LlamaIndex

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

import os
from llama_index.core import Settings
from llama_index.llms.openai_like import OpenAILike
from llama_index.embeddings.openai_like import OpenAILikeEmbedding

Settings.llm = OpenAILike(
    model="deepseek-v4.1-flash",
    api_key=os.environ["NEOSANTARA_API_KEY"],
    api_base="https://api.neosantara.xyz/v1",
    temperature=0.2,
    max_tokens=1024,
    is_chat_model=True
)

Settings.embed_model = OpenAILikeEmbedding(
    model="text-embedding-3-small",
    api_key=os.environ["NEOSANTARA_API_KEY"],
    api_base="https://api.neosantara.xyz/v1"
)

import os
from llama_index.core import Document, VectorStoreIndex, Settings
from llama_index.llms.openai_like import OpenAILike
from llama_index.embeddings.openai_like import OpenAILikeEmbedding

# 1. Konfigurasi provider LLM dan Embedding
Settings.llm = OpenAILike(
    model="deepseek-v4.1-flash",
    api_key=os.environ["NEOSANTARA_API_KEY"],
    api_base="https://api.neosantara.xyz/v1",
    is_chat_model=True
)

Settings.embed_model = OpenAILikeEmbedding(
    model="text-embedding-3-small",
    api_key=os.environ["NEOSANTARA_API_KEY"],
    api_base="https://api.neosantara.xyz/v1"
)

# 2. Siapkan dokumen contoh
documents = [
    Document(text="Neosantara adalah AI Gateway Indonesia dengan dukungan pembayaran Rupiah dan saldo berbasis PAYG."),
    Document(text="Limit rate tier Free adalah 10 RPM, 30.000 ITPM, dan 8.000 OTPM dengan deposit awal minimum Rp 50.000 via Mayar QRIS."),
    Document(text="Fitur Guardrail UU PDP No. 27/2022 Neosantara dapat diaktifkan per-request melalui header X-Guard: on.")
]

# 3. Buat indeks vektor
index = VectorStoreIndex.from_documents(documents)

# 4. Inisialisasi query engine dan jalankan pertanyaan
query_engine = index.as_query_engine(similarity_top_k=2)
response = query_engine.query("Bagaimana cara mengaktifkan guardrail perlindungan data pribadi di Neosantara?")

print("Jawaban:", response)

query_engine = index.as_query_engine(streaming=True)
streaming_response = query_engine.query("Berapa limit rate untuk pengguna tier Free?")

for text in streaming_response.response_gen:
    print(text, end="", flush=True)
print()