Given the following description of a dataset:

{description}

Please identify 5 potential users who would engage with this dataset. For each user, list 5 tasks they would perform with this dataset. Then, for each (user, task) combination, generate 5 questions that require a high-level understanding of the entire dataset.

Output the results in the following structure:
- User 1: [user description]
    - Task 1: [task description]
        - Question 1:
        - Question 2:
        - Question 3:
        - Question 4:
        - Question 5:
    - Task 2: [task description]
        ...
    - Task 5: [task description]
- User 2: [user description]
    ...
- User 5: [user description]
    ...

---Role---
You are an expert tasked with evaluating two answers to the same question based on three criteria: **Comprehensiveness**, **Diversity**, and **Empowerment**.
---Goal---
You will evaluate two answers to the same question based on three criteria: **Comprehensiveness**, **Diversity**, and **Empowerment**.

- **Comprehensiveness**: How much detail does the answer provide to cover all aspects and details of the question?
- **Diversity**: How varied and rich is the answer in providing different perspectives and insights on the question?
- **Empowerment**: How well does the answer help the reader understand and make informed judgments about the topic?

For each criterion, choose the better answer (either Answer 1 or Answer 2) and explain why. Then, select an overall winner based on these three categories.

Here is the question:
{query}

Here are the two answers:

**Answer 1:**
{answer1}

**Answer 2:**
{answer2}

Evaluate both answers using the three criteria listed above and provide detailed explanations for each criterion.

Output your evaluation in the following JSON format:

{{
    "Comprehensiveness": {{
        "Winner": "[Answer 1 or Answer 2]",
        "Explanation": "[Provide explanation here]"
    }},
    "Empowerment": {{
        "Winner": "[Answer 1 or Answer 2]",
        "Explanation": "[Provide explanation here]"
    }},
    "Overall Winner": {{
        "Winner": "[Answer 1 or Answer 2]",
        "Explanation": "[Summarize why this answer is the overall winner based on the three criteria]"
    }}
}}

def extract_unique_contexts(input_directory, output_directory):

    os.makedirs(output_directory, exist_ok=True)

    jsonl_files = glob.glob(os.path.join(input_directory, '*.jsonl'))
    print(f"Found {len(jsonl_files)} JSONL files.")

    for file_path in jsonl_files:
        filename = os.path.basename(file_path)
        name, ext = os.path.splitext(filename)
        output_filename = f"{name}_unique_contexts.json"
        output_path = os.path.join(output_directory, output_filename)

        unique_contexts_dict = {}

        print(f"Processing file: {filename}")

        try:
            with open(file_path, 'r', encoding='utf-8') as infile:
                for line_number, line in enumerate(infile, start=1):
                    line = line.strip()
                    if not line:
                        continue
                    try:
                        json_obj = json.loads(line)
                        context = json_obj.get('context')
                        if context and context not in unique_contexts_dict:
                            unique_contexts_dict[context] = None
                    except json.JSONDecodeError as e:
                        print(f"JSON decoding error in file {filename} at line {line_number}: {e}")
        except FileNotFoundError:
            print(f"File not found: {filename}")
            continue
        except Exception as e:
            print(f"An error occurred while processing file {filename}: {e}")
            continue

        unique_contexts_list = list(unique_contexts_dict.keys())
        print(f"There are {len(unique_contexts_list)} unique `context` entries in the file {filename}.")

        try:
            with open(output_path, 'w', encoding='utf-8') as outfile:
                json.dump(unique_contexts_list, outfile, ensure_ascii=False, indent=4)
            print(f"Unique `context` entries have been saved to: {output_filename}")
        except Exception as e:
            print(f"An error occurred while saving to the file {output_filename}: {e}")

    print("All files have been processed.")

def insert_text(rag, file_path):
    with open(file_path, mode='r') as f:
        unique_contexts = json.load(f)

    retries = 0
    max_retries = 3
    while retries < max_retries:
        try:
            rag.insert(unique_contexts)
            break
        except Exception as e:
            retries += 1
            print(f"Insertion failed, retrying ({retries}/{max_retries}), error: {e}")
            time.sleep(10)
    if retries == max_retries:
        print("Insertion failed after exceeding the maximum number of retries")

tokenizer = GPT2Tokenizer.from_pretrained('gpt2')

def get_summary(context, tot_tokens=2000):
    tokens = tokenizer.tokenize(context)
    half_tokens = tot_tokens // 2

    start_tokens = tokens[1000:1000 + half_tokens]
    end_tokens = tokens[-(1000 + half_tokens):1000]

    summary_tokens = start_tokens + end_tokens
    summary = tokenizer.convert_tokens_to_string(summary_tokens)

    return summary

def extract_queries(file_path):
    with open(file_path, 'r') as f:
        data = f.read()

    data = data.replace('**', '')

    queries = re.findall(r'- Question \d+: (.+)', data)

    return queries