A Philosophy RAG demo

Go to file

Nielson Janné f020257fbe Update readme with .env information		2025-03-15 14:14:58 +01:00
generic_rag	Remove dependency on huggingface and use Ollama	2025-03-15 14:12:24 +01:00
.gitignore	Add .chroma directory to gitignore	2025-03-14 23:50:54 +01:00
.python-version	Initial chainlit + langchain commit	2025-03-11 17:31:24 +01:00
pyproject.toml	Remove dependency on huggingface and use Ollama	2025-03-15 14:12:24 +01:00
README.md	Update readme with .env information	2025-03-15 14:14:58 +01:00
requirements.txt	Add requirements.txt and uv.lock file	2025-03-11 17:31:24 +01:00
uv.lock	Remove dependency on huggingface and use Ollama	2025-03-15 14:12:24 +01:00

README.md

generic-RAG-demo

A Sogeti Nederland generic RAG demo

Getting Started

Please mind due to use of argparse the generic RAG demo can not be launched the usual way chainlit is started.

chainlit run generic_rag/app.py  # will not work

Instead, the app can be launched and debugged the usual way.

python generic_rag/app.py -p data  # will work
python generic_rag/app.py --help  # will work and prints command line options

.env file

A .env file needs to be populated to configure API end-points or local back-ends using environment variables. Currently all required environment variables are defined in code at backend/models.py with the exception of the API key variables itself. More information about configuring API endpoints for langchain can be found at the following locations.

for local models we currently use Ollama

An .env example is as followed.

# only need 1 backend (azure, google, local, etc)

AZURE_OPENAI_API_KEY="<secret_key>"
AZURE_LLM_ENDPOINT="https://<project_hub>.openai.azure.com"
AZURE_LLM_DEPLOYMENT_NAME="gpt-4"
AZURE_LLM_API_VERSION="2025-01-01-preview"
AZURE_EMB_ENDPOINT="https://<project_hub>.openai.azure.com"
AZURE_EMB_DEPLOYMENT_NAME="text-embedding-3-large"
AZURE_EMB_API_VERSION="2023-05-15"

LOCAL_CHAT_MODEL="llama3.1:8b"
LOCAL_EMB_MODEL="llama3.1:8b"

# google vertex AI does not use API keys but a seperate authentication method
GOOGLE_GENAI_CHAT_MODEL="gemini-2.0-flash"
GOOGLE_GENAI_EMB_MODEL="models/text-embedding-004"

Chainlit starters

Chainlit suggestions (starters) can be set with the CHAINLIT_STARTERS environment variable. The variable should be a JSON array of objects with label and message properties. An example is as followed.

CHAINLIT_STARTERS=[{"label":"Label 1","message":"Message one."},{"label":"Label 2","message":"Message two."},{"label":"Label 3","message":"Message three."}]