AI_EXTRACT

=AI_EXTRACT(text, extract_type, [temperature], [model], [max_tokens], [api_key], [api_url])

=AI_EXTRACT("During today's annual review, we discussed progress with Acme Corporation, Global Enterprises, and TechSolutions Inc. All three clients reported satisfaction with our services.", "client names")

=AI_EXTRACT("Q1 results exceeded expectations with revenue of $2.4M, an EBITDA margin of 18.5%, and customer acquisition costs decreasing by 12%. Cash reserves stand at $5.2M and our runway extends to 24 months.", "financial metrics")

=AI_EXTRACT("Hi team, Following our strategic planning session: 1) Mark needs to finalize the budget by Friday, 2) Sarah will contact vendors for new quotes, 3) Development team must provide timeline estimates by next Wednesday, and 4) Everyone should review the new marketing materials.", "action items")

=AI_EXTRACT("John Smith\nSenior Project Manager\nInnovative Solutions Inc.\[email protected]\n+1 (555) 123-4567\n123 Business Avenue, Suite 400\nSan Francisco, CA 94107", "contact information")

=AI_EXTRACT("The initial design phase will be completed by May 15, 2025. The stakeholder review is scheduled for May 20-22, with development starting June 1. Testing will run through September 15, with final delivery expected by October 3, 2025.", "dates and deadlines")

import requests
import json
 
# This function uses AI to extract specific types of information from text.
def ai_extract(text, extract_type, temperature=0.0, model='mistral-small-latest', max_tokens=1000, api_key=None, api_url=None):
    """
    Uses AI to extract specific types of information from text.
 
    Args:
        text (str or list): The text to analyze (string or 2D list with a single cell)
        extract_type (str): Type of information to extract (e.g., 'emails', 'dates', 'action items')
        temperature (float, optional): Controls response creativity (0-2). Default is 0.0
        model (str, optional): ID of the model to use
        max_tokens (int, optional): Maximum tokens for response generation. Default is 1000
        api_key (str, optional): API key for authentication (e.g. for Mistral AI)
        api_url (str, optional): OpenAI compatible URL. (e.g., https://api.mistral.ai/v1/chat/completions)
 
    Returns:
        list: 2D list representing the extracted data as a single column
    """
    # Demo fallback logic (Boardflare)
    if api_key is None or api_url is None:
        if 'idToken' in globals():
            api_key = globals()['idToken']
            api_url = "https://llm.boardflare.com"
        else:
            return [["Login on the Functions tab for limited demo usage, or sign up for a free Mistral AI account at https://console.mistral.ai/ and add your own api_key."]]
 
    # Handle 2D list input (flatten to a single string)
    if isinstance(text, list):
        if len(text) > 0 and len(text[0]) > 0:
            text = str(text[0][0])
        else:
            return [["Error: Empty input text."]]
 
    # Validate temperature
    if not (isinstance(temperature, (int, float)) and 0.0 <= float(temperature) <= 2.0):
        return [["Error: temperature must be a float between 0.0 and 2.0."]]
 
    # Validate max_tokens
    if not (isinstance(max_tokens, int) and max_tokens > 0):
        return [["Error: max_tokens must be a positive integer."]]
 
    # Construct a specific prompt for data extraction
    extract_prompt = f"Extract the following from the text: {extract_type}\n\nText: {text}"
    extract_prompt += "\n\nReturn ONLY a JSON object with a key 'items' whose value is a JSON array of the items you extracted. "
    extract_prompt += "Each item should be a single value representing one extracted piece of information. "
    extract_prompt += "Do not include any explanatory text, just the JSON object. "
    extract_prompt += "For example: {\"items\": [\"item1\", \"item2\", \"item3\"]}"
 
    payload = {
        "messages": [{"role": "user", "content": extract_prompt}],
        "temperature": temperature,
        "model": model,
        "max_tokens": max_tokens,
        "response_format": {"type": "json_object"}
    }
 
    headers = {
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
        "Accept": "application/json"
    }
 
    try:
        response = requests.post(api_url, headers=headers, json=payload)
        response.raise_for_status()
        response_data = response.json()
        content = response_data["choices"][0]["message"]["content"]
        try:
            extracted_data = json.loads(content)
            if isinstance(extracted_data, dict) and "items" in extracted_data:
                extracted_data = extracted_data["items"]
            elif isinstance(extracted_data, dict):
                if "extracted" in extracted_data:
                    extracted_data = extracted_data["extracted"]
                elif "results" in extracted_data:
                    extracted_data = extracted_data["results"]
            if isinstance(extracted_data, list):
                return [[item] for item in extracted_data]
            else:
                return [["Error: Unable to parse response. Expected a list."]]
        except (json.JSONDecodeError, ValueError):
            return [["Error: Unable to extract data. The AI response wasn't in the expected format."]]
    except requests.exceptions.RequestException as e:
        return [["Error: API request failed.", str(e)]]