clean up project repo

.gitignore

@@ -51,6 +51,17 @@ venv.bak/
 .pytest_cache/
 .coverage
 htmlcov/
+.tox/
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+
+# Test artifacts and outputs
+tests/output/
+tests/results/
+test_results/
+*.test
 
 # Database files (if downloading local copies)
 *.db

DATABASE_README.md

@@ -1,6 +1,6 @@
 # GAIA Agent with Database Search Integration
 
-This enhanced GAIA agent system includes semantic search against your Supabase database to find similar questions before processing new ones, improving both accuracy and efficiency.
+This enhanced GAIA agent system includes semantic search against a Supabase database to find similar questions before processing new ones, improving both accuracy and efficiency.
 
 ## 🏗️ Architecture
 
@@ -46,7 +46,7 @@ agents-course-v2/
 ```
 
 ### 2. Example Database Entries
-Your database contains 165 GAIA Q&A pairs like:
+The database contains 165 GAIA Q&A pairs like:
 ```json
 {
   "question": "A paper about AI regulation submitted to arXiv.org in June 2022...",
@@ -64,11 +64,11 @@ The system uses:
 ## 🛠️ Setup
 
 ### 1. Environment Variables
-Add to your `.env` file:
+Add to the `.env` file:
 ```env
-OPENAI_API_KEY=your_openai_key
-SUPABASE_URL=your_supabase_url  
-SUPABASE_SERVICE_KEY=your_SUPABASE_SERVICE_KEY
+OPENAI_API_KEY=openai_api_key
+SUPABASE_URL=supabase_url  
+SUPABASE_SERVICE_KEY=supabase_service_key
 ```
 
 ### 2. Install Dependencies
@@ -126,4 +126,4 @@ answer = answer_gaia_question(
 - **Strategy**: Database-enhanced agent coordination
 - **Focus**: Exact answer formatting and efficient tool usage
 
-This system leverages your existing 165 GAIA Q&A pairs to bootstrap better performance on new questions, making your agent more competitive on the leaderboard!
+This system leverages existing 165 GAIA Q&A pairs to bootstrap better performance on new questions, making the agent more competitive on the leaderboard!

SUPABASE_SETUP.md

@@ -9,7 +9,7 @@ This SQL function enables efficient vector similarity search:
 ```sql
 -- Create the similarity search function for LangChain integration
 create or replace function match_documents_langchain (
-  query_embedding vector(1536),  -- Adjust dimension based on your embedding model
+  query_embedding vector(1536),  -- Adjust dimension based on embedding model
   match_threshold float default 0.75,
   match_count int default 3
 )
@@ -74,9 +74,9 @@ end;
 $$;
 ```
 
-### 3. Update Your Database Table Structure
+### 3. Update Database Table Structure
 
-Ensure your `documents` table has the right structure:
+Ensure the `documents` table has the right structure:
 
 ```sql
 -- Check/create the documents table structure
@@ -96,17 +96,17 @@ WITH (lists = 100);
 
 ### 4. Environment Variables
 
-Update your `.env` file:
+Update the `.env` file:
 
 ```env
 # Required for both approaches
-SUPABASE_URL=your_supabase_project_url
-SUPABASE_SERVICE_KEY=your_SUPABASE_SERVICE_KEY
+SUPABASE_URL=supabase_project_url
+SUPABASE_SERVICE_KEY=supabase_service_key
 # Alternative key name (some setups use this)
-SUPABASE_KEY=your_SUPABASE_SERVICE_KEY
+SUPABASE_KEY=supabase_service_key
 
 # Optional: For OpenAI fallback
-OPENAI_API_KEY=your_openai_api_key
+OPENAI_API_KEY=openai_api_key
 ```
 
 ## Performance Comparison
@@ -123,7 +123,7 @@ OPENAI_API_KEY=your_openai_api_key
 ❌ **Costs money per embedding**
 ❌ **API rate limits**
 
-## Testing Your Setup
+## Testing the Setup
 
 1. **Test the function exists:**
 ```sql

agent.py

@@ -33,8 +33,6 @@ os.environ["TOKENIZERS_PARALLELISM"] = "false"
 llm = ChatOpenAI(model="gpt-4o", temperature=0)
 
 
-
-
 # ─────────────────────────────────────────────────────────────────────────────
 # SIMPLE AGENT SETUP (following course pattern)
 # ─────────────────────────────────────────────────────────────────────────────
@@ -106,7 +104,7 @@ def should_continue(state: MessagesState):
 builder.add_node("agent", gaia_agent)
 builder.add_node("tools", ToolNode(ALL_TOOLS))
 
-# Add edges - much simpler!
+# Add edges
 builder.add_edge(START, "agent")
 builder.add_conditional_edges("agent", should_continue)
 builder.add_edge("tools", "agent")  # Return to agent after using tools

app.py

@@ -6,21 +6,9 @@ import pandas as pd
 from agent import graph
 from langchain_core.messages import HumanMessage
 
