app.py

import gradio as gr
from langchain_openai import ChatOpenAI
# from dspy import Agent  # Base class for custom agent
# from dspy import spawn_processes  # Distributed computing utility
from transformers import pipeline

# Choose model
model_name = "dolphin-phi"

# Load the chosen LLM model
llm = pipeline("text-generation", model="TheBloke/dolphin-2_6-phi-2-GGUF")

#Vectara config:
# customer_id =
# corpus_id = 
# api_key = 

# Brought from Vectara example from Tonic. Global variables to hold component references
components = {}
dotenv.load_dotenv()
seamless_client = Client("TheBloke/dolphin-2_6-phi-2-GGUF")
HuggingFace_Token = os.getenv("HuggingFace_Token")
hf_token = os.getenv("HuggingFace_Token")
base_model_id = os.getenv('BASE_MODEL_ID', 'default_base_model_id')
model_directory = os.getenv('MODEL_DIRECTORY', 'default_model_directory')
import requests

# DSPy-based prompt generation
from dspy.agents import Agent
from dspy import spawn_processes
from dspy.utils import SentenceSplitter, SentimentAnalyzer, NamedEntityRecognizer

def dspy_generate_agent_prompts(prompt):
    """
    Generates prompts for different agents based on the provided prompt and DSPy functionalities.

    Args:
        prompt (str): The user-provided prompt (e.g., customer reviews).

    Returns:
        list: A list containing agent-specific prompts.
    """

    # 1. Split the prompt into individual sentences
    sentences = SentenceSplitter().process(prompt)

    # 2. Analyze sentiment for each sentence
    sentiment_analyzer = SentimentAnalyzer()
    sentiment_labels = []
    for sentence in sentences:
        sentiment_labels.append(sentiment_analyzer.analyze(sentence))

    # 3. Extract named entities related to specific topics
    ner = NamedEntityRecognizer(model_name="en_core_web_sm")
    extracted_entities = {}
    for sentence in sentences:
        entities = ner.process(sentence)
        for entity in entities:
            if entity.label_ in ["FOOD", "ORG", "LOCATION"]:  # Customize entity labels based on needs
                extracted_entities.setdefault(entity.label_, []).append(entity.text)

    # 4. Craft prompts for each agent (incomplete)
    agent_prompts = []

    # **Sentiment Analyzer Prompt:**
    sentiment_prompt = f"Analyze the sentiment of the following sentences:\n" + "\n".join(sentences)
    agent_prompts.append(sentiment_prompt)

    # **Topic Extractor Prompt:** (Modify based on your specific topics)
    topic_prompt = f"Extract the main topics discussed in the following text, focusing on food, service, and ambiance:\n{prompt}"
    agent_prompts.append(topic_prompt)

    # **Recommendation Generator Prompt:** (Modify based on your requirements)
    positive_count = sum(label == "POSITIVE" for label in sentiment_labels)
    negative_count = sum(label == "NEGATIVE" for label in sentiment_labels)
    neutral_count = sum(label == "NEUTRAL" for label in sentiment_labels)
    topic_mentions = "\n".join(f"{k}: {','.join(v)}" for k, v in extracted_entities.items())

    recommendation_prompt = f"""Based on the sentiment analysis (positive: {positive_count}, negative: {negative_count}, neutral: {neutral_count}) and extracted topics ({topic_mentions}), suggest recommendations for the restaurant to improve."""
    agent_prompts.append(recommendation_prompt)

    return agent_prompts

def query_vectara(text):
    user_message = text

    # Read authentication parameters from the .env file
    customer_id = os.getenv('CUSTOMER_ID')
    corpus_id = os.getenv('CORPUS_ID')
    api_key = os.getenv('API_KEY')

    # Define the headers
    api_key_header = {
        "customer-id": customer_id,
        "x-api-key": api_key
    }

    # Define the request body in the structure provided in the example
    request_body = {
        "query": [
            {
                "query": user_message,
                "queryContext": "",
                "start": 1,
                "numResults": 25,
                "contextConfig": {
                    "charsBefore": 0,
                    "charsAfter": 0,
                    "sentencesBefore": 2,
                    "sentencesAfter": 2,
                    "startTag": "%START_SNIPPET%",
                    "endTag": "%END_SNIPPET%",
                },
                "rerankingConfig": {
                    "rerankerId": 272725718,
                    "mmrConfig": {
                        "diversityBias": 0.35
                    }
                },
                "corpusKey": [
                    {
                        "customerId": customer_id,
                        "corpusId": corpus_id,
                        "semantics": 0,
                        "metadataFilter": "",
                        "lexicalInterpolationConfig": {
                            "lambda": 0
                        },
                        "dim": []
                    }
                ],
                "summary": [
                    {
                        "maxSummarizedResults": 5,
                        "responseLang": "auto",
                        "summarizerPromptName": "vectara-summary-ext-v1.2.0"
                    }
                ]
            }
        ]
    }

    # Make the API request using Gradio
    response = requests.post(
        "https://api.vectara.io/v1/query",
        json=request_body,  # Use json to automatically serialize the request body
        verify=True,
        headers=api_key_header
    )

    if response.status_code == 200:
        query_data = response.json()
        if query_data:
            sources_info = []

            # Extract the summary.
            summary = query_data['responseSet'][0]['summary'][0]['text']

            # Iterate over all response sets
            for response_set in query_data.get('responseSet', []):
                # Extract sources
                # Limit to top 5 sources.
                for source in response_set.get('response', [])[:5]:
                    source_metadata = source.get('metadata', [])
                    source_info = {}

                    for metadata in source_metadata:
                        metadata_name = metadata.get('name', '')
                        metadata_value = metadata.get('value', '')

                        if metadata_name == 'title':
                            source_info['title'] = metadata_value
                        elif metadata_name == 'author':
                            source_info['author'] = metadata_value
                        elif metadata_name == 'pageNumber':
                            source_info['page number'] = metadata_value

                    if source_info:
                        sources_info.append(source_info)

            result = {"summary": summary, "sources": sources_info}
            return f"{json.dumps(result, indent=2)}"
        else:
            return "No data found in the response."
    else:
        return f"Error: {response.status_code}"

# Define the main function to be used with Gradio
def generate_outputs(user_prompt):
    # 1. Process prompt with langchain (replace with your actual implementation)
    # processed_prompt = dspy_generate_agent_prompts(user_prompt)  # Replaced langchain logic with DSPy function below

    # 2. Generate synthetic data using DSPy's distributed computing capabilities
    synthetic_data = generate_synthetic_data_distributed(user_prompt)

    # 3. Combine user prompt and synthetic data
    combined_data = f"{user_prompt}\n{synthetic_data}"

    # 4. Generate prompts for agents using DSPy
    agent_prompts = dspy_generate_agent_prompts(processed_prompt)

    # 5. Use the chosen LLM for two of the prompts and vectara tool use for the third agent
    output_1 = llm(agent_prompts[0], max_length=100)[0][combined_data]
    output_2 = llm(agent_prompts[1], max_length=100)[0][combined_data]
    output_3 = query_vectara(prompt)

    # 6. Produce outputs with Langchain or DSPy (stand in section)
    report, recommendations, visualization = produce_outputs(combined_data)

    return report, recommendations, visualization

# Create the Gradio interface
gr.Interface(
    fn=generate_outputs,
    inputs=gr.Textbox(label="Enter a prompt"),
    outputs=["textbox", "textbox", "image"],
    title="Multi-Agent Prompt Processor",
    description="Processes a prompt using Langchain, DSPy, and a chosen Hugging Face LLM to generate diverse outputs.",
).launch()