ToolMessage
+from langchain.agents import create_agent
+from langchain.agents.middleware import wrap_tool_call
+from langchain_openai import ChatOpenAI
+from langchain_google_genai import ChatGoogleGenerativeAI
+from PIL import Image
+from pydantic import BaseModel, Field, create_model
+
+from io import BytesIO
+import base64
+
+load_dotenv()
+
+
+class PromptCaller:
+    def __init__(self, promptPath="prompts"):
+        self.promptPath = promptPath
+
+    def _loadPrompt(self, file_path):
+        with open(file_path, "r", encoding="utf-8") as file:
+            content = file.read()
+
+        # Split YAML header and the body
+        header, body = content.split("---", 2)[1:]
+
+        # Parse the YAML header
+        model_config = yaml.safe_load(header.strip())
+
+        # Step 2: Parse the JSX body and return it
+        return model_config, body.strip()
+
+    def _renderTemplate(self, body, context):
+        template = Template(body)
+        return template.render(context)
+
+    import re
+
+    def _parseJSXBody(self, body):
+        elements = []
+        # 1. Regex to find tags, attributes string, and content
+        tag_pattern = r"<(system|user|assistant|image)([^>]*)>(.*?)</\1>"
+
+        # 2. Regex to find key="value" pairs within the attributes string
+        attr_pattern = r'(\w+)\s*=\s*"(.*?)"'
+
+        matches = re.findall(tag_pattern, body, re.DOTALL)
+
+        for tag, attrs_string, content in matches:
+            # 3. Parse the attributes string (e.g., ' tag="image 1"') into a dict
+            attributes = {}
+            if attrs_string:
+                attr_matches = re.findall(attr_pattern, attrs_string)
+                for key, value in attr_matches:
+                    attributes[key] = value
+
+            element = {"role": tag, "content": content.strip()}
+
+            # 4. Add the attributes to our element dict if they exist
+            if attributes:
+                element["attributes"] = attributes
+
+            elements.append(element)
+
+        return elements
+
+    def _createChat(self, configuration):
+        if configuration.get("model") is not None and configuration.get(
+            "model"
+        ).startswith("gemini"):
+            return ChatGoogleGenerativeAI(**configuration)
+        else:
+            return ChatOpenAI(**configuration)
+
+    def getImageBase64(self, url: str) -> str:
+        response = requests.get(url)
+        response.raise_for_status()
+        img = Image.open(BytesIO(response.content))
+        buffered = BytesIO()
+        img.save(buffered, format="PNG")
+        img_base64 = base64.b64encode(buffered.getvalue()).decode("utf-8")
+        return f"data:image/png;base64,{img_base64}"
+
+    def loadPrompt(self, promptName, context=None):
+        # initialize context
+        if context is None:
+            context = {}
+
+        configuration, template = self._loadPrompt(
+            os.path.join(self.promptPath, f"{promptName}.prompt")
+        )
+
+        template = self._renderTemplate(template, context)
+
+        parsedMessages = self._parseJSXBody(template)
+
+        messages = []
+
+        for message in parsedMessages:
+            if message.get("role") == "system":
+                messages.append(SystemMessage(content=message.get("content")))
+
+            if message.get("role") == "user":
+                messages.append(HumanMessage(content=message.get("content")))
+
+            if message.get("role") == "image":
+                base64_image = message.get("content")
+
+                if base64_image.startswith("http"):
+                    base64_image = self.getImageBase64(base64_image)
+
+                content = [
+                    {
+                        "type": "image_url",
+                        "image_url": {"url": base64_image},
+                    }
+                ]
+
+                tag = message.get("attributes", {}).get("tag")
+                if tag:
+                    content.append({"type": "text", "text": f"({tag})"})
+
+                messages.append(HumanMessage(content=content))
+
+        return configuration, messages
+
+    def createPydanticModel(self, dynamic_dict):
+        # Create a dynamic Pydantic model from the dictionary
+        fields = {
+            key: (str, Field(description=f"Description for {key}"))
+            for key in dynamic_dict.keys()
+        }
+        # Dynamically create the Pydantic model with the fields
+        return create_model("DynamicModel", **fields)
+
+    def call(self, promptName, context=None):
+        configuration, messages = self.loadPrompt(promptName, context)
+
+        output = None
+
+        if "output" in configuration:
+            output = configuration.get("output")
