https://github.com/neo4j-examples/langchain-starter-kit
https://github.com/neo4j-examples/langchain-starter-kit
Last synced: about 2 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/neo4j-examples/langchain-starter-kit
- Owner: neo4j-examples
- License: apache-2.0
- Created: 2024-02-26T16:05:40.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-07-28T01:19:54.000Z (11 months ago)
- Last Synced: 2025-05-08T01:42:44.259Z (about 2 months ago)
- Language: Python
- Size: 303 KB
- Stars: 33
- Watchers: 7
- Forks: 7
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
Awesome Lists containing this project
README
# Neo4j LangChain Starter Kit
This kit provides a simple [FastAPI](https://fastapi.tiangolo.com/) backend service connected to [OpenAI](https://platform.openai.com/docs/overview) and [Neo4j](https://neo4j.com/developer/) for powering GenAI projects. The Neo4j interface leverages both [Vector Indexes](https://python.langchain.com/docs/integrations/vectorstores/neo4jvector) and [Text2Cypher](https://python.langchain.com/docs/use_cases/graph/integrations/graph_cypher_qa) chains to provide more accurate results.
## Requirements
- [Poetry](https://python-poetry.org/) for virtual enviroment management
- [LangChain](https://python.langchain.com/docs/get_started/introduction)
- An [OpenAI API Key](https://openai.com/blog/openai-api)
- A running [local](https://neo4j.com/download/) or [cloud](https://neo4j.com/cloud/platform/aura-graph-database/) Neo4j database
## Presumptions
For the vector portion of this kit to work, it presumes the following about the source data:
- There are Nodes labeled 'Chunk' already within the database. This target label type can be changed within app/vector_chain.py file - line 49
- Node records contain a 'text' property with the unstructured data of interest. This can be changed within the app/vector_chain.py file - line 52
- Node records contain a 'sources' property. This is used by LangChain's [RetrievalQAWithSourcesChain](https://api.python.langchain.com/en/latest/chains/langchain.chains.qa_with_sources.retrieval.RetrievalQAWithSourcesChain.html)
## Usage
Add a .env file to the root folder with the following keys and your own credentials (or these included public access only creds):
```
NEO4J_URI=neo4j+ssc://9fcf58c6.databases.neo4j.io
NEO4J_DATABASE=neo4j
NEO4J_USERNAME=public
NEO4J_PASSWORD=read_only
OPENAI_API_KEY=
```
Then run: `poetry run uvicorn app.server:app --reload --port=8000`
Or add env variables at runtime:
```
NEO4J_URI=neo4j+ssc://9fcf58c6.databases.neo4j.io \
NEO4J_DATABASE=neo4j \
NEO4J_USERNAME=public \
NEO4J_PASSWORD=read_only \
OPENAI_API_KEY= \
poetry run uvicorn app.server:app --reload --port=8000 --log-config=log_conf.yaml
```
_NOTE_ the above Neo4j credentials are for read-only access to a hosted sample dataset. Your own OpenAI api key will be needed to run this server.
_NOTE_ the `NEO4J_URI` value can use either the neo4j or [bolt](https://neo4j.com/docs/bolt/current/bolt/) uri scheme. For more details on which to use, see this [example](https://neo4j.com/docs/driver-manual/4.0/client-applications/#driver-configuration-examples)
A FastAPI server should now be running on your local port 8000/api/chat.
## Custom Database Setup
If you would like to load your own instance with a subset of this information. Add your own OpenAI key to the Cypher code in the [edgar_import.cypher](edgar_import.cypher) file and run it in your instance's [Neo4j browser](https://neo4j.com/docs/browser-manual/current/).
For more information on how this load script works, see [this notebook](https://github.com/neo4j-examples/sec-edgar-notebooks/blob/main/notebooks/kg-construction/1-mvg.ipynb).
## Docs
FastAPI will make endpoint information and the ability to test from a browser at http://localhost:8000/docs
## Testing
Alternatively, after the server is running, a curl command can be triggered to test the endpoint:
```
curl --location 'http://127.0.0.1:8000/api/chat' \
--header 'Content-Type: application/json' \
--data '{
"message":"How many forms are there?"}'
```
## Feedback
Please provide feedback and report bugs as [GitHub issues](https://github.com/neo4j-examples/langchain-starter-kit/issues)
## Contributing
Want to improve this kit? See the [contributing guide](./CONTRIBUTING.md)
## Learn More
At [Neo4j GraphAcademy](https://graphacademy.neo4j.com), we offer a wide range of courses completely free of charge, including [Neo4j & LLM Fundamentals](https://graphacademy.neo4j.com/courses/llm-fundamentals/) and [Build a Neo4j-backed Chatbot using Python](https://graphacademy.neo4j.com/courses/llm-chatbot-python/).