Create an FAQ bot that can be used in Slack and is trained on public + private data
python3 -m venv env
source env/bin/activate
pip install -r requirements.txt --upgrade
deactivate
There is a .env_sample
file. Rename it to .env
and fill in the values.
We'll run ChromaDB locally using Docker.
Follow the instructions here.
brew install docker-compose
Follow the instructions here.
git clone [email protected]:chroma-core/chroma.git
Start docker
cd chroma
docker-compose up -d --build
You will likely run into an error which requires updating your docker config
nano ~/.docker/config.json
Remove the following line to the file and run the docker-compose command again
"credSstore": "desktop"
Start docker, then go to the chroma folder and run
docker-compose up -d --build
The DB server is exposed to port 8000 on the host machine and we should be able to access it from the host machine at localhost:8000 . We can hit the heartbeat URL http://localhost:8000/api/v1/heartbeat to make sure the server is up and running. If you see a JSON with a nanosecond EPOC timestamp, you're all set!
We will run llama2 locally. Original instructions from this article
Just in case, updated instructions for an M2 are also here. There's quite a bit that no longer works in their documentation.
../../llama.cpp/main -m ../../llama/llama-2-7b-chat/ggml-model-f16_q4_0.gguf \
-t 8 \
-n 128 \
-p 'The first man on the moon was '
python ./lib/get_zendesk_content.py
python ./lib/main.py