{"slug": "feeding-your-local-data-to-llms-ii", "title": "Feeding Your Local Data to LLMs (II)", "summary": "A developer tutorial demonstrates extending local LLM data feeding by storing embeddings in a Neo4j graph database and combining similarity search with full-text search, using a local LLM and Python packages including langchain_community, tiktoken, neo4j, openai, sentence-transformers, ipywidgets, and pdfplumber.", "body_md": "Member-only story\n\n# Feeding Your Local Data to LLMs (II)\n\n## Using Graph Database combined with full-text search\n\nIn [the previous article](https://medium.com/dev-genius/feeding-your-local-data-to-llms-ec410b3aa95a), I presented a simple way for feeding local data into LLM queries. In this article, it is extended in two ways.\n\n- The embedding will be stored in a graph database\n- Similarity search will be combined with full-text search\n\nI will use Neo4j graph database. For this article, a community version is deployed on Kubernetes. The detailed deployment steps are available in [Deploying Neo4j Graph Database in Kubernetes](https://medium.com/dev-genius/deploying-neo4j-graph-database-in-kubernetes-a367e10bfe0f) article.\n\nThe overall procedure is shown in the diagram below.\n\n## Code Walk-through\n\nIn this section, we will go through a running example code. We use a local LLM and a Neo4j graph database as a knowledge database.\n\nWe install the following Python packages for the example code.\n\n- langchain_community\n- tiktoken\n- neo4j\n- openai\n- sentence-transformers\n- ipywidgets\n- pdfplumber\n\nWe set all the environment specific variables in the `.env` file and load it using the `load_dotenv` function.", "url": "https://wpnews.pro/news/feeding-your-local-data-to-llms-ii", "canonical_source": "https://blog.devgenius.io/feeding-your-local-data-to-llms-ii-c6f7e965acbf?source=rss----4e2c1156667e---4", "published_at": "2026-09-08 12:51:48+00:00", "updated_at": "2026-09-08 13:29:44.765867+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-infrastructure"], "entities": ["Neo4j", "langchain_community", "tiktoken", "openai", "sentence-transformers", "ipywidgets", "pdfplumber"], "alternates": {"html": "https://wpnews.pro/news/feeding-your-local-data-to-llms-ii", "markdown": "https://wpnews.pro/news/feeding-your-local-data-to-llms-ii.md", "text": "https://wpnews.pro/news/feeding-your-local-data-to-llms-ii.txt", "jsonld": "https://wpnews.pro/news/feeding-your-local-data-to-llms-ii.jsonld"}}