Upload 9 files

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -1,4 +1,2 @@
----
-license: apache-2.0
----
-hi
+# bloomington-guide
+The repository consists of the code for creation of the dataset and training the small language models via model distillation.

config.py

@@ -0,0 +1,53 @@
+import os
+from pathlib import Path
+
+# API Keys
+SERP_API_KEY = "2d78ac7b2491065a206825e614a2f20e6f70f90a7958463883f58ae2c2f55bae"
+GEMINI_API_KEY = "AIzaSyAPf9oyyb0l9vQcP46Yh1SkG1dE8GvJJv0"
+
+# API Limits
+SERP_MONTHLY_LIMIT = 80
+GEMINI_RATE_LIMIT = 10  # requests per minute
+PAIRS_PER_PROMPT = 5
+TARGET_QA_PAIRS = 1000
+
+# Project Paths
+PROJECT_ROOT = Path(__file__).parent
+DATA_DIR = PROJECT_ROOT / "data"
+RAW_DIR = DATA_DIR / "raw"
+PROCESSED_DIR = DATA_DIR / "processed"
+FINAL_DIR = DATA_DIR / "final"
+LOG_DIR = PROJECT_ROOT / "logs"
+
+# Create directories if they don't exist
+for dir_path in [DATA_DIR, RAW_DIR, PROCESSED_DIR, FINAL_DIR, LOG_DIR]:
+    dir_path.mkdir(parents=True, exist_ok=True)
+
+# Search Queries
+SEARCH_QUERIES = {
+    "attractions": [
+        "Bloomington Indiana tourist attractions",
+        "Indiana University landmarks",
+        "Bloomington cultural venues"
+    ],
+    "dining": [
+        "Best restaurants Bloomington Indiana",
+        "Bloomington cafes and bars",
+        "Food trucks Bloomington IN"
+    ],
+    "events": [
+        "Events in Bloomington Indiana",
+        "Festivals Bloomington IN",
+        "Concerts Bloomington Indiana"
+    ],
+    "outdoor": [
+        "Bloomington parks and recreation",
+        "Hiking trails Bloomington IN",
+        "Lake Monroe activities"
+    ],
+    "accommodation": [
+        "Hotels Bloomington Indiana",
+        "B&B Bloomington IN",
+        "Student housing IU Bloomington"
+    ]
+}

