LangDB Embedder

Generate embeddings through a LangDB project endpoint.

LangDBEmbedder routes OpenAI-compatible embedding requests through the project selected by LANGDB_PROJECT_ID.

langdb_embedder.py

from os import environ

from agno.knowledge.embedder.langdb import LangDBEmbedder

project_id = environ["LANGDB_PROJECT_ID"]
embedder = LangDBEmbedder(
    base_url=f"https://api.langdb.ai/{project_id}/v1",
)
embedding = embedder.get_embedding(
    "The quick brown fox jumps over the lazy dog."
)

print(f"First values: {embedding[:5]}")
print(f"Dimensions: {len(embedding)}")

The default model is text-embedding-ada-002 with 1536 dimensions. Pass id and dimensions together when selecting another model.

Agno v2.7.2 constructs the legacy api.us-east-1.langdb.ai host when base_url is omitted. LangDB’s current API guide uses api.langdb.ai. Pass base_url as shown above.

Run the Example

1. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   

   uv venv --python 3.12
   .venv\Scripts\activate
   
2. Configure the project

   export LANGDB_API_KEY=your_langdb_api_key_here
   export LANGDB_PROJECT_ID=your_langdb_project_id_here
   
3. Install dependencies

   uv pip install -U agno openai
   
4. Run the example

   python langdb_embedder.py
   

Developer Resources

• Embedders overview
• LangDB API setup
• LangDB embeddings endpoint