-# (Keep Constants as is)
-# --- Constants ---
+# Constants
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
-# class BasicAgent:
-#     def __init__(self):
-#         print("BasicAgent initialized.")
-#     def __call__(self, question: str) -> str:
-#         print(f"Agent received question (first 50 chars): {question[:50]}...")
-#         fixed_answer = "This is a default answer."
-#         print(f"Agent returning fixed answer: {fixed_answer}")
-#         return fixed_answer
-    
 class GaiaAgent:
     def __init__(self):
         print("Graph-based agent initialized.")

tests/README.md

@@ -0,0 +1,37 @@
+# Tests
+
+This directory contains test files for the GAIA agent system.
+
+## Test Files
+
+- `test_database.py` - Tests database search integration and similarity matching
+- `test_single.py` - Single question test for debugging specific issues
+- `test_routing.py` - Tests intelligent routing and agent decision-making
+
+## Running Tests
+
+Make sure to activate the virtual environment first:
+
+```bash
+source .venv/bin/activate
+```
+
+Then run individual tests:
+
+```bash
+python tests/test_database.py
+python tests/test_single.py
+python tests/test_routing.py
+```
+
+## Test Structure
+
+All test files include the necessary path setup to import modules from the parent directory:
+
+```python
+import sys
+import os
+sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+```
+
+This allows the tests to import from the main project modules while being organized in a separate directory.

test_database.py → tests/test_database.py

@@ -1,9 +1,14 @@
 """
 Example usage of the GAIA agent with database search integration.
-This shows how the system works with your Supabase database.
+This shows how the system works with the Supabase database.
 """
 
 import os
+import sys
+
+# Add parent directory to path for imports
+sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
 from agent import answer_gaia_question
 from tools.database_tools import get_retriever
 

test_routing.py → tests/test_routing.py

@@ -2,6 +2,12 @@
 Test the intelligent routing system to show how the orchestrator makes decisions.
 """
 
+import os
+import sys
+
+# Add parent directory to path for imports
+sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
 from agent import answer_gaia_question
 
 def test_intelligent_routing():

test_single.py → tests/test_single.py

@@ -3,6 +3,11 @@ Test a single problematic question to debug the routing logic.
 """
 
 import os
+import sys
+
+# Add parent directory to path for imports
+sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
 from agent import answer_gaia_question
 from tools.database_tools import get_retriever
 

tools/__init__.py

@@ -4,7 +4,7 @@ Import tools from their respective modules.
 """
 
 from .file_tools import read_excel_file, read_csv_file, calculate_column_sum
-from .research_tools import web_search, get_company_info, verify_fact  
+from .research_tools import web_search
 from .math_tools import calculate_expression, percentage_calculation, currency_format, statistical_summary
 from .database_tools import search_similar_gaia_questions, get_exact_answer_if_highly_similar
 
@@ -12,7 +12,7 @@ from .database_tools import search_similar_gaia_questions, get_exact_answer_if_h
 FILE_TOOLS = [read_excel_file, read_csv_file, calculate_column_sum]
 
 # Research tools  
-RESEARCH_TOOLS = [web_search, get_company_info, verify_fact]
+RESEARCH_TOOLS = [web_search]
 
 # Mathematical tools
 MATH_TOOLS = [calculate_expression, percentage_calculation, currency_format, statistical_summary]

tools/research_tools.py

@@ -19,36 +19,8 @@ def web_search(query: str, max_results: int = 5) -> str:
     Returns:
         Search results as formatted text
     """
-    # Implement with your preferred search API (DuckDuckGo, Serper, etc.)
-    # This is a placeholder - replace with actual search implementation
+    # TODO:Implement search API (Tavily or DuckDuckGo)
     return f"Search results for: {query}"
 
-@tool
-def get_company_info(company_name: str) -> str:
-    """
-    Get basic information about a company.
-    
-    Args:
-        company_name: Name of the company
-    
-    Returns:
-        Company information
-    """
-    # Implement company lookup logic
-    return f"Information about {company_name}"
-
-@tool
-def verify_fact(claim: str) -> str:
-    """
-    Verify a factual claim using multiple sources.
-    
-    Args:
-        claim: The claim to verify
-    
-    Returns:
-        Verification result
-    """
-    # Implement fact verification logic
-    return f"Verification result for: {claim}"
 
-# Add more research tools as needed
+# TODO: Add more research tools as needed (e.g., Wikipedia, Arxiv, etc.)

utils/supbase_fill.py

@@ -14,11 +14,11 @@ SUPABASE_SERVICE_KEY = os.getenv("SUPABASE_SERVICE_KEY")
 HF_TOKEN             = os.getenv("HUGGINGFACE_API_TOKEN")
 
 if not SUPABASE_URL or not SUPABASE_SERVICE_KEY:
-    raise RuntimeError("Please set SUPABASE_URL and SUPABASE_SERVICE_KEY in your .env")
+    raise RuntimeError("Set SUPABASE_URL and SUPABASE_SERVICE_KEY in your .env")
 
 if not HF_TOKEN:
     raise RuntimeError(
-        "Please set HUGGINGFACE_API_TOKEN in your .env and ensure you've been granted access to the GAIA dataset."
+        "Set HUGGINGFACE_API_TOKEN in your .env and ensure you've been granted access to the GAIA dataset."
     )
 
 # -----------------------------------------------------------------------------