+            configuration.pop("output")
+
+        chat = self._createChat(configuration)
+
+        if output:
+            dynamicModel = self.createPydanticModel(output)
+            chat = chat.with_structured_output(dynamicModel)
+
+        response = chat.invoke(messages)
+
+        return response
+
+    def _create_pdf_middleware(self):
+        """Middleware to handle tool responses that contain pdf content."""
+
+        @wrap_tool_call
+        def handle_pdf_response(request, handler):
+            # Execute the actual tool
+            result = handler(request)
+
+            # Check if result content is pdf data
+            if hasattr(result, "content"):
+                content = result.content
+                # Try to parse if it's a string representation of a list
+                if isinstance(content, str) and content.startswith("["):
+                    try:
+                        content = ast.literal_eval(content)
+                    except (ValueError, SyntaxError):
+                        pass
+
+                if (
+                    isinstance(content, list)
+                    and content
+                    and isinstance(content[0], dict)
+                    and "input_file" in content[0]
+                    and "pdf" in content[0]["file_data"]
+                ):
+                    # Use Command to add both tool result and image to messages
+                    return Command(
+                        update={"messages": [result, HumanMessage(content=content)]}
+                    )
+
+            return result  # Return normal result
+
+        return handle_pdf_response
+
+    def _create_image_middleware(self):
+        """Middleware to handle tool responses that contain image content."""
+
+        @wrap_tool_call
+        def handle_image_response(request, handler):
+            # Execute the actual tool
+            result = handler(request)
+
+            # Check if result content is image data (list with image_url dict)
+            if hasattr(result, "content"):
+                content = result.content
+                # Try to parse if it's a string representation of a list
+                if isinstance(content, str) and content.startswith("["):
+                    try:
+                        content = ast.literal_eval(content)
+                    except (ValueError, SyntaxError):
+                        pass
+
+                if (
+                    isinstance(content, list)
+                    and content
+                    and isinstance(content[0], dict)
+                    and "image_url" in content[0]
+                ):
+                    # Use Command to add both tool result and image to messages
+                    return Command(
+                        update={"messages": [result, HumanMessage(content=content)]}
+                    )
+
+            return result  # Return normal result
+
+        return handle_image_response
+
+    def agent(
+        self, promptName, context=None, tools=None, output=None, allowed_steps=10
+    ):
+        configuration, messages = self.loadPrompt(promptName, context)
+
+        # Handle structured output from config
+        dynamicOutput = None
+        if output is None and "output" in configuration:
+            dynamicOutput = configuration.pop("output")
+
+        chat = self._createChat(configuration)
+
+        # Prepare tools
+        if tools is None:
+            tools = []
+        tools = [tool(t) for t in tools]
+
+        # Handle response format (structured output)
+        response_format = None
+        if output:
+            response_format = output
+        elif dynamicOutput:
+            response_format = self.createPydanticModel(dynamicOutput)
+
+        # Extract system message for create_agent
+        system_prompt = None
+        user_messages = []
+        for msg in messages:
+            if isinstance(msg, SystemMessage):
+                system_prompt = msg.content
+            else:
+                user_messages.append(msg)
+
+        # Create and invoke agent
+        agent_graph = create_agent(
+            model=chat,
+            tools=tools,
+            system_prompt=system_prompt,
+            response_format=response_format,
+            middleware=[
+                self._create_image_middleware(),
+                self._create_pdf_middleware(),
+            ],
+        )
+
+        result = agent_graph.invoke(
+            {"messages": user_messages}, config={"recursion_limit": allowed_steps}
+        )
+
+        # Return structured output or last message
+        if response_format and result.get("structured_response"):
+            return result["structured_response"]
+        return result["messages"][-1]

