File size: 5,370 Bytes
21f89f6 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 |
from langchain_core.tools import tool
from typing import List, Dict, Any, Optional
import tempfile
from urllib.parse import urlparse
import os
import uuid
import requests
from PIL import Image
import pytesseract
import pandas as pd
import docx
import fitz
@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 extract_text_from_image(image_path: str) -> str:
"""
Extract text from an image using OCR library pytesseract (if available).
Args:
image_path (str): the path to the image file.
"""
try:
# Open the image
image = Image.open(image_path)
# Extract text from the image
text = pytesseract.image_to_string(image)
return f"Extracted text from image:\n\n{text}"
except Exception as e:
return f"Error extracting text from image: {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)}"
@tool
def analyze_excel_file(file_path: str, query: str) -> str:
"""
Analyze an Excel file using pandas and answer a question about it.
Args:
file_path (str): the path to the Excel file.
query (str): Question about the data
"""
try:
# Read the Excel file
df = pd.read_excel(file_path)
# Run various analyses based on the query
result = (
f"Excel 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 Excel file: {str(e)}"
@tool
def analyze_word_file(file_path: str, query: str) -> str:
"""
Analyze a Word (.docx) document and summarize its contents.
Args:
file_path (str): path to the .docx file.
query (str): Question or instruction regarding the document content.
"""
try:
doc = docx.Document(file_path)
full_text = "\n".join(
[para.text for para in doc.paragraphs if para.text.strip()])
return f"Word document loaded. Length: {len(full_text)} characters.\nPreview:\n{full_text[:1000]}"
except Exception as e:
return f"Error analyzing Word document: {str(e)}"
@tool
def analyze_pdf_file(file_path: str, query: str) -> str:
"""
Analyze a PDF file and summarize its contents.
Args:
file_path (str): path to the PDF file.
query (str): Question or instruction regarding the document content.
"""
try:
doc = fitz.open(file_path)
text = ""
for page in doc:
text += page.get_text()
return f"PDF loaded. Length: {len(text)} characters.\nPreview:\n{text[:1000]}"
except Exception as e:
return f"Error analyzing PDF: {str(e)}"
|