generator.py

@@ -0,0 +1,286 @@
+import json
+import time
+import logging
+import re
+from datetime import datetime
+from typing import Dict, List, Tuple
+import google.generativeai as genai
+from tqdm import tqdm
+import pandas as pd
+
+from config import (
+    GEMINI_API_KEY, GEMINI_RATE_LIMIT, PAIRS_PER_PROMPT,
+    TARGET_QA_PAIRS, PROCESSED_DIR, FINAL_DIR, LOG_DIR
+)
+
+class QAPairGenerator:
+    def __init__(self):
+        # Configure Gemini
+        genai.configure(api_key=GEMINI_API_KEY)
+        self.model = genai.GenerativeModel('gemini-1.5-flash')
+        
+        # Set up logging
+        log_file = LOG_DIR / f"generator_{datetime.now().strftime('%Y%m%d_%H%M%S')}.log"
+        logging.basicConfig(
+            level=logging.INFO,
+            format='%(asctime)s - %(levelname)s - %(message)s',
+            filename=log_file
+        )
+        
+        self.generated_pairs = []
+        self.failed_generations = []
+        self.total_pairs_generated = 0  # Add counter for total pairs
+
+    def _generate_qa_batch(self, content: str, category: str) -> List[Dict]:
+        """Generate a batch of QA pairs from content using regex parsing"""
+        prompt = f"""
+        Based on the following content about Bloomington, Indiana, generate {PAIRS_PER_PROMPT} different instruction-response pairs.
+        The content is related to the category: {category}
+        
+        Focus on creating specific, practical questions that tourists might ask, with detailed, actionable responses.
+        Include relevant details like operating hours, costs, locations, and tips when applicable.
+        
+        Format your response EXACTLY as a JSON array with each object containing "instruction", "response", and "category" fields.
+        
+        Example format:
+        [
+            {{
+                "instruction": "What are the peak times to visit the Sample Gardens and how much does it cost?",
+                "response": "Sample Gardens is busiest during weekends and holidays. Admission is $10 for adults, $5 for children (5-12), and free for children under 5. To avoid crowds, visit on weekday mornings between 9-11am. Free parking is available.",
+                "category": "attractions"
+            }}
+        ]
+
+        Content: {content}
+        """
+        
+        try:
+            response = self.model.generate_content(prompt)
+            response_text = response.text.strip()
+            
+            # Try regex parsing first
+            try:
+                # Pattern to match the entire JSON array
+                array_pattern = r'\[\s*(\{[^]]*\})\s*(?:,\s*(\{[^]]*\})\s*)*\]'
+                array_match = re.search(array_pattern, response_text, re.DOTALL)
+                
+                if array_match:
+                    json_str = array_match.group(0)
+                    
+                    # Additional regex to validate individual objects
+                    object_pattern = r'\{\s*"instruction":\s*"([^"]*)",\s*"response":\s*"([^"]*)",\s*"category":\s*"([^"]*)"\s*\}'
+                    objects = re.finditer(object_pattern, json_str)
+                    
+                    valid_pairs = []
+                    for obj_match in objects:
+                        instruction = obj_match.group(1)
+                        response = obj_match.group(2)
+                        obj_category = obj_match.group(3)
+                        
+                        # Validate lengths
+                        if len(instruction) >= 20 and len(response) >= 50:
+                            valid_pairs.append({
+                                'instruction': instruction,
+                                'response': response,
+                                'category': category  # Use the passed category instead of the one in response
+                            })
+                        else:
+                            logging.warning(f"Pair rejected due to length requirements: Q: {len(instruction)} chars, A: {len(response)} chars")
+                    
+                    if valid_pairs:
+                        return valid_pairs
+                
+                logging.warning("Regex parsing failed, attempting JSON parsing as fallback")
+                
+            except Exception as regex_error:
+                logging.warning(f"Regex parsing error: {str(regex_error)}")
+            
+            # Fallback to JSON parsing
+            try:
+                # Find the first '[' and last ']' to extract JSON array
+                start_idx = response_text.find('[')
+                end_idx = response_text.rfind(']') + 1
+                
+                if start_idx != -1 and end_idx > start_idx:
+                    json_str = response_text[start_idx:end_idx]
+                    pairs = json.loads(json_str)
+                else:
+                    pairs = json.loads(response_text)
+                
+                # Validate pairs
+                valid_pairs = []
+                for pair in pairs:
+                    if (isinstance(pair, dict) and 
+                        'instruction' in pair and 
+                        'response' in pair and 
+                        isinstance(pair['instruction'], str) and 
+                        isinstance(pair['response'], str) and 
+                        len(pair['instruction']) >= 20 and 
+                        len(pair['response']) >= 50):
+                        
+                        pair['category'] = category
+                        valid_pairs.append(pair)
+                    else:
+                        logging.warning(f"Invalid pair structure or length: {pair}")
+                
+                return valid_pairs
+                
+            except json.JSONDecodeError as json_error:
+                logging.error(f"JSON parsing error: {str(json_error)}\nResponse text: {response_text}")
+                return []
+                
+        except Exception as e:
+            logging.error(f"Error in QA pair generation: {str(e)}")
+            self.failed_generations.append({
+                'content': content,
+                'category': category,
+                'error': str(e),
+                'response_text': response_text if 'response_text' in locals() else None,
