tools/langchain_tools.py

# tools/langchain_tools.py
"""
LangChain-compatible tool wrappers for our existing tools
Complete integration of multimodal, search, math, and YouTube tools
"""

from langchain_core.tools import tool
from typing import Optional
import os
from dotenv import load_dotenv

# Load environment variables FIRST, before any tool imports
load_dotenv()

from .multimodal_tools import MultimodalTools, analyze_transcript as _analyze_transcript, analyze_excel, analyze_python
from .search_tools import SearchTools
from .math_tools import MathTools
from .youtube_tools import YouTubeTools
from .wikipedia_tools import search_wikipedia, get_wikipedia_page, wikipedia_summary

# Initialize tool instances (now env vars are available)
multimodal_tools = MultimodalTools()
search_tools = SearchTools()
youtube_tools = YouTubeTools()

# =============================================================================
# MULTIMODAL TOOLS
# =============================================================================

@tool
def extract_text(image_path: str) -> str:
    """Extract text from an image using OCR"""
    return multimodal_tools.extract_text_from_image(image_path)

@tool
def analyze_image_tool(image_path: str, question: str = "Describe this image in detail") -> str:
    """Analyze an image and answer questions about it"""
    return multimodal_tools.analyze_image(image_path, question)

@tool
def analyze_audio_tool(transcript: str, question: str = "Summarize this audio content") -> str:
    """Analyze audio content via transcript"""
    return multimodal_tools.analyze_audio_transcript(transcript, question)

@tool
def analyze_excel_tool(file_path: str, question: str) -> str:
    """Analyze Excel or CSV files to answer questions about the data"""
    return analyze_excel(file_path, question)

# =============================================================================
# SEARCH TOOLS
# =============================================================================

@tool
def search_tool(query: str, max_results: int = 10) -> str:
    """Search the web for information"""
    results = search_tools.search(query, max_results)
    if not results:
        return "No search results found"
    
    # Format results for the LLM
    formatted_results = []
    for i, result in enumerate(results, 1):
        title = result.get('title', 'No title')
        content = result.get('content', 'No content')
        url = result.get('url', 'No URL')
        formatted_results.append(f"{i}. {title}\n{content[:200]}...\nSource: {url}\n")
    
    return "\n".join(formatted_results)

@tool
def search_news_tool(query: str, max_results: int = 10) -> str:
    """Search for news articles about a topic"""
    results = search_tools.search_news(query, max_results)
    if not results:
        return "No news results found"
    
    # Format results for the LLM
    formatted_results = []
    for i, result in enumerate(results, 1):
        title = result.get('title', 'No title')
        content = result.get('content', 'No content')
        url = result.get('url', 'No URL')
        formatted_results.append(f"{i}. {title}\n{content[:200]}...\nSource: {url}\n")
    
    return "\n".join(formatted_results)

@tool
def search_academic_tool(query: str, max_results: int = 10) -> str:
    """Search for academic research and papers"""
    results = search_tools.search_academic(query, max_results)
    if not results:
        return "No academic results found"
    
    # Format results for the LLM
    formatted_results = []
    for i, result in enumerate(results, 1):
        title = result.get('title', 'No title')
        content = result.get('content', 'No content')
        url = result.get('url', 'No URL')
        formatted_results.append(f"{i}. {title}\n{content[:200]}...\nSource: {url}\n")
    
    return "\n".join(formatted_results)

# =============================================================================
# YOUTUBE TOOLS
# =============================================================================

@tool
def extract_youtube_transcript(url: str, language_code: str = 'en') -> str:
    """Extract transcript/captions from a YouTube video"""
    captions = youtube_tools.get_captions(url, language_code)
    if captions:
        return captions
    else:
        return "No captions available for this video"

@tool
def get_youtube_info(url: str) -> str:
    """Get information about a YouTube video"""
    info = youtube_tools.get_video_info(url)
    if info:
        return f"Title: {info.get('title', 'Unknown')}\nAuthor: {info.get('author', 'Unknown')}\nDuration: {info.get('length', 0)} seconds\nViews: {info.get('views', 0):,}"
    else:
        return "Could not retrieve video information"

@tool
def get_youtube_playlist_info(playlist_url: str) -> str:
    """Get information about a YouTube playlist"""
    info = youtube_tools.get_playlist_info(playlist_url)
    if info:
        return f"Playlist: {info.get('title', 'Unknown')}\nVideos: {info.get('video_count', 0)}\nOwner: {info.get('owner', 'Unknown')}"
    else:
        return "Could not retrieve playlist information"

# =============================================================================
# MATH TOOLS - Basic Operations
# =============================================================================

@tool
def add(a: float, b: float) -> float:
    """Add two numbers"""
    return MathTools.add(a, b)

@tool
def subtract(a: float, b: float) -> float:
    """Subtract two numbers"""
    return MathTools.subtract(a, b)

@tool
def multiply(a: float, b: float) -> float:
    """Multiply two numbers"""
    return MathTools.multiply(a, b)

@tool
def divide(a: float, b: float) -> str:
    """Divide two numbers"""
    result = MathTools.divide(a, b)
    return str(result)

@tool
def power(base: float, exponent: float) -> float:
    """Calculate base raised to the power of exponent"""
    return MathTools.power(base, exponent)

# =============================================================================
# MATH TOOLS - Advanced Operations
# =============================================================================

