Spaces:
Sleeping
Sleeping
Update README.md
Browse files
README.md
CHANGED
@@ -8,6 +8,9 @@ short_description: Self Reflective Multi Agent LangGraph CRAG Application
|
|
8 |
sdk_version: 1.38.0
|
9 |
---
|
10 |
|
|
|
|
|
|
|
11 |
# Overview
|
12 |
This project demonstrates a self Reflective corrective Retrieval Augmented Generation (CRAG) application built using LangGraph. The application leverages a Gemma2 9B LLM to provide informative and relevant responses to user queries. It employs a multi-agent approach, incorporating various components for enhanced performance and user experience.
|
13 |
|
@@ -17,7 +20,6 @@ This project demonstrates a self Reflective corrective Retrieval Augmented Gener
|
|
17 |
* LLM Graders: Evaluates question relevance, answer grounding, and helpfulness to maintain high-quality responses.
|
18 |
* Retrieval and Generation: Combines context retrieval from vector store and web search with LLM generation to provide comprehensive answers.
|
19 |
* Iterative Refinement: Rewrites questions and regenerates answers as needed to ensure accuracy and relevance.
|
20 |
-
* Customization: Offers flexibility in model selection, fine-tuning, and retrieval methods to tailor the application to specific requirements.
|
21 |
* Local Deployment: Can be deployed locally for enhanced user data privacy.
|
22 |
## Technical Specifications
|
23 |
* LLM: Gemma2 9B
|
|
|
8 |
sdk_version: 1.38.0
|
9 |
---
|
10 |
|
11 |
+
# Project presentation
|
12 |
+
https://gamma.app/docs/Info-Assistant-LangGraph-Approach-to-AI-Assistant-ed9thprs24oyhkj
|
13 |
+
|
14 |
# Overview
|
15 |
This project demonstrates a self Reflective corrective Retrieval Augmented Generation (CRAG) application built using LangGraph. The application leverages a Gemma2 9B LLM to provide informative and relevant responses to user queries. It employs a multi-agent approach, incorporating various components for enhanced performance and user experience.
|
16 |
|
|
|
20 |
* LLM Graders: Evaluates question relevance, answer grounding, and helpfulness to maintain high-quality responses.
|
21 |
* Retrieval and Generation: Combines context retrieval from vector store and web search with LLM generation to provide comprehensive answers.
|
22 |
* Iterative Refinement: Rewrites questions and regenerates answers as needed to ensure accuracy and relevance.
|
|
|
23 |
* Local Deployment: Can be deployed locally for enhanced user data privacy.
|
24 |
## Technical Specifications
|
25 |
* LLM: Gemma2 9B
|