+                'timestamp': datetime.now().isoformat()
+            })
+            return []
+
+    def generate_pairs_for_category(self, category: str) -> List[Dict]:
+        """Generate QA pairs for a specific category"""
+        input_file = PROCESSED_DIR / f"{category}_processed.json"
+        
+        try:
+            with open(input_file, 'r') as f:
+                processed_data = json.load(f)
+        except Exception as e:
+            logging.error(f"Error loading {input_file}: {e}")
+            return []
+
+        category_pairs = []
+        
+        # Calculate remaining pairs needed
+        remaining_pairs = TARGET_QA_PAIRS - self.total_pairs_generated
+        
+        if remaining_pairs <= 0:
+            logging.info("Target number of QA pairs reached")
+            return []
+
+        for item in tqdm(processed_data, desc=f"Generating pairs for {category}"):
+            if self.total_pairs_generated >= TARGET_QA_PAIRS:
+                logging.info(f"Target of {TARGET_QA_PAIRS} pairs reached. Stopping generation.")
+                break
+                
+            # Combine all available content
+            content = f"{item['title']} {item['snippet']}"
+            if 'additional_content' in item:
+                content += f" {item['additional_content']}"
+
+            pairs = self._generate_qa_batch(content, category)
+            
+            # Only take as many pairs as needed
+            pairs_needed = min(len(pairs), TARGET_QA_PAIRS - self.total_pairs_generated)
+            valid_pairs = pairs[:pairs_needed]
+            
+            category_pairs.extend(valid_pairs)
+            self.total_pairs_generated += len(valid_pairs)
+            
+            logging.info(f"Progress: {self.total_pairs_generated}/{TARGET_QA_PAIRS} pairs")
+            
+            if self.total_pairs_generated >= TARGET_QA_PAIRS:
+                break
+                
+            time.sleep(60/GEMINI_RATE_LIMIT)  # Respect rate limit
+        
+        # Save category pairs
+        output_file = FINAL_DIR / f"{category}_qa_pairs.json"
+        with open(output_file, 'w') as f:
+            json.dump(category_pairs, f, indent=2)
+        
+        return category_pairs
+
+    def generate_all_pairs(self) -> None:
+        """Generate QA pairs for all categories until target is reached"""
+        categories = [f.stem.replace('_processed', '') 
+                     for f in PROCESSED_DIR.glob('*_processed.json')]
+        
+        all_pairs = []
+        
+        # Keep generating pairs until we reach the target
+        while self.total_pairs_generated < TARGET_QA_PAIRS and categories:
+            for category in categories[:]:  # Create a copy to modify safely
+                if self.total_pairs_generated >= TARGET_QA_PAIRS:
+                    break
+                    
+                logging.info(f"Starting generation for category: {category}")
+                category_pairs = self.generate_pairs_for_category(category)
+                
+                if not category_pairs:  # If no more pairs can be generated for this category
+                    categories.remove(category)
+                    continue
+                    
+                all_pairs.extend(category_pairs)
+                logging.info(f"Generated {len(category_pairs)} pairs for {category}")
+                self._save_progress(all_pairs)
+                
+                if self.total_pairs_generated >= TARGET_QA_PAIRS:
+                    break
+            
+            # Check if we need to continue
+            if self.total_pairs_generated < TARGET_QA_PAIRS and not categories:
+                logging.warning(f"Exhausted all categories. Generated {self.total_pairs_generated}/{TARGET_QA_PAIRS} pairs")
+                break
+
+        # Save final results
+        self._save_final_results(all_pairs)
+
+    def _save_progress(self, pairs: List[Dict]) -> None:
+        """Save intermediate progress"""
+        timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
+        progress_file = FINAL_DIR / f"qa_pairs_progress_{timestamp}.json"
+        
+        progress_data = {
+            'pairs': pairs,
+            'stats': {
+                'total_pairs': len(pairs),
+                'target_pairs': TARGET_QA_PAIRS,
+                'completion_percentage': (self.total_pairs_generated / TARGET_QA_PAIRS) * 100,
+                'pairs_per_category': pd.DataFrame(pairs)['category'].value_counts().to_dict(),
+                'timestamp': timestamp
+            }
+        }
+        
+        with open(progress_file, 'w') as f:
+            json.dump(progress_data, f, indent=2)
+
+    def _save_final_results(self, pairs: List[Dict]) -> None:
+        """Save final results and statistics"""
+        final_file = FINAL_DIR / "final_qa_pairs.json"
+        
+        final_data = {
+            'pairs': pairs,
+            'stats': {
+                'total_pairs_generated': self.total_pairs_generated,
+                'target_pairs': TARGET_QA_PAIRS,
+                'completion_percentage': (self.total_pairs_generated / TARGET_QA_PAIRS) * 100,
+                'pairs_per_category': pd.DataFrame(pairs)['category'].value_counts().to_dict(),
+                'avg_instruction_length': pd.DataFrame(pairs)['instruction'].str.len().mean(),
+                'avg_response_length': pd.DataFrame(pairs)['response'].str.len().mean(),
+                'failed_generations': len(self.failed_generations),
+                'completion_timestamp': datetime.now().strftime('%Y-%m-%d %H:%M:%S')
+            }
+        }
+        
+        # Save main results
+        with open(final_file, 'w') as f:
+            json.dump(final_data, f, indent=2)
+        
+        # Save as CSV
+        df = pd.DataFrame(pairs)
+        df.to_csv(FINAL_DIR / "final_qa_pairs.csv", index=False)
+        
+        # Save failed generations for analysis
+        if self.failed_generations:
+            with open(FINAL_DIR / "failed_generations.json", 'w') as f:
+                json.dump(self.failed_generations, f, indent=2)
+
+        logging.info(f"""
+        Generation completed:
+        - Total pairs generated: {self.total_pairs_generated}
+        - Target pairs: {TARGET_QA_PAIRS}
+        - Categories used: {len(set(pair['category'] for pair in pairs))}
+        """)

