prompt-caller 0.0.4__py3-none-any.whl → 0.1.0__py3-none-any.whl

prompt_caller/prompt_caller.py

@@ -1,13 +1,19 @@
 import os
 import re
 
+import requests
 import yaml
 from dotenv import load_dotenv
 from jinja2 import Template
-from langchain_core.messages import HumanMessage, SystemMessage
+from langchain_core.tools import tool
+from langchain_core.messages import HumanMessage, SystemMessage, ToolMessage
 from langchain_openai import ChatOpenAI
+from PIL import Image
 from pydantic import BaseModel, Field, create_model
 
+from io import BytesIO
+import base64
+
 load_dotenv()
 
 
@@ -32,7 +38,7 @@ class PromptCaller:
 
     def _parseJSXBody(self, body):
         elements = []
-        tag_pattern = r"<(system|user|assistant)>(.*?)</\1>"
+        tag_pattern = r"<(system|user|assistant|image)>(.*?)</\1>"
 
         matches = re.findall(tag_pattern, body, re.DOTALL)
 
@@ -41,6 +47,15 @@ class PromptCaller:
 
         return elements
 
+    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:
@@ -63,6 +78,23 @@ class PromptCaller:
             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):
@@ -93,3 +125,79 @@ class PromptCaller:
         response = chat.invoke(messages)
 
         return response
+
+    def agent(self, promptName, context=None, tools=None, allowed_steps=3):
+
+        configuration, messages = self.loadPrompt(promptName, context)
+
+        output = None
+
+        if "output" in configuration:
+            output = 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 = ChatOpenAI(**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:
+            dynamicModel = self.createPydanticModel(output)
+
+        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 tool_name == "dynamicmodel":
+                        return dynamicModel.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:
+            # Replace with appropriate logging in production
+            raise RuntimeError("Error during agent process") from e

{prompt_caller-0.0.4.dist-info → prompt_caller-0.1.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: prompt_caller
-Version: 0.0.4
+Version: 0.1.0
 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
@@ -15,6 +15,7 @@ Requires-Dist: python-dotenv>=1.0.1
 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
 
 # PromptCaller
 
@@ -86,6 +87,36 @@ In this example:
 - The `expression` value `3+8/9` is injected into the user message.
 - The model will respond with both the result of the expression and an explanation, as specified in the `output` section of the prompt.
 
+3. **Using the agent feature:**  
+
+   The `agent` method allows you to enhance the prompt's functionality by integrating external tools. Here’s an example where we evaluate a mathematical expression using Python’s `eval` in a safe execution environment:
+
+   ```python
+   from prompt_caller import PromptCaller
+
+   ai = PromptCaller()
+
+   def evaluate_expression(expression: str):
+       """
+       Evaluate a math expression using eval.
+       """
+       safe_globals = {"__builtins__": None}
+       return eval(expression, safe_globals, {})
+
+   response = ai.agent(
+       "sample-agent", {"expression": "3+8/9"}, tools=[evaluate_expression]
+   )
+
+   print(response)
+   ```
+
+   In this example:
+
+   - The `agent` method is used to process the prompt while integrating external tools.
+   - The `evaluate_expression` function evaluates the mathematical expression securely.
+   - The response includes the processed result based on the prompt and tool execution.
+   
+
 ## How It Works
 
 1. **\_loadPrompt:** Loads the prompt file, splits the YAML header from the body, and parses them.

prompt_caller-0.1.0.dist-info/RECORD

@@ -0,0 +1,8 @@
+prompt_caller/__init__.py,sha256=4EGdeAJ_Ig7A-b-e17-nYbiXjckT7uL3to5lchMsoW4,41
+prompt_caller/__main__.py,sha256=dJ0dYtVmnhZuoV79R6YiAIta1ZkUKb-TEX4VEuYbgk0,139
+prompt_caller/prompt_caller.py,sha256=FlQEmNJWrxrdLMaoTxsCfPPcbr3DXWN5Oq1pp45yVQM,6644
+prompt_caller-0.1.0.dist-info/LICENSE,sha256=HrhfyXIkWY2tGFK11kg7vPCqhgh5DcxleloqdhrpyMY,11558
+prompt_caller-0.1.0.dist-info/METADATA,sha256=0ciKS5ENrpqRA6EjrulhMu_R-7iwWwmMEbiYpjJbymk,4957
+prompt_caller-0.1.0.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
+prompt_caller-0.1.0.dist-info/top_level.txt,sha256=iihiDRq-0VrKB8IKjxf7Lrtv-fLMq4tvgM4fH3x0I94,14
+prompt_caller-0.1.0.dist-info/RECORD,,

prompt_caller-0.0.4.dist-info/RECORD

@@ -1,8 +0,0 @@
-prompt_caller/__init__.py,sha256=4EGdeAJ_Ig7A-b-e17-nYbiXjckT7uL3to5lchMsoW4,41
-prompt_caller/__main__.py,sha256=dJ0dYtVmnhZuoV79R6YiAIta1ZkUKb-TEX4VEuYbgk0,139
-prompt_caller/prompt_caller.py,sha256=KRQYxvAOPMFIqhoLgJWQYr1ahGEWefNWtIjw1W_v8BM,2842
-prompt_caller-0.0.4.dist-info/LICENSE,sha256=HrhfyXIkWY2tGFK11kg7vPCqhgh5DcxleloqdhrpyMY,11558
-prompt_caller-0.0.4.dist-info/METADATA,sha256=PEL3ljVM0N5qT_SHpWmoWsDeZGlKLsy9fFXAFECOUTY,3916
-prompt_caller-0.0.4.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
-prompt_caller-0.0.4.dist-info/top_level.txt,sha256=iihiDRq-0VrKB8IKjxf7Lrtv-fLMq4tvgM4fH3x0I94,14
-prompt_caller-0.0.4.dist-info/RECORD,,