---
title: "Discussion on \"Building an Offline RAG Chatbot: From Semantic Search to LLM Inference with Flask, Chroma DB, Sentence Transformer, Re-ranker and Ollama\" | Hashnode"
description: "Discussion on \"Building an Offline RAG Chatbot: From Semantic Search to LLM Inference with Flask, Chroma DB, Sentence Transformer, Re-ranker and Ollama\". From semantic retrieval to streaming LLM responses in a disconnected enterprise environment\nA Retrieval-Augmented Generation (RAG) chatbot is often demonstrated with a few lines of code, a vector data"
url: "https://hashnode.com/posts/building-an-offline-rag-chatbot-from-semantic-search-to-llm-inference-with-flask-chroma-db-sentence-transformer-re-ranker-and-ollama/6ad275a998db2053e67e553c"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Building an Offline RAG Chatbot: From Semantic Search to LLM Inference with Flask, Chroma DB, Sentence Transformer, Re-ranker and Ollama](https://ameypote.hashnode.dev/building-an-offline-rag-chatbot-from-semantic-search-to-llm-inference-with-flask-chroma-db-sentence-transformer-re-ranker-and-ollama?utm_source=hashnode&utm_medium=feed)

From semantic retrieval to streaming LLM responses in a disconnected enterprise environment A Retrieval-Augmented Generation (RAG) chatbot is often demonstrated with a few lines of code, a vector data

Oct 16 · 36 min read · ameypote.hashnode.dev  
Read the article

-   [#ai](https://hashnode.com/tag/ai)
-   [#rag](https://hashnode.com/tag/rag)
-   [#python](https://hashnode.com/tag/python)
-   [#docker](https://hashnode.com/tag/docker)
-   [#fastapi](https://hashnode.com/tag/fastapi)
-   [#openshift](https://hashnode.com/tag/openshift)
-   [#kubernetes](https://hashnode.com/tag/kubernetes)

## Written by

[Amey Pote](https://hashnode.com/@ameypote)

@ameypote

  
[View profile](https://hashnode.com/@ameypote)

Big Data Explorer with Machine Learning

## Responses

Markdown supported · ⌘↵ to post

No responses yet.
