Demo using instructor to extract metadata from search queries
Create a .env
file in the root of the repository with the following content:
- set LLM-specific environment variables in the
.env
file as explained here: https://litellm.vercel.app/#basic-usage - if you are using Langfuse, set up the environment variables as explained here: https://langfuse.com/docs/get-started
Afterwards, your .env
might look like this (using Azure OpenAI and Langfuse):
AZURE_API_KEY = ""
AZURE_API_BASE = ""
AZURE_API_VERSION = ""
LANGFUSE_SECRET_KEY = ""
LANGFUSE_PUBLIC_KEY = ""
LANGFUSE_HOST = ""
- Clone the repository
- Create a Python virtual environment
- Install the requirements:
python -m pip install -r requirements.txt
Run through the Jupyter notebook instructor_search_metadata_demo.ipynb
. Do the suggested exercises.
Please open an issue if you have any questions, feedback or suggestions.