LlamaIndex

pip install llama-index llama-index-llms-openai llama-index-embeddings-openai

from llama_index.llms.openai import OpenAI
from llama_index.core import Settings

# Configure LLM
llm = OpenAI(
    model="gpt-4o",
    api_key="sk-your-lemondata-key",
    api_base="https://api.lemondata.cc/v1"
)

# Set as default
Settings.llm = llm

# Simple query
response = llm.complete("What is LemonData?")
print(response.text)

# OpenAI GPT-4o
gpt4 = OpenAI(
    model="gpt-4o",
    api_key="sk-your-key",
    api_base="https://api.lemondata.cc/v1"
)

# Anthropic Claude (via OpenAI-compatible endpoint)
claude = OpenAI(
    model="claude-sonnet-4-5",
    api_key="sk-your-key",
    api_base="https://api.lemondata.cc/v1"
)

# Google Gemini
gemini = OpenAI(
    model="gemini-2.5-flash",
    api_key="sk-your-key",
    api_base="https://api.lemondata.cc/v1"
)

from llama_index.core.llms import ChatMessage

messages = [
    ChatMessage(role="system", content="You are a helpful assistant."),
    ChatMessage(role="user", content="What is the capital of France?")
]

response = llm.chat(messages)
print(response.message.content)

# Streaming completion
for chunk in llm.stream_complete("Write a poem about AI"):
    print(chunk.delta, end="", flush=True)

# Streaming chat
for chunk in llm.stream_chat(messages):
    print(chunk.delta, end="", flush=True)

from llama_index.embeddings.openai import OpenAIEmbedding

embed_model = OpenAIEmbedding(
    model="text-embedding-3-small",
    api_key="sk-your-lemondata-key",
    api_base="https://api.lemondata.cc/v1"
)

# Set as default
Settings.embed_model = embed_model

# Get embeddings
embeddings = embed_model.get_text_embedding("Hello, world!")
print(f"Embedding dimension: {len(embeddings)}")

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader

# Configure settings
Settings.llm = llm
Settings.embed_model = embed_model

# Load documents
documents = SimpleDirectoryReader("./data").load_data()

# Create index
index = VectorStoreIndex.from_documents(documents)

# Query
query_engine = index.as_query_engine()
response = query_engine.query("What is in my documents?")
print(response)

# Create chat engine with memory
chat_engine = index.as_chat_engine(chat_mode="condense_question")

# Multi-turn conversation
response = chat_engine.chat("What is LemonData?")
print(response)

response = chat_engine.chat("How many models does it support?")
print(response)

import asyncio

async def main():
    response = await llm.acomplete("Hello!")
    print(response.text)

asyncio.run(main())

export OPENAI_API_KEY="sk-your-lemondata-key"
export OPENAI_API_BASE="https://api.lemondata.cc/v1"

from llama_index.llms.openai import OpenAI

# Will automatically use environment variables
llm = OpenAI(model="gpt-4o")