File size: 2,959 Bytes
bd73133
e7b4937
bd73133
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
24cb1b4
bd73133
5890f66
bd73133
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
38cc8e4
 
 
f1b095a
 
38cc8e4
bd73133
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c9e941b
9fb23b8
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
# GAIA Benchmark Agent - Dependencies
# Author: @mangubee
# Date: 2026-01-01

# ============================================================================
# LangGraph Framework (Level 6 - Implementation Framework)
# ============================================================================
langgraph>=0.2.0
langchain>=0.3.0
langchain-core>=0.3.0

# ============================================================================
# LLM SDKs (Level 5 - Component Selection)
# ============================================================================
# Primary: Claude Sonnet 4.5
anthropic>=0.39.0

# Free baseline alternatives
google-generativeai>=0.8.0  # Gemini 2.0 Flash (current SDK used in code)
huggingface-hub>=0.26.0     # For HF Inference API (Qwen, Llama)
groq>=0.4.0                 # Groq API (Llama 3.1 70B - free tier, 30 req/min)

# ============================================================================
# Tool Dependencies (Level 5 - Component Selection)
# ============================================================================
# Web search
exa-py>=1.0.0              # Exa API client
tavily-python>=0.5.0       # Tavily search API (default, free tier)
requests>=2.32.0           # HTTP requests fallback

# Python code interpreter
# (Using built-in exec/eval - no additional dependency)

# File readers (multi-format support)
PyPDF2>=3.0.0              # PDF reading
openpyxl>=3.1.0            # Excel files (.xlsx)
python-docx>=1.1.0         # Word documents
pillow>=10.4.0             # Image files (JPEG, PNG, etc.)

# Multi-modal processing (vision)
# (Using LLM native vision capabilities - no additional dependency)

# Audio/Video processing (Phase 1: YouTube support)
youtube-transcript-api>=0.6.0  # YouTube transcript extraction
openai-whisper>=20231117       # Audio transcription ( Whisper)
yt-dlp>=2024.0.0               # Audio/video extraction from YouTube
opencv-python>=4.8.0           # Frame extraction from video

# ============================================================================
# Existing Dependencies (from current app.py)
# ============================================================================
gradio>=4.0.0              # UI framework
gradio[oauth]              # OAuth integration
pandas>=2.2.0              # Data manipulation

# ============================================================================
# Development & Testing
# ============================================================================
pytest>=8.0.0              # Testing framework
python-dotenv>=1.0.0       # Environment variable management

# ============================================================================
# Utilities
# ============================================================================
pydantic>=2.0.0            # Data validation (for StateGraph)
typing-extensions>=4.12.0  # Type hints support
tenacity>=9.1.2            # Retry logic with exponential backoff
datasets==4.4.2