Weaviate is an AI-native vector database. This demo app showcases various capabilities that can be achieved with Weaviate.
This app uses a combination of Weaviate, Streamlit and Ollama, as well as the Cohere API. Note that Ollama and the Cohere API can be replaced with other services that provide similar functionality.
If you are using the Cohere API, you will need to sign up for an account and get an API key. Then, save it as an environment variable with the name COHERE_APIKEY
.
- Clone this repository
- (Optional) Activate a virtual environment
- Run Weaviate with:
docker compose up
- Install the dependencies with
pip install -r requirements.txt
- Run the app with
streamlit run 1_$'\360\237\247\240'_Mind_reading.py
(Orstreamlit run 1_š§ _Mind_reading.py
)
- Weaviate Quickstart
- Sign up for a free Weaviate Cloud sandbox
- More in-depth learning materials on:
- Weaviate Academy
- DeepLearning.ai course on Vector Databases, or on Multimodal search