main.py

@@ -0,0 +1,52 @@
+import logging
+from datetime import datetime
+
+from scraper import BloomingtonScraper
+from processor import DataProcessor
+from generator import QAPairGenerator
+from config import LOG_DIR
+
+def setup_logging() -> None:
+    """Set up logging configuration"""
+    log_file = LOG_DIR / f"main_{datetime.now().strftime('%Y%m%d_%H%M%S')}.log"
+    logging.basicConfig(
+        level=logging.INFO,
+        format='%(asctime)s - %(levelname)s - %(message)s',
+        handlers=[
+            logging.FileHandler(log_file),
+            logging.StreamHandler()  # Also print to console
+        ]
+    )
+
+def main():
+    setup_logging()
+    logging.info("Starting Bloomington Tourist Guide data collection and QA pair generation")
+    
+    try:
+        # Step 1: Data Collection
+        logging.info("Starting data collection...")
+        scraper = BloomingtonScraper()
+        scraper.scrape_all_categories()
+        search_stats = scraper.get_search_stats()
+        logging.info(f"Data collection completed. Search stats: {search_stats}")
+        
+        # Step 2: Data Processing
+        logging.info("Starting data processing...")
+        processor = DataProcessor()
+        processor.process_all_categories()
+        logging.info("Data processing completed")
+        
+        # Step 3: QA Pair Generation
+        logging.info("Starting QA pair generation...")
+        generator = QAPairGenerator()
+        generator.generate_all_pairs()
+        logging.info("QA pair generation completed")
+        
+    except Exception as e:
+        logging.error(f"Error in main execution: {e}", exc_info=True)
+        raise
+    
+    logging.info("Pipeline completed successfully")
+
+if __name__ == "__main__":
+    main()

