Teach ChatGPT to Answer Questions: Using Azure Cognitive Search & Azure OpenAI Services

# Library imports
from collections import OrderedDict
import requests

# Langchain library imports
from langchain.chains import RetrievalQAWithSourcesChain
from langchain.chat_models import AzureChatOpenAI
from langchain.docstore.document import Document
from langchain.embeddings import OpenAIEmbeddings
from langchain.vectorstores import FAISS

# Azure Search Service settings
SEARCH_SERVICE_NAME = 'your-search-service-name' # 'test-search-service1'
SEARCH_SERVICE_ENDPOINT = f'https://{SEARCH_SERVICE_NAME.lower()}.search.windows.net/'
SEARCH_SERVICE_KEY = 'your-search-service-key'
SEARCH_SERVICE_API_VERSION = 'your-API-version' # '2023-07-01-preview'

# Azure Search Service Index settings
SEARCH_SERVICE_INDEX_NAME1 = 'your-search-service-index-name' # 'azureblob-index1'

# Azure Cognitive Search Service Semantic configuration settings
SEARCH_SERVICE_SEMANTIC_CONFIG_NAME = 'your-semantic-configuration-name' # 'test-configuration'

# Azure OpenAI settings
AZURE_OPENAI_NAME = 'your-openai-name' # 'testopenai1004'
AZURE_OPENAI_ENDPOINT = f'https://{AZURE_OPENAI_NAME.lower()}.openai.azure.com/'
AZURE_OPENAI_KEY = 'your-openai-key'
AZURE_OPENAI_API_VERSION = 'your-API-version' # '2023-08-01-preview'

# Azure Search Service settings
SEARCH_SERVICE_NAME = 'your-search-service-name' # 'test-search-service1'
SEARCH_SERVICE_ENDPOINT = f'https://{SEARCH_SERVICE_NAME.lower()}.search.windows.net/'
SEARCH_SERVICE_KEY = 'your-search-service-key'
SEARCH_SERVICE_API_VERSION = 'your-API-version' # '2023-07-01-preview'

# Azure Search Service Index settings
SEARCH_SERVICE_INDEX_NAME1 = 'your-search-service-index-name' # 'azureblob-index1'

# Azure Cognitive Search Service Semantic configuration settings
SEARCH_SERVICE_SEMANTIC_CONFIG_NAME = 'your-semantic-configuration-name' # 'test-configuration'

# Azure OpenAI settings
AZURE_OPENAI_NAME = 'your-openai-name' # 'testopenai1004'
AZURE_OPENAI_ENDPOINT = f'https://{AZURE_OPENAI_NAME.lower()}.openai.azure.com/'
AZURE_OPENAI_KEY = 'your-openai-key'
AZURE_OPENAI_API_VERSION = 'your-API-version' # '2023-08-01-preview'

# Library imports
from collections import OrderedDict
import requests

# Langchain library imports
from langchain.chains import RetrievalQAWithSourcesChain
from langchain.chat_models import AzureChatOpenAI
from langchain.docstore.document import Document
from langchain.embeddings import OpenAIEmbeddings
from langchain.vectorstores import FAISS

# Configuration imports
from config import (
    SEARCH_SERVICE_ENDPOINT,
    SEARCH_SERVICE_KEY,
    SEARCH_SERVICE_API_VERSION,
    SEARCH_SERVICE_INDEX_NAME1,
    SEARCH_SERVICE_SEMANTIC_CONFIG_NAME,
    AZURE_OPENAI_ENDPOINT,
    AZURE_OPENAI_KEY,
    AZURE_OPENAI_API_VERSION,
)

# Cognitive Search Service header settings
HEADERS = {
    'Content-Type': 'application/json',
    'api-key': SEARCH_SERVICE_KEY
}

# Function to search documents using Azure Cognitive Search
def search_documents(question):
    url = (SEARCH_SERVICE_ENDPOINT + 'indexes/' +
               SEARCH_SERVICE_INDEX_NAME1 + '/docs')
    params = {
        'api-version': SEARCH_SERVICE_API_VERSION,
        'search': question,
        'select': '*',
        '$top': 3,
        'queryLanguage': 'en-us',
        'queryType': 'semantic',
        'semanticConfiguration': SEARCH_SERVICE_SEMANTIC_CONFIG_NAME,
        '$count': 'true',
        'speller': 'lexicon',
        'answers': 'extractive|count-3',
        'captions': 'extractive|highlight-false'
        }
    resp = requests.get(url, headers=HEADERS, params=params)
    return resp.json()
       
# Extract documents that score above a certain threshold in semantic search
def extract_documents(search_results):
    file_content = OrderedDict()
    for result in search_results['value']:
        # The '@search.rerankerScore' range is 1 to 4.00, where a higher score indicates a stronger semantic match.
        if result['@search.rerankerScore'] > 1.5:
            file_content[result['metadata_storage_path']] = {
                'chunks': result['pages'][:10],
                'captions': result['@search.captions'][:10],
                'score': result['@search.rerankerScore'],
                'file_name': result['metadata_storage_name']
            }

    return file_content

# Function to create an embedding model
def create_embeddings():
    return OpenAIEmbeddings(
        openai_api_type='azure',
        openai_api_key=AZURE_OPENAI_KEY,
        openai_api_base=AZURE_OPENAI_ENDPOINT,
        openai_api_version=AZURE_OPENAI_API_VERSION,
        deployment='text-embedding-ada-002',
        model='text-embedding-ada-002',
        chunk_size=1
    )

# Function to create a Vectorstore
def create_vector_store(docs, embeddings):
    return FAISS.from_documents(docs, embeddings)

# Function to retrieve search results using Langchain and Chatgpt
def search_with_langchain(vector_store, question):
    llm = AzureChatOpenAI(
        openai_api_key=AZURE_OPENAI_KEY,
        openai_api_base=AZURE_OPENAI_ENDPOINT,
        openai_api_version=AZURE_OPENAI_API_VERSION,
        openai_api_type='azure',
        deployment_name='gpt-35-turbo',
        temperature=0.0,
        max_tokens=500
    )

    chain = RetrievalQAWithSourcesChain.from_chain_type(
        llm=llm,
        chain_type='stuff',
        retriever=vector_store.as_retriever(),
        return_source_documents=True
    )

    return chain({'question': question})

def main():
    QUESTION = 'Tell me about effective prompting strategies'

    # Search for documents with Azure Cognitive Search
    search_results = search_documents(QUESTION)
    file_content = extract_documents(search_results)

    print('Total Documents Found: {}, Top Documents: {}'.format(
        search_results['@odata.count'], len(search_results['value'])))

    # 'chunks' is the value that corresponds to the Pages field that you set up in the Cognitive Search service.
    # Find the number of chunks
    docs = []
    for key,value in file_content.items():
        for page in value['chunks']:
            docs.append(Document(page_content = page,
                             metadata={"source": value["file_name"]}))
    print("Number of chunks: ", len(docs))

    # Create an embedding model
    embeddings = create_embeddings()

    # Create a Vectorstore
    vector_store = create_vector_store(docs, embeddings)

    # Search results using Langchain and Chatgpt
    result = search_with_langchain(vector_store, QUESTION)

    print('Question: ', QUESTION)
    print('Answer: ', result['answer'])
    print('Reference: ', result['sources'].replace(",","\n"))

# execute the main function
if __name__ == "__main__":
    main()