How to use Azure opneai api with scrapegraph-ai

[Dong Wook]

from langchain_openai import AzureChatOpenAI
from langchain_openai import AzureOpenAIEmbeddings
import os

llm_model_instance = AzureChatOpenAI(
    openai_api_version=os.environ["AZURE_OPENAI_API_VERSION"],
    azure_deployment=os.environ["AZURE_OPENAI_CHAT_DEPLOYMENT_NAME"],
)

embedder_model_instance = AzureOpenAIEmbeddings(
    openai_api_version = os.environ["AZURE_OPENAI_API_VERSION"],
    azure_deployment=os.environ["AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME"],
)

graph_config = {
    "llm": {
        "model_instance": llm_model_instance,
    },
    "embeddings": {
        "model_instance": embedder_model_instance,
    }
}

from scrapegraphai.graphs import SmartScraperGraph
from scrapegraphai.utils import prettify_exec_info

smart_scraper_graph = SmartScraperGraph(
    prompt="List me all the projects with their description.",
    # also accepts a string with the already downloaded HTML code
    source="https://perinim.github.io/projects",
    config=graph_config
)

result = smart_scraper_graph.run()
print(result)

Exception has occurred: KeyError
'AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME'
KeyError: b'AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME'

During handling of the above exception, another exception occurred:

File "/home/dongwook/Project/UniApi/main.py", line 12, in
azure_deployment=os.environ["AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME"],
KeyError: 'AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME'

[Anirudh Kansal]

@dwk601, This is because it is not able to access required .env variables.

# required environment variable in .env
# AZURE_OPENAI_ENDPOINT
# AZURE_OPENAI_CHAT_DEPLOYMENT_NAME
# MODEL_NAME
# AZURE_OPENAI_API_KEY
# OPENAI_API_TYPE
# AZURE_OPENAI_API_VERSION
# AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME

And then load these variables by using:

from dotenv import load_dotenv
load_dotenv()