{prompt_caller-0.1.3 → prompt_caller-0.2.0}/prompt_caller.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: prompt_caller
-Version: 0.1.3
+Version: 0.2.0
 Summary: This package is responsible for calling prompts in a specific format. It uses LangChain and OpenAI API
 Home-page: https://github.com/ThiNepo/prompt-caller
 Author: Thiago Nepomuceno
@@ -11,11 +11,13 @@ Classifier: Operating System :: OS Independent
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: pyyaml>=6.0.2
-Requires-Dist: python-dotenv>=1.0.1
+Requires-Dist: python-dotenv>=1.2.1
 Requires-Dist: Jinja2>=3.1.4
-Requires-Dist: langchain-openai>=0.3.5
-Requires-Dist: openai>=1.63.0
-Requires-Dist: pillow>=11.0.0
+Requires-Dist: langchain-core>=1.2.7
+Requires-Dist: langchain-openai>=1.1.7
+Requires-Dist: langchain-google-genai>=4.2.0
+Requires-Dist: openai>=2.16.0
+Requires-Dist: pillow>=12.1.0
 
 # PromptCaller
 

prompt_caller-0.2.0/prompt_caller.egg-info/requires.txt

@@ -0,0 +1,8 @@
+pyyaml>=6.0.2
+python-dotenv>=1.2.1
+Jinja2>=3.1.4
+langchain-core>=1.2.7
+langchain-openai>=1.1.7
+langchain-google-genai>=4.2.0
+openai>=2.16.0
+pillow>=12.1.0

{prompt_caller-0.1.3 → prompt_caller-0.2.0}/setup.py

@@ -35,7 +35,7 @@ class BdistWheelCommand(bdist_wheel):
 
 setuptools.setup(
     name="prompt_caller",
-    version="0.1.3",
+    version="0.2.0",
     author="Thiago Nepomuceno",
     author_email="thiago@neps.academy",
     description="This package is responsible for calling prompts in a specific format. It uses LangChain and OpenAI API",
@@ -51,11 +51,13 @@ setuptools.setup(
     ],
     install_requires=[
         "pyyaml>=6.0.2",
-        "python-dotenv>=1.0.1",
+        "python-dotenv>=1.2.1",
         "Jinja2>=3.1.4",
-        "langchain-openai>=0.3.5",
-        "openai>=1.63.0",
-        "pillow>=11.0.0",
+        "langchain-core>=1.2.7",
+        "langchain-openai>=1.1.7",
+        "langchain-google-genai>=4.2.0",
+        "openai>=2.16.0",
+        "pillow>=12.1.0",
     ],
     cmdclass={"sdist": SdistCommand, "bdist_wheel": BdistWheelCommand},
 )