post_processor.py

@@ -0,0 +1,113 @@
+import json
+import pandas as pd
+from pathlib import Path
+from typing import List, Dict
+import logging
+from datetime import datetime
+
+class DatasetConverter:
+    def __init__(self, input_file: str, output_dir: str):
+        """
+        Initialize the converter with input and output paths
+        
+        Args:
+            input_file (str): Path to the input JSON file
+            output_dir (str): Directory to save the output files
+        """
+        self.input_file = Path(input_file)
+        self.output_dir = Path(output_dir)
+        self.output_dir.mkdir(parents=True, exist_ok=True)
+        
+        # Set up logging
+        logging.basicConfig(
+            level=logging.INFO,
+            format='%(asctime)s - %(levelname)s - %(message)s'
+        )
+        
+    def _format_message(self, instruction: str, response: str) -> List[Dict]:
+        """
+        Format a single instruction-response pair into the required message format
+        
+        Args:
+            instruction (str): The user instruction/question
+            response (str): The assistant's response
+            
+        Returns:
+            List[Dict]: Formatted message list
+        """
+        return [
+            {"content": instruction, "role": "user"},
+            {"content": response, "role": "assistant"}
+        ]
+    
+    def convert(self) -> None:
+        """
+        Convert the input JSON file to HuggingFace dataset format
+        """
+        try:
+            # Read input JSON file
+            logging.info(f"Reading input file: {self.input_file}")
+            with open(self.input_file, 'r', encoding='utf-8') as f:
+                data = json.load(f)
+            
+            # Extract QA pairs from the JSON structure
+            qa_pairs = data.get('pairs', [])  # Handle both raw list and nested structure
+            if not qa_pairs and isinstance(data, list):
+                qa_pairs = data
+            
+            logging.info(f"Found {len(qa_pairs)} QA pairs")
+            
+            # Create dataset records
+            dataset_records = []
+            for idx, pair in enumerate(qa_pairs):
+                try:
+                    messages = self._format_message(
+                        pair['instruction'],
+                        pair['response']
+                    )
+                    
+                    dataset_records.append({
+                        'id': f'bloomington_{idx:05d}',
+                        'messages': messages
+                    })
+                except KeyError as e:
+                    logging.warning(f"Skipping invalid pair at index {idx}: {e}")
+            
+            # Convert to DataFrame
+            df = pd.DataFrame(dataset_records)
+            
+            # Save as CSV and JSON
+            timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
+            csv_path = self.output_dir / f'bloomington_dataset_{timestamp}.csv'
+            json_path = self.output_dir / f'bloomington_dataset_{timestamp}.json'
+            
+            df.to_csv(csv_path, index=False)
+            df.to_json(json_path, orient='records', indent=2)
+            
+            logging.info(f"Successfully converted {len(dataset_records)} records")
+            logging.info(f"Saved dataset to:\n- CSV: {csv_path}\n- JSON: {json_path}")
+            
+            # Generate and save dataset statistics
+            stats = {
+                'total_records': len(dataset_records),
+                'avg_instruction_length': sum(len(record['messages'][0]['content']) 
+                                           for record in dataset_records) / len(dataset_records),
+                'avg_response_length': sum(len(record['messages'][1]['content']) 
+                                        for record in dataset_records) / len(dataset_records),
+                'timestamp': timestamp
+            }
+            
+            with open(self.output_dir / f'dataset_stats_{timestamp}.json', 'w') as f:
+                json.dump(stats, f, indent=2)
+                
+        except Exception as e:
+            logging.error(f"Error converting dataset: {e}", exc_info=True)
+            raise
+
+if __name__ == "__main__":
+    # Example usage
+    converter = DatasetConverter(
+        input_file="data/final/final_qa_pairs.json",
+        output_dir="data/huggingface"
+    )
+    converter.convert()

