RAG with Chinese AI Models

Build a complete RAG pipeline using AIWave's embeddings and chat models. Cost-effective alternative to OpenAI embeddings.

RAG Pipeline

Documents → Chunk → Embed → Vector DB
Query → Embed → Retrieve → LLM → Answer

Implementation

from openai import OpenAI
client = OpenAI(
    base_url="https://aiwave.live/v1",
    api_key="sk-YOUR_KEY"
)

def embed(text):
    resp = client.embeddings.create(
        model="text-embedding-3-small",
        input=text
    )
    return resp.data[0].embedding

def rag_query(question, vector_db):
    q_embed = embed(question)
    docs = vector_db.search(q_embed, top_k=3)
    context = "\n".join(docs)
    resp = client.chat.completions.create(
        model="deepseek-v4-pro",
        messages=[{
            "role":"user",
            "content": f"Context:\n{context}\n\nQuestion: {question}"
        }]
    )
    return resp.choices[0].message.content

Recommended Stack

Component	AIWave Model	Cost
Embeddings	text-embedding-3-small	Low
Chat/Generation	deepseek-v4-pro	$0.14/M input
Vector DB	Pinecone / Weaviate / Chroma	Free tier available