How to use Gemini API with LlamaIndex

pip install openai llama-index

import os
from openai import OpenAI
from llama_index import SimpleDirectoryReader, GPTVectorStoreIndex, ServiceContext

# Initialize OpenAI client with Gemini model
client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

def query_gemini_with_llamaindex():
    # Load documents from a local directory
    documents = SimpleDirectoryReader("./data").load_data()

    # Create a service context with a custom embed model using Gemini
    def embed_text(texts):
        # Call Gemini embedding endpoint
        response = client.embeddings.create(
            model="gemini-1.5-pro",
            input=texts
        )
        return [embedding.embedding for embedding in response.data]

    service_context = ServiceContext.from_defaults(embed_model=embed_text)

    # Build the index
    index = GPTVectorStoreIndex.from_documents(documents, service_context=service_context)

    # Query the index
    query = "What is the main topic of the documents?"
    response = index.query(query)
    print("Query response:", response.response)

if __name__ == "__main__":
    query_gemini_with_llamaindex()

import asyncio
import os
from openai import OpenAI

async def async_gemini_call():
    client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])
    response = await client.chat.completions.acreate(
        model="gemini-2.0-flash",
        messages=[{"role": "user", "content": "Hello from async Gemini!"}]
    )
    print(response.choices[0].message.content)

if __name__ == "__main__":
    asyncio.run(async_gemini_call())