Tutorial/Agentic rag (lancedb#205)

* updated README.md * Add files via upload * Update README.md * Update README.md * Update README for agentic rag * Update README.md * Update README.md * Update README.md * fix path * Update and rename tutorials/Agentic_RAG/main.ipynb to tutorials/Agentic_RAG/data/info.txt * Add files via upload * added medium blog link * Add files via upload * remove ghost blog . added personal medium blog link in readme
raghavdixit99 · Jun 9, 2024 · 08734ea · 08734ea
1 parent d62902a
commit 08734ea
Show file tree

Hide file tree

Showing 6 changed files with 410 additions and 1 deletion.
diff --git a/README.md b/README.md
@@ -4,7 +4,7 @@ Dive into building GenAI applications!
 This repository contains examples, applications, starter code, & tutorials to help you kickstart your GenAI projects.
 
 - These are built using LanceDB, a free, open-source, serverless vectorDB that **requires no setup**. 
-- It **integrates into python data ecosystem** so you can simply start using these in your existing data pipelines in pandas, arrow, pydantic etc.
+- It **integrates into Python data ecosystem** so you can simply start using these in your existing data pipelines in pandas, arrow, pydantic etc.
 - LanceDB has **native Typescript SDK** using which you can **run vector search** in serverless functions!
 
 <img src="https://github.com/lancedb/vectordb-recipes/assets/5846846/d284accb-24b9-4404-8605-56483160e579" height="85%" width="85%" />
@@ -58,6 +58,7 @@ The following examples are organized into different tables to make similar types
 | [Improve RAG with FLARE](./examples/better-rag-FLAIR) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/better-rag-FLAIR/main.ipynb) [![local LLM](https://img.shields.io/badge/local-llm-green)](#) [![LLM](https://img.shields.io/badge/openai-api-white)](#) [![advanced](https://img.shields.io/badge/advanced-FF3333)](#)|[![Ghost](https://img.shields.io/badge/ghost-000?style=for-the-badge&logo=ghost&logoColor=%23F7DF1E)](https://blog.lancedb.com/better-rag-with-active-retrieval-augmented-generation-flare-3b66646e2a9f/) |
 | [Query Expansion and Reranker ](/examples/QueryExpansion&Reranker/) | <a href="https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/QueryExpansion&Reranker/main.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>  [![LLM](https://img.shields.io/badge/openai-api-white)](#) [![advanced](https://img.shields.io/badge/advanced-FF3333)](#)|[![Ghost](https://img.shields.io/badge/ghost-000?style=for-the-badge&logo=ghost&logoColor=%23F7DF1E)](https://blog.lancedb.com/improving-rag-with-query-expansion-reranking-models/)|
 | [RAG Fusion](/examples/RAG_Fusion/) | <a href="https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/RAG_Fusion/main.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>   [![LLM](https://img.shields.io/badge/openai-api-white)](#) [![advanced](https://img.shields.io/badge/advanced-FF3333)](#)|
+| [Agentic RAG ](/tutorials/Agentic_RAG/) | <a href="https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/tutorials/Agentic_RAG/main.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>  [![LLM](https://img.shields.io/badge/openai-api-white)](#) [![advanced](https://img.shields.io/badge/advanced-FF3333)](#)|
 ||||
 
 

diff --git a/tutorials/Agentic_RAG/README.md b/tutorials/Agentic_RAG/README.md
@@ -0,0 +1,28 @@
+## Agentic RAG
+Agentic RAG  is an advanced framework designed to handle complex information retrieval tasks using a network of intelligent agents. 
+These agents collaborate to perform nuanced tasks such as synthesizing information from multiple documents,
+summarizing content, and comparing data points across various sources. Agentic RAG infuses autonomy and 
+intelligence into traditional retrieval systems, enabling them to act as proactive entities that
+understand context, evaluate data quality, and make informed decisions.
+
+
+## Implementation Example with Langraph and LanceDB
+
+
+Install necessary packages:
+```
+!pip install langchain-community tiktoken langchain-openai langchainhub lancedb  langchain langgraph langchain-text-splitters langchain_openai gradio
+
+```
+
+## Google Colab Walkthrough
+For a detailed, interactive walkthrough of this implementation, you can explore the Google Colab notebook provided below. 
+This notebook includes support for ***Gradio***, making it easier to create UIs for your machine-learning models, 
+ensuring a more interactive and user-friendly experience.
+
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/tutorials/Agentic_RAG/main.ipynb)
+
+
+## Blog
+
+For a detailed explanation of agentic rag, check out  [blog post on Medium](https://aksdesai1998.medium.com/662bac582da9).
diff --git a/tutorials/Agentic_RAG/data/CIEP.pdf b/tutorials/Agentic_RAG/data/CIEP.pdf
diff --git a/tutorials/Agentic_RAG/data/GAE.pdf b/tutorials/Agentic_RAG/data/GAE.pdf
diff --git a/tutorials/Agentic_RAG/data/info.txt b/tutorials/Agentic_RAG/data/info.txt
@@ -0,0 +1 @@
+data take from exim website