@tool
def factorial(n: int) -> str:
    """Calculate factorial of a number"""
    result = MathTools.factorial(n)
    return str(result)

@tool
def square_root(n: float) -> str:
    """Calculate square root of a number"""
    result = MathTools.square_root(n)
    return str(result)

@tool
def percentage(part: float, whole: float) -> str:
    """Calculate percentage"""
    result = MathTools.percentage(part, whole)
    return str(result)

@tool
def average(numbers: str) -> str:
    """Calculate average of numbers (provide as comma-separated string)"""
    try:
        number_list = [float(x.strip()) for x in numbers.split(',')]
        result = MathTools.average(number_list)
        return str(result)
    except Exception as e:
        return f"Error parsing numbers: {str(e)}"

@tool
def calculate_expression(expression: str) -> str:
    """Calculate a mathematical expression safely"""
    from .math_tools import calculate_expression as calc_expr
    return str(calc_expr(expression))

@tool
def absolute_value(n: float) -> float:
    """Calculate absolute value of a number"""
    return MathTools.absolute(n)

@tool
def round_number(n: float, decimals: int = 2) -> float:
    """Round number to specified decimal places"""
    return MathTools.round_number(n, decimals)

@tool
def min_value(numbers: str) -> str:
    """Find minimum value in a list of numbers (provide as comma-separated string)"""
    try:
        number_list = [float(x.strip()) for x in numbers.split(',')]
        result = MathTools.min_value(number_list)
        return str(result)
    except Exception as e:
        return f"Error parsing numbers: {str(e)}"

@tool
def max_value(numbers: str) -> str:
    """Find maximum value in a list of numbers (provide as comma-separated string)"""
    try:
        number_list = [float(x.strip()) for x in numbers.split(',')]
        result = MathTools.max_value(number_list)
        return str(result)
    except Exception as e:
        return f"Error parsing numbers: {str(e)}"

@tool
def compound_interest(principal: float, rate: float, time: float, compounds_per_year: int = 1) -> str:
    """Calculate compound interest"""
    result = MathTools.calculate_compound_interest(principal, rate, time, compounds_per_year)
    return str(result)

@tool
def solve_quadratic(a: float, b: float, c: float) -> str:
    """Solve quadratic equation ax² + bx + c = 0"""
    result = MathTools.solve_quadratic(a, b, c)
    return str(result)

@tool
def analyze_python_tool(file_path: str, question: str = "What is the final output of this code?") -> str:
    """Read and analyze Python code files, can execute code to get results"""
    return analyze_python(file_path, question)
# =============================================================================
# TOOL COLLECTIONS FOR EASY IMPORT
# =============================================================================
@tool
def analyze_youtube_frames(url: str, question: str = "Describe what happens in this video") -> str:
    """Extract frames from YouTube video and analyze visual content"""
    youtube_tools = YouTubeTools()
    return youtube_tools.analyze_video_content(url, question)

@tool
def extract_video_slides(url: str) -> str:
    """Extract and analyze slides from educational YouTube videos"""
    youtube_tools = YouTubeTools()
    results = youtube_tools.analyze_video_slides(url)
    
    if 'error' in results:
        return results['error']
    
    # Format slide analysis for LLM
    slide_content = []
    for frame in results.get('frames_analyzed', []):
        if 'slide' in frame.get('analysis', '').lower():
            slide_content.append(f"Slide {frame['frame_number']}: {frame['analysis']}")
    
    if slide_content:
        return "\n\n".join(slide_content)
    else:
        return results.get('analysis_summary', 'No slides detected in video')
# Add Wikipedia tools
@tool
def search_wikipedia_tool(query: str, language: str = 'en') -> str:
    """Search Wikipedia for information about a topic"""
    return search_wikipedia(query, language)

@tool
def get_wikipedia_page_tool(page_title: str, language: str = 'en') -> str:
    """Retrieve a specific Wikipedia page by title"""
    return get_wikipedia_page(page_title, language)

@tool
def wikipedia_summary_tool(query: str, language: str = 'en') -> str:
    """Get a concise Wikipedia summary about a topic"""
    return wikipedia_summary(query, language)

# Core tools (matching original template)
CORE_TOOLS = [
    extract_text,
    analyze_image_tool,
    analyze_audio_tool,
    extract_youtube_transcript,
    add,
    subtract,
    multiply,
    divide,
    search_tool
]

# Extended tools with new Excel functionality
EXTENDED_TOOLS = CORE_TOOLS + [
    analyze_excel_tool,  # NEW: Excel/CSV analysis
     analyze_youtube_frames,  # ✅ NEW: Frame extraction and analysis
    extract_video_slides,    # ✅ NEW: Slide detection
    analyze_python_tool,
    search_news_tool,
     search_wikipedia_tool,      # ✅ NEW: Wikipedia search
    get_wikipedia_page_tool,    # ✅ NEW: Specific Wikipedia pages
    wikipedia_summary_tool,     # ✅ NEW: Wikipedia summaries
    search_academic_tool,
    get_youtube_info,
    get_youtube_playlist_info,
    calculate_expression,
    factorial,
    square_root,
    percentage,
    average
]

# All available tools
ALL_TOOLS = EXTENDED_TOOLS + [
    power,
    absolute_value,
    round_number,
    min_value,
    max_value,
    compound_interest,
    solve_quadratic
]

# Default export (for backwards compatibility)
tools = CORE_TOOLS