processor.py

@@ -0,0 +1,120 @@
+import json
+import logging
+from datetime import datetime
+from typing import Dict, List
+import pandas as pd
+from bs4 import BeautifulSoup
+import requests
+from urllib.parse import urlparse
+
+from config import RAW_DIR, PROCESSED_DIR, LOG_DIR
+
+class DataProcessor:
+    def __init__(self):
+        # Set up logging
+        log_file = LOG_DIR / f"processor_{datetime.now().strftime('%Y%m%d_%H%M%S')}.log"
+        logging.basicConfig(
+            level=logging.INFO,
+            format='%(asctime)s - %(levelname)s - %(message)s',
+            filename=log_file
+        )
+        
+        self.processed_data = {}
+
+    def _extract_domain(self, url: str) -> str:
+        """Extract domain from URL"""
+        try:
+            return urlparse(url).netloc
+        except Exception:
+            return ""
+
+    def _scrape_webpage(self, url: str) -> str:
+        """Scrape additional content from webpage"""
+        try:
+            headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'}
+            response = requests.get(url, headers=headers, timeout=10)
+            soup = BeautifulSoup(response.text, 'lxml')
+            
+            # Remove unwanted elements
+            for element in soup(['script', 'style', 'nav', 'footer']):
+                element.decompose()
+            
+            return ' '.join(soup.stripped_strings)
+        except Exception as e:
+            logging.error(f"Error scraping {url}: {e}")
+            return ""
+
+    def process_category(self, category: str) -> List[Dict]:
+        """Process data for a single category"""
+        input_file = RAW_DIR / f"{category}_results.json"
+        
+        try:
+            with open(input_file, 'r') as f:
+                raw_results = json.load(f)
+        except Exception as e:
+            logging.error(f"Error loading {input_file}: {e}")
+            return []
+
+        processed_results = []
+        
+        for result in raw_results:
+            processed_result = {
+                'title': result.get('title', ''),
+                'snippet': result.get('snippet', ''),
+                'url': result.get('link', ''),
+                'domain': self._extract_domain(result.get('link', '')),
+                'category': category
+            }
+            
+            # Add additional content for certain domains
+            if any(domain in processed_result['domain'] 
+                  for domain in ['visitbloomington.com', 'indiana.edu', 'bloomington.in.gov']):
+                additional_content = self._scrape_webpage(processed_result['url'])
+                processed_result['additional_content'] = additional_content[:5000]  # Limit content length
+            
+            processed_results.append(processed_result)
+
+        # Save processed results
+        output_file = PROCESSED_DIR / f"{category}_processed.json"
+        with open(output_file, 'w') as f:
+            json.dump(processed_results, f, indent=2)
+        
+        # Also save as CSV for easy viewing
+        df = pd.DataFrame(processed_results)
+        df.to_csv(PROCESSED_DIR / f"{category}_processed.csv", index=False)
+        
+        self.processed_data[category] = processed_results
+        return processed_results
+
+    def process_all_categories(self) -> Dict[str, List[Dict]]:
+        """Process all categories"""
+        categories = [f.stem.replace('_results', '') 
+                     for f in RAW_DIR.glob('*_results.json')]
+        
+        for category in categories:
+            logging.info(f"Processing category: {category}")
+            self.process_category(category)
+        
+        # Save combined results
+        all_results = []
+        for category_results in self.processed_data.values():
+            all_results.extend(category_results)
+        
+        combined_df = pd.DataFrame(all_results)
+        combined_df.to_csv(PROCESSED_DIR / "all_processed.csv", index=False)
+        
+        # Generate and save statistics
+        stats = {
+            'total_results': len(all_results),
+            'results_per_category': {
+                category: len(results) 
+                for category, results in self.processed_data.items()
+            },
+            'domains_distribution': combined_df['domain'].value_counts().to_dict(),
+            'timestamp': datetime.now().strftime('%Y-%m-%d %H:%M:%S')
+        }
+        
+        with open(PROCESSED_DIR / "processing_stats.json", 'w') as f:
+            json.dump(stats, f, indent=2)
+        
+        return self.processed_data

