Added tools. It's a me!

agent_tools.py

@@ -12,6 +12,7 @@ from youtube_transcript_api import YouTubeTranscriptApi
 from langchain.docstore.document import Document
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_community.retrievers import BM25Retriever
+import pdfplumber
 
 #YouTube Transcriber
 @tool
@@ -143,7 +144,6 @@ def text_from_pdf(pdf_file: str) -> str:
         content = ' '.join([page.extract_text() for page in pdf.pages])
         content = content.replace('\n', ' ')
 
-
 #vector store
 
 #string reverse

scratchpad.py

@@ -0,0 +1,133 @@
+from dotenv import load_dotenv
+
+load_dotenv()
+
+use_mistral = False
+use_gemini = True
+
+import base64
+import requests
+import os
+from mistralai import Mistral
+
+def encode_image(image_path):
+    """Encode the image to base64."""
+    try:
+        with open(image_path, "rb") as image_file:
+            return base64.b64encode(image_file.read()).decode('utf-8')
+    except FileNotFoundError:
+        print(f"Error: The file {image_path} was not found.")
+        return None
+    except Exception as e:  # Added general exception handling
+        print(f"Error: {e}")
+        return None
+
+# Path to your image
+image_path = "chess_test.jpg"
+
+# Getting the base64 string
+base64_image = encode_image(image_path)
+
+# Retrieve the API key from environment variables
+api_key = os.environ.get("API_KEY_MISTRAL")
+
+# Specify model
+model = "pixtral-large-latest"
+
+# Initialize the Mistral client
+client = Mistral(api_key=api_key)
+
+# Define the messages for the chat
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "text",
+                "text": r"""Below is an image of a chess board mid-game. Only use the image as a reference for the response. NEVER use implicit knowledge of chess or positions. 
+                The bottom left square is A1, the top right square is H8.
+                
+                Identify the position of all pieces in JSON format: {colour:{piece_type:[coordinates]}}
+                
+                Chess board diagram:"""
+            },
+            {
+                "type": "image_url",
+                "image_url": f"data:image/jpeg;base64,{base64_image}"
+            }
+        ]
+    }
+]
+
+if use_mistral:
+    # Get the chat response
+    chat_response = client.chat.complete(
+        model=model,
+        messages=messages
+    )
+
+    # Print the content of the response
+    print(chat_response.choices[0].message.content)
+    
+#### Gemini
+
+from google import genai
+from google.genai import types
+
+# Only run this block for Gemini Developer API
+
+client = genai.Client(api_key=os.environ.get("API_KEY_GEMINI2"))
+flash = True
+
+if flash:
+    google_model = 'gemini-2.5-flash-preview-05-20'
+else:
+    google_model = 'gemini-2.5-pro-preview-05-06'
+
+chess_prompt = """Using this image of a chess board diagram. Black squares are coloured dark brown, white squares are light brown. A1 is at the bottom left of the image, H8 is at the top right. Complete the following tasks in order:
+Task 1: Count the number of occupied and unoccupied squares in each row. e.g. {'occupied':3, 'unoccupied':5} => STRING
+Task 2: Count the number of each piece type in each row. Check that they add up to the total number of pieces. => STRING
+Task 3: In JSON format note the position of every piece by colour, type and then list of coordinates => JSON
+Task 4: Convert JSON format to FEN string. {'board_fen': <FEN STRING>} => JSON"""
+
+
+# To run this code you need to install the following dependencies:
+# pip install google-genai
+
+import base64
+import os
+from google import genai
+from google.genai import types
+
+def generate():
+    client = genai.Client(
+        api_key=os.environ.get("GEMINI_API_KEY"),
+    )
+
+    model = google_model #"gemini-2.5-pro-preview-05-06"
+    contents = [
+        types.Content(
+            role="user",
+            parts=[
+                types.Part.from_bytes(
+                    mime_type="image/jpeg",
+                    data=base64_image,
+                ),
+                types.Part.from_text(text=chess_prompt),
+            ],
+        ),
+    ]
+    generate_content_config = types.GenerateContentConfig(
+        temperature=0.15,
+        response_mime_type="text/plain",
+    )
+
+    for chunk in client.models.generate_content_stream(
+        model=model,
+        contents=contents,
+        config=generate_content_config,
+    ):
+        print(chunk.text, end="")
+
+if __name__ == "__main__":
+    generate()

test.py

@@ -0,0 +1,22 @@
+import requests
+import pandas as pd
+from io import BytesIO
+
+# URL of the Excel file
+url = r'https://datamillnorth.org/download/2nx5n/a3be8bde-b1d5-4da1-bdf9-258c994c6960/Copy%20of%20Q1%2023-24%20Data%20Mill.xlsx'
+
+# Send a GET request to the URL
+response = requests.get(url)
+
+# Check if the request was successful
+if response.status_code == 200:
+    # Use BytesIO to read the content of the response as a binary stream
+    excel_file = BytesIO(response.content)
+    
+    # Read the Excel file into a DataFrame
+    df = pd.read_excel(excel_file)
+    
+    # Display the DataFrame
+    print(df)
+else:
+    print(f"Failed to retrieve the file. Status code: {response.status_code}")