update tools

agent.py

@@ -16,6 +16,19 @@ from langchain_community.vectorstores import SupabaseVectorStore
 from langchain_openai import ChatOpenAI
 from langchain_core.documents import Document
 import json
+import pdfplumber
+import pandas as pd
+from transformers import BlipProcessor, BlipForConditionalGeneration
+from PIL import Image
+import torch
+import cmath
+from code_interpreter import CodeInterpreter
+import uuid
+import tempfile
+import requests
+from urllib.parse import urlparse
+from typing import Optional
+
 
 load_dotenv()
 
@@ -47,6 +60,28 @@ def modulus(a: int, b: int) -> int:
     """Get remainder of a divided by b."""
     return a % b
 
+@tool
+def square_root(a: float) -> float | complex:
+    """
+    Get the square root of a number.
+    Args:
+        a (float): the number to get the square root of
+    """
+    if a >= 0:
+        return a**0.5
+    return cmath.sqrt(a)
+
+@tool
+def power(a: float, b: float) -> float:
+    """
+    Get the power of two numbers.
+    Args:
+        a (float): the first number
+        b (float): the second number
+    """
+    return a**b
+
+
 @tool
 def wiki_search(query: str) -> str:
     """Search Wikipedia for a query (max 2 results)."""
@@ -80,10 +115,183 @@ def read_excel_file(path: str) -> str:
         return content.strip()
     except Exception as e:
         return f"Error reading Excel file: {str(e)}"
+    
+@tool
+def extract_text_from_pdf(path: str) -> str:
+    """Extract text from a PDF file given its local path."""
+    try:
+        text = ""
+        with pdfplumber.open(path) as pdf:
+            for page in pdf.pages[:5]:  # 限前5页，避免过大
+                page_text = page.extract_text()
+                if page_text:
+                    text += page_text + "\n\n"
+        return text.strip() if text else "No text extracted from PDF."
+    except Exception as e:
+        return f"Error reading PDF: {str(e)}"
+
+# 初始化模型（首次加载可能稍慢）
+processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
+model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")
+
+@tool
+def blip_image_caption(image_path: str) -> str:
+    """Generate a description for an image using BLIP."""
+    try:
+        image = Image.open(image_path).convert("RGB")
+        inputs = processor(image, return_tensors="pt")
+        with torch.no_grad():
+            out = model.generate(**inputs)
+        caption = processor.decode(out[0], skip_special_tokens=True)
+        return caption
+    except Exception as e:
+        return f"Failed to process image with BLIP: {str(e)}"
+    
+@tool
+def execute_code_multilang(code: str, language: str = "python") -> str:
+    """Execute code in multiple languages (Python, Bash, SQL, C, Java) and return results.
+    Args:
+        code (str): The source code to execute.
+        language (str): The language of the code. Supported: "python", "bash", "sql", "c", "java".
+    Returns:
+        A string summarizing the execution results (stdout, stderr, errors, plots, dataframes if any).
+    """
+    supported_languages = ["python", "bash", "sql", "c", "java"]
+    language = language.lower()
+    interpreter_instance = CodeInterpreter()
+
+    if language not in supported_languages:
+        return f"❌ Unsupported language: {language}. Supported languages are: {', '.join(supported_languages)}"
+
+    result = interpreter_instance.execute_code(code, language=language)
+
+    response = []
+
+    if result["status"] == "success":
+        response.append(f"✅ Code executed successfully in **{language.upper()}**")
+
+        if result.get("stdout"):
+            response.append(
+                "\n**Standard Output:**\n```\n" + result["stdout"].strip() + "\n```"
+            )
+
+        if result.get("stderr"):
+            response.append(
+                "\n**Standard Error (if any):**\n```\n"
+                + result["stderr"].strip()
+                + "\n```"
+            )
+
+        if result.get("result") is not None:
+            response.append(
+                "\n**Execution Result:**\n```\n"
+                + str(result["result"]).strip()
+                + "\n```"
+            )
 