prompt_caller-0.1.3/prompt_caller/prompt_caller.py

@@ -1,224 +0,0 @@
-import os
-import re
-
-import requests
-import yaml
-from dotenv import load_dotenv
-from jinja2 import Template
-from langchain_core.tools import tool
-from langchain_core.messages import HumanMessage, SystemMessage, ToolMessage
-from langchain_openai import ChatOpenAI
-from langchain_google_genai import ChatGoogleGenerativeAI
-from PIL import Image
-from pydantic import BaseModel, Field, create_model
-
-from io import BytesIO
-import base64
-
-load_dotenv()
-
-
-class PromptCaller:
-
-    def __init__(self, promptPath="prompts"):
-        self.promptPath = promptPath
-
-    def _loadPrompt(self, file_path):
-        with open(file_path, "r", encoding="utf-8") as file:
-            content = file.read()
-
-        # Split YAML header and the body
-        header, body = content.split("---", 2)[1:]
-
-        # Parse the YAML header
-        model_config = yaml.safe_load(header.strip())
-
-        # Step 2: Parse the JSX body and return it
-        return model_config, body.strip()
-
-    def _renderTemplate(self, body, context):
-        template = Template(body)
-        return template.render(context)
-
-    def _parseJSXBody(self, body):
-        elements = []
-        tag_pattern = r"<(system|user|assistant|image)>(.*?)</\1>"
-
-        matches = re.findall(tag_pattern, body, re.DOTALL)
-
-        for tag, content in matches:
-            elements.append({"role": tag, "content": content.strip()})
-
-        return elements
-
-    def _createChat(self, configuration):
-        if configuration.get("model") is not None and configuration.get(
-            "model"
-        ).startswith("gemini"):
-            return ChatGoogleGenerativeAI(**configuration)
-        else:
-            return ChatOpenAI(**configuration)
-
-    def getImageBase64(self, url: str) -> str:
-        response = requests.get(url)
-        response.raise_for_status()
-        img = Image.open(BytesIO(response.content))
-        buffered = BytesIO()
-        img.save(buffered, format="PNG")
-        img_base64 = base64.b64encode(buffered.getvalue()).decode("utf-8")
-        return f"data:image/png;base64,{img_base64}"
-
-    def loadPrompt(self, promptName, context=None):
-        # initialize context
-        if context is None:
-            context = {}
-
-        configuration, template = self._loadPrompt(
-            os.path.join(self.promptPath, f"{promptName}.prompt")
-        )
-
-        template = self._renderTemplate(template, context)
-
-        parsedMessages = self._parseJSXBody(template)
-
-        messages = []
-
-        for message in parsedMessages:
-            if message.get("role") == "system":
-                messages.append(SystemMessage(content=message.get("content")))
-
-            if message.get("role") == "user":
-                messages.append(HumanMessage(content=message.get("content")))
-
-            if message.get("role") == "image":
-                base64_image = message.get("content")
-
-                if base64_image.startswith("http"):
-                    base64_image = self.getImageBase64(base64_image)
-
-                messages.append(
-                    HumanMessage(
-                        content=[
-                            {
-                                "type": "image_url",
-                                "image_url": {"url": base64_image},
-                            }
-                        ]
-                    )
-                )
-
-        return configuration, messages
-
-    def createPydanticModel(self, dynamic_dict):
-        # Create a dynamic Pydantic model from the dictionary
-        fields = {
-            key: (str, Field(description=f"Description for {key}"))
-            for key in dynamic_dict.keys()
-        }
-        # Dynamically create the Pydantic model with the fields
-        return create_model("DynamicModel", **fields)
-
-    def call(self, promptName, context=None):
-
-        configuration, messages = self.loadPrompt(promptName, context)
-
-        output = None
-
-        if "output" in configuration:
-            output = configuration.get("output")
-            configuration.pop("output")
-
-        chat = self._createChat(configuration)
-
-        if output:
-            dynamicModel = self.createPydanticModel(output)
-            chat = chat.with_structured_output(dynamicModel)
-
-        response = chat.invoke(messages)
-
-        return response
-
-    def agent(
-        self, promptName, context=None, tools=None, output=None, allowed_steps=10
-    ):
-
-        configuration, messages = self.loadPrompt(promptName, context)
-
-        dynamicOutput = None
-
-        if output is None and "output" in configuration:
-            dynamicOutput = configuration.get("output")
-            configuration.pop("output")
-
-            for message in messages:
-                if isinstance(message, SystemMessage):
-                    message.content += "\nOnly use the tool DynamicModel when providing an output call."
-                    break
-
-        chat = self._createChat(configuration)
-
-        # Register the tools
-        if tools is None:
-            tools = []
-
-        # Transform functions in tools
-        tools = [tool(t) for t in tools]
-
-        tools_dict = {t.name.lower(): t for t in tools}
-
-        if output:
-            tools.extend([output])
-            tools_dict[output.__name__.lower()] = output
-        elif dynamicOutput:
-            dynamicModel = self.createPydanticModel(dynamicOutput)
-
-            tools.extend([dynamicModel])
-            tools_dict["dynamicmodel"] = dynamicModel
-
-        chat = chat.bind_tools(tools)
-
-        try:
-            # First LLM invocation
-            response = chat.invoke(messages)
-            messages.append(response)
-
-            steps = 0
-            while response.tool_calls and steps < allowed_steps:
-                for tool_call in response.tool_calls:
-                    tool_name = tool_call["name"].lower()
-
-                    # If it's the final formatting tool, validate and return
-                    if dynamicOutput and tool_name == "dynamicmodel":
-                        return dynamicModel.model_validate(tool_call["args"])
-
-                    if output and tool_name == output.__name__.lower():
-                        return output.model_validate(tool_call["args"])
-
-                    selected_tool = tools_dict.get(tool_name)
-                    if not selected_tool:
-                        raise ValueError(f"Unknown tool: {tool_name}")
-
-                    # Invoke the selected tool with provided arguments
-                    tool_response = selected_tool.invoke(tool_call)
-                    messages.append(tool_response)
-
-                # If the latest message is a ToolMessage, re-invoke the LLM
-                if isinstance(messages[-1], ToolMessage):
-                    response = chat.invoke(messages)
-                    messages.append(response)
-                else:
-                    break
-
-                steps += 1
-
-            # Final LLM call if the last message is still a ToolMessage
-            if isinstance(messages[-1], ToolMessage):
-                response = chat.invoke(messages)
-                messages.append(response)
-
-            return response
-
-        except Exception as e:
-            print(e)
-            # Replace with appropriate logging in production
-            raise RuntimeError("Error during agent process") from e

prompt_caller-0.1.3/prompt_caller.egg-info/requires.txt

@@ -1,6 +0,0 @@
-pyyaml>=6.0.2
-python-dotenv>=1.0.1
-Jinja2>=3.1.4
-langchain-openai>=0.3.5
-openai>=1.63.0
-pillow>=11.0.0