Options
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
02-16-2024 12:15 PM
The solution I found was to create those functions in a separated python code called eg. custom_functions.py and deploy as follows in ml flow
with mlflow.start_run() as run:
signature = infer_signature(question, answer)
logged_model = mlflow.langchain.log_model(
chain,
artifact_path="chain",
registered_model_name=registered_model_name,
loader_fn=get_retriever,
persist_dir=persist_directory,
pip_requirements=["mlflow==" + mlflow.__version__,"langchain==" + langchain.__version__,"sentence_transformers","chromadb"],
code_paths=["custom_functions.py"],
#conda_env=conda_env,
input_example=question,
metadata={"task": "llm/v1/chat"},
signature=signature,
await_registration_for=900 # wait for 15 minutes for model registration to complete
)