+        if result.get("dataframes"):
+            for df_info in result["dataframes"]:
+                response.append(
+                    f"\n**DataFrame `{df_info['name']}` (Shape: {df_info['shape']})**"
+                )
+                df_preview = pd.DataFrame(df_info["head"])
+                response.append("First 5 rows:\n```\n" + str(df_preview) + "\n```")
 
+        if result.get("plots"):
+            response.append(
+                f"\n**Generated {len(result['plots'])} plot(s)** (Image data returned separately)"
+            )
+
+    else:
+        response.append(f"❌ Code execution failed in **{language.upper()}**")
+        if result.get("stderr"):
+            response.append(
+                "\n**Error Log:**\n```\n" + result["stderr"].strip() + "\n```"
+            )
 
-tools = [multiply, add, subtract, divide, modulus, wiki_search, web_search, arvix_search, read_excel_file]
+    return "\n".join(response)
+
+@tool
+def save_and_read_file(content: str, filename: Optional[str] = None) -> str:
+    """
+    Save content to a file and return the path.
+    Args:
+        content (str): the content to save to the file
+        filename (str, optional): the name of the file. If not provided, a random name file will be created.
+    """
+    temp_dir = tempfile.gettempdir()
+    if filename is None:
+        temp_file = tempfile.NamedTemporaryFile(delete=False, dir=temp_dir)
+        filepath = temp_file.name
+    else:
+        filepath = os.path.join(temp_dir, filename)
+
+    with open(filepath, "w") as f:
+        f.write(content)
+
+    return f"File saved to {filepath}. You can read this file to process its contents."
+
+
+@tool
+def download_file_from_url(url: str, filename: Optional[str] = None) -> str:
+    """
+    Download a file from a URL and save it to a temporary location.
+    Args:
+        url (str): the URL of the file to download.
+        filename (str, optional): the name of the file. If not provided, a random name file will be created.
+    """
+    try:
+        # Parse URL to get filename if not provided
+        if not filename:
+            path = urlparse(url).path
+            filename = os.path.basename(path)
+            if not filename:
+                filename = f"downloaded_{uuid.uuid4().hex[:8]}"
+
+        # Create temporary file
+        temp_dir = tempfile.gettempdir()
+        filepath = os.path.join(temp_dir, filename)
+
+        # Download the file
+        response = requests.get(url, stream=True)
+        response.raise_for_status()
+
+        # Save the file
+        with open(filepath, "wb") as f:
+            for chunk in response.iter_content(chunk_size=8192):
+                f.write(chunk)
+
+        return f"File downloaded to {filepath}. You can read this file to process its contents."
+    except Exception as e:
+        return f"Error downloading file: {str(e)}"
+    
+@tool
+def analyze_csv_file(file_path: str, query: str) -> str:
+    """
+    Analyze a CSV file using pandas and answer a question about it.
+    Args:
+        file_path (str): the path to the CSV file.
+        query (str): Question about the data
+    """
+    try:
+        # Read the CSV file
+        df = pd.read_csv(file_path)
+
+        # Run various analyses based on the query
+        result = f"CSV file loaded with {len(df)} rows and {len(df.columns)} columns.\n"
+        result += f"Columns: {', '.join(df.columns)}\n\n"
+
+        # Add summary statistics
+        result += "Summary statistics:\n"
+        result += str(df.describe())
+
+        return result
+
+    except Exception as e:
+        return f"Error analyzing CSV file: {str(e)}"
+tools = [multiply, add, subtract, divide, modulus, 
+         wiki_search, web_search, arvix_search, read_excel_file, extract_text_from_pdf,
+         blip_image_caption, execute_code_multilang, save_and_read_file, download_file_from_url, analyze_csv_file]
 
 # ------------------- SYSTEM PROMPT -------------------
 system_prompt_path = "system_prompt.txt"

requirements.txt

@@ -24,4 +24,5 @@ beautifulsoup4
 transformers 
 torch 
 torchvision 
-pillow
+pillow
+matplotlib