app.py

import gradio as gr
import requests
import json
from decouple import Config

config = Config('.env')


def query_vectara(question):
    user_message = question

    # Read authentication parameters from the .env file
    CUSTOMER_ID = config('CUSTOMER_ID')
    CORPUS_ID = config('CORPUS_ID')
    API_KEY = config('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": 10,
                "contextConfig": {
                    "charsBefore": 0,
                    "charsAfter": 0,
                    "sentencesBefore": 2,
                    "sentencesAfter": 2,
                    "startTag": "%START_SNIPPET%",
                    "endTag": "%END_SNIPPET%",
                },
                "rerankingConfig": {
                    "rerankerId": 272725718,
                    "mmrConfig": {
                        "diversityBias": 0.27
                    }
                },
                "corpusKey": [
                    {
                        "customerId": CUSTOMER_ID,
                        "corpusId": CORPUS_ID,
                        "semantics": 0,
                        "metadataFilter": "",
                        "lexicalInterpolationConfig": {
                            "lambda": 0
                        },
                        "dim": []
                    }
                ],
                "summary": [
                    {
                        "maxSummarizedResults": 5,
                        "responseLang": "eng",
                        "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    
                for source in response_set.get('response', [])[:5]:  # Limit to top 5 sources.  
                    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}"    


def convert_to_markdown(vectara_response_json):  
    vectara_response = json.loads(vectara_response_json)  
    if vectara_response:  
        summary = vectara_response.get('summary', 'No summary available')  
        sources_info = vectara_response.get('sources', [])  
  
        # Format the summary as Markdown  
        markdown_summary = f'**Summary:** {summary}\n\n'  
  
        # Format the sources as a numbered list  
        markdown_sources = ""  
        for i, source_info in enumerate(sources_info):  
            author = source_info.get('author', 'Unknown author')  
            title = source_info.get('title', 'Unknown title')  
            page_number = source_info.get('page number', 'Unknown page number')  
            markdown_sources += f"{i+1}. {title} by {author}, Page {page_number}\n"  
  
        return f"{markdown_summary}**Sources:**\n{markdown_sources}"  
    else:  
        return "No data found in the response."  
  
  
iface = gr.Interface(  
    fn=lambda text: convert_to_markdown(query_vectara(text)),  
    inputs=[gr.Textbox(label="Input Text")],  
    outputs=[gr.Markdown(label="Output Text")],  
    title="Vectara Chatbot",  
    description="Ask me anything using the Vectara API!"  
)  
  
iface.launch()