This repo contains the source code for Build an LLM RAG Chatbot With LangChain.
Create a .env file in the root directory and add the following environment variables:
NEO4J_URI=<YOUR_NEO4J_URI>
NEO4J_USERNAME=<YOUR_NEO4J_USERNAME>
NEO4J_PASSWORD=<YOUR_NEO4J_PASSWORD>
OPENAI_API_KEY=<YOUR_OPENAI_API_KEY>
HOSPITALS_CSV_PATH=https://raw.githubusercontent.com/hfhoffman1144/langchain_neo4j_rag_app/main/data/hospitals.csv
PAYERS_CSV_PATH=https://raw.githubusercontent.com/hfhoffman1144/langchain_neo4j_rag_app/main/data/payers.csv
PHYSICIANS_CSV_PATH=https://raw.githubusercontent.com/hfhoffman1144/langchain_neo4j_rag_app/main/data/physicians.csv
PATIENTS_CSV_PATH=https://raw.githubusercontent.com/hfhoffman1144/langchain_neo4j_rag_app/main/data/patients.csv
VISITS_CSV_PATH=https://raw.githubusercontent.com/hfhoffman1144/langchain_neo4j_rag_app/main/data/visits.csv
REVIEWS_CSV_PATH=https://raw.githubusercontent.com/hfhoffman1144/langchain_neo4j_rag_app/main/data/reviews.csv
CHATBOT_URL=http://host.docker.internal:8000/hospital-rag-agent
HOSPITAL_AGENT_MODEL=gpt-3.5-turbo-1106
HOSPITAL_CYPHER_MODEL=gpt-3.5-turbo-1106
HOSPITAL_QA_MODEL=gpt-3.5-turboThe three NEO4J_ variables are used to connect to your Neo4j AuraDB instance. Follow the directions here to create a free instance.
The chatbot uses OpenAI LLMs, so you'll need to create an OpenAI API key and store it as OPENAI_API_KEY.
Once you have a running Neo4j instance, and have filled out all the environment variables in .env, you can run the entire project with Docker Compose. You can install Docker Compose by following these directions.
Once you've filled in all of the environment variables, set up a Neo4j AuraDB instance, and installed Docker Compose, open a terminal and run:
$ docker-compose up --buildAfter each container finishes building, you'll be able to access the chatbot api at http://localhost:8000/docs and the Streamlit app at http://localhost:8501/.
