tools.py

import base64
from langchain_core.messages import AnyMessage, HumanMessage, AIMessage


def extract_text(img_path: str) -> str:
    """
    Extract text from an image file using a multimodal model.
    """
    all_text = ""
    try:
        # Read image and encode as base64
        with open(img_path, "rb") as image_file:
            image_bytes = image_file.read()

        image_base64 = base64.b64encode(image_bytes).decode("utf-8")

        # Prepare the prompt including the base64 image data
        message = [
            HumanMessage(
                content=[
                    {
                        "type": "text",
                        "text": (
                            "Extract all the text from this image. "
                            "Return only the extracted text, no explanations."
                        ),
                    },
                    {
                        "type": "image_url",
                        "image_url": {
                            "url": f"data:image/png;base64,{image_base64}"
                        },
                    },
                ]
            )
        ]

        # Call the vision-capable model
        response = vision_llm.invoke(message)

        # Append extracted text
        all_text += response.content + "\n\n"

        return all_text.strip()
    except Exception as e:
        error_msg = f"Error extracting text: {str(e)}"
        print(error_msg)
        return ""


def web_search(query: str):
    """Performs a web search using SerpAPI."""
    search = GoogleSearch({
        "q": query,
        "num": 5,
        "api_key": "your_serpapi_key"
    })
    results = search.get_dict()["organic_results"]
    return results