LlamaIndex

LlamaIndex is a framework for applications that search your own data. Use its OpenAI-like embedding class with the exchange as the base URL to buy embeddings.

Before you start

• A workspace with a balance and a spend key. See API keys.
• A model name from GET /v1/models?kind=embedding. See Embeddings.

1. Export the key

export LIQUID_API_KEY=sk-liquid-...

2. Install the package

# Python 3.9 or later
pip install llama-index-embeddings-openai-like

3. Embed text

Use OpenAILikeEmbedding. Do not use OpenAIEmbedding, because it accepts only the model names of OpenAI.

import os
from llama_index.embeddings.openai_like import OpenAILikeEmbedding

embed_model = OpenAILikeEmbedding(
    model_name="text-embedding-3-small",
    api_base="https://router.inference.ai.exchange/v1",
    api_key=os.environ["LIQUID_API_KEY"],
    embed_batch_size=64,
)

vectors = embed_model.get_text_embedding_batch(["a cat on a bicycle", "a dog in a car"])
print(len(vectors), len(vectors[0]))

# To use it in every index and query engine:
from llama_index.core import Settings

Settings.embed_model = embed_model

The last lines set the model for every index and query engine.

Notes

• Keep one model for one index. A change of model needs a new index. See Embeddings.
• The exchange sets a cap on each request. It is in the x-liquid-cap-usd response header. To limit total spend, set a spending limit on the key. See API keys.
• A request can have 2,048 texts at most. Keep embed_batch_size at or below that number.
• The exchange has no streaming form for embeddings. It sends each batch complete.

Troubleshooting

See Errors for the error codes.

Next steps

• Embeddings: the request, the price and the limits.
• Qdrant: store the vectors in a collection.
• LangChain: the same task with LangChain.