BAAI BGE-M3

BGE-M3 (from the Beijing Academy of Artificial Intelligence) is the industry-standard multilingual embedding model: supporting 100+ languages including strong Arabic coverage, and uniquely emitting dense, sparse, and multi-vector representations from a single forward pass. 8192-token context window. The default starting point for any RAG pipeline; pair with `baai/bge-reranker-v2-m3` for the canonical two-stage retrieval stack.

Quick start

Use any OpenAI-compatible client. Just change base_url and your key.

from openai import OpenAI

client = OpenAI(
    api_key="tl-xxxxxxxxxxxxxxxxxxxxxxxx",
    base_url="https://api.thalam.ai/v1",
)

response = client.chat.completions.create(
    model="baai/bge-m3",
    messages=[
        {"role": "user", "content": "Hello from Thalam!"}
    ],
)

print(response.choices[0].message.content)