Last active
November 20, 2023 13:59
-
-
Save csiebler/e287b791333011183792c08bad1dc140 to your computer and use it in GitHub Desktop.
Using LlamaIndex (GPT Index) with Azure OpenAI Service
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import os | |
import openai | |
from dotenv import load_dotenv | |
from llama_index import GPTSimpleVectorIndex, SimpleDirectoryReader, LLMPredictor, PromptHelper | |
from langchain.llms import AzureOpenAI | |
from langchain.embeddings import OpenAIEmbeddings | |
from llama_index import LangchainEmbedding | |
# Load env variables (create .env with OPENAI_API_KEY and OPENAI_API_BASE) | |
load_dotenv() | |
# Configure OpenAI API | |
openai.api_type = "azure" | |
openai.api_version = "2022-12-01" | |
openai.api_base = os.getenv('OPENAI_API_BASE') | |
openai.api_key = os.getenv("OPENAI_API_KEY") | |
deployment_name = "text-davinci-003" | |
# Create LLM via Azure OpenAI Service | |
llm = AzureOpenAI(deployment_name=deployment_name) | |
llm_predictor = LLMPredictor(llm=llm) | |
embedding_llm = LangchainEmbedding(OpenAIEmbeddings()) | |
# Define prompt helper | |
max_input_size = 3000 | |
num_output = 256 | |
chunk_size_limit = 1000 # token window size per document | |
max_chunk_overlap = 20 # overlap for each token fragment | |
prompt_helper = PromptHelper(max_input_size=max_input_size, num_output=num_output, max_chunk_overlap=max_chunk_overlap, chunk_size_limit=chunk_size_limit) | |
# Read txt files from data directory | |
documents = SimpleDirectoryReader('data').load_data() | |
index = GPTSimpleVectorIndex(documents, llm_predictor=llm_predictor, embed_model=embedding_llm, prompt_helper=prompt_helper) | |
index.save_to_disk("index.json") | |
# Query index with a question | |
response = index.query("What is azure openai service?") | |
print(response) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
.....
I had deploy as well the training Model....