requirements.txt

@@ -0,0 +1,24 @@
+# API Clients
+google-generativeai==0.8.3
+google-search-results==2.4.2
+
+# Data Processing
+pandas==2.2.3
+numpy==2.2.0
+
+# Web Scraping
+beautifulsoup4==4.12.3
+requests==2.32.3
+
+# Progress Bars and Utils
+tqdm==4.67.1
+ratelimit==2.2.1
+
+# Date and Time
+python-dateutil==2.9.0
+
+# Output Formatting
+tabulate==0.9.0  # For nice DataFrame display
+
+# Optional but recommended for better HTML parsing
+lxml==5.3.0

scraper.py

@@ -0,0 +1,103 @@
+import json
+import time
+from datetime import datetime
+from typing import Dict, List
+import logging
+from serpapi import GoogleSearch
+from pathlib import Path
+
+from config import (
+    SERP_API_KEY, SERP_MONTHLY_LIMIT, SEARCH_QUERIES,
+    RAW_DIR, LOG_DIR
+)
+
+class BloomingtonScraper:
+    def __init__(self):
+        self.search_count = 0
+        self.results_by_category = {}
+        
+        # Set up logging
+        log_file = LOG_DIR / f"scraper_{datetime.now().strftime('%Y%m%d_%H%M%S')}.log"
+        logging.basicConfig(
+            level=logging.INFO,
+            format='%(asctime)s - %(levelname)s - %(message)s',
+            filename=log_file
+        )
+
+    def _make_serp_request(self, query: str, category: str) -> List[Dict]:
+        """Make a single SERP API request"""
+        if self.search_count >= SERP_MONTHLY_LIMIT:
+            logging.warning("Monthly SERP API limit reached")
+            return []
+
+        params = {
+            "api_key": SERP_API_KEY,
+            "engine": "google",
+            "q": query,
+            "location": "Bloomington, Indiana, United States",
+            "google_domain": "google.com",
+            "num": 100,  # Get maximum results per query
+            "start": 0
+        }
+
+        try:
+            search = GoogleSearch(params)
+            results = search.get_dict()
+            self.search_count += 1
+            
+            # Save raw results
+            timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
+            raw_file = RAW_DIR / f"raw_results_{category}_{timestamp}.json"
+            with open(raw_file, 'w') as f:
+                json.dump(results, f, indent=2)
+            
+            logging.info(f"SERP API calls used: {self.search_count}/{SERP_MONTHLY_LIMIT}")
+            return results.get('organic_results', [])
+
+        except Exception as e:
+            logging.error(f"SERP API error for query '{query}': {e}")
+            return []
+
+    def scrape_all_categories(self) -> Dict[str, List[Dict]]:
+        """Scrape data for all categories"""
+        for category, queries in SEARCH_QUERIES.items():
+            logging.info(f"Starting scraping for category: {category}")
+            category_results = []
+            
+            for query in queries:
+                if self.search_count >= SERP_MONTHLY_LIMIT:
+                    logging.warning(f"Monthly limit reached during {category} scraping")
+                    break
+                
+                results = self._make_serp_request(query, category)
+                category_results.extend(results)
+                time.sleep(2)  # Polite delay between requests
+            
+            self.results_by_category[category] = category_results
+            
+            # Save category results
+            category_file = RAW_DIR / f"{category}_results.json"
+            with open(category_file, 'w') as f:
+                json.dump(category_results, f, indent=2)
+            
+            logging.info(f"Completed scraping for {category}: {len(category_results)} results")
+        
+        return self.results_by_category
+
+    def get_search_stats(self) -> Dict:
+        """Get statistics about the search results"""
+        stats = {
+            "total_searches": self.search_count,
+            "remaining_searches": SERP_MONTHLY_LIMIT - self.search_count,
+            "results_per_category": {
+                category: len(results) 
+                for category, results in self.results_by_category.items()
+            }
+        }
+        
+        # Save stats
+        stats_file = RAW_DIR / "search_stats.json"
+        with open(stats_file, 'w') as f:
+            json.dump(stats, f, indent=2)
+        
+        return stats