Spaces:
Running
Running
Jatin Mehra
commited on
Commit
·
68f0395
1
Parent(s):
ab5e975
Update README (HF) with system architecture diagram and enhance section titles for clarity
Browse files- README_hf.md +135 -3
README_hf.md
CHANGED
@@ -16,7 +16,7 @@ An advanced PDF document analysis tool that combines RAG (Retrieval Augmented Ge
|
|
16 |
|
17 |
- [Overview](#overview)
|
18 |
- [Features](#features)
|
19 |
-
- [RAG
|
20 |
- [Architecture](#architecture)
|
21 |
- [Technical Stack](#technical-stack)
|
22 |
- [Installation](#installation)
|
@@ -45,6 +45,7 @@ The application employs an agentic approach that can augment the document's info
|
|
45 |
- **Hugging Face Integration**: Automatic deployment to Hugging Face Spaces
|
46 |
- **Android Application**: Native mobile client
|
47 |
|
|
|
48 |
## RAG System Metrics
|
49 |
|
50 |
1. **Key Metrics Overview**:
|
@@ -81,6 +82,138 @@ The application employs an agentic approach that can augment the document's info
|
|
81 |
|
82 |
The application follows a modular architecture with these main components:
|
83 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
84 |
### Backend Components
|
85 |
|
86 |
1. **PDF Processing Module** (`preprocessing.py`):
|
@@ -226,7 +359,6 @@ PDF-Insight-Beta/
|
|
226 |
- **Java source code**: Activity management, splash screen, and WebView configuration
|
227 |
- **Android resources**: UI layouts, icons, and mobile-specific configurations
|
228 |
|
229 |
-
|
230 |
## Technical Stack
|
231 |
|
232 |
### Backend
|
@@ -264,7 +396,7 @@ PDF-Insight-Beta/
|
|
264 |
|
265 |
1. Clone the repository:
|
266 |
```bash
|
267 |
-
git clone https://github.com/
|
268 |
cd PDF-Insight-Beta
|
269 |
```
|
270 |
|
|
|
16 |
|
17 |
- [Overview](#overview)
|
18 |
- [Features](#features)
|
19 |
+
- [RAG SYSTEM PERFORMANCE](#rag-system-metrics)
|
20 |
- [Architecture](#architecture)
|
21 |
- [Technical Stack](#technical-stack)
|
22 |
- [Installation](#installation)
|
|
|
45 |
- **Hugging Face Integration**: Automatic deployment to Hugging Face Spaces
|
46 |
- **Android Application**: Native mobile client
|
47 |
|
48 |
+
|
49 |
## RAG System Metrics
|
50 |
|
51 |
1. **Key Metrics Overview**:
|
|
|
82 |
|
83 |
The application follows a modular architecture with these main components:
|
84 |
|
85 |
+
### System Architecture Diagram
|
86 |
+
|
87 |
+
```mermaid
|
88 |
+
---
|
89 |
+
config:
|
90 |
+
theme: forest
|
91 |
+
look: neo
|
92 |
+
layout: dagre
|
93 |
+
---
|
94 |
+
flowchart TD
|
95 |
+
subgraph subGraph0["Presentation Layer"]
|
96 |
+
direction TB
|
97 |
+
Browser["Web Browser UI"]
|
98 |
+
Android["Android WebView Client"]
|
99 |
+
end
|
100 |
+
subgraph subGraph1["API Layer"]
|
101 |
+
direction TB
|
102 |
+
APIGateway["FastAPI Entrypoints"]
|
103 |
+
ChatRoutes["chat_routes.py"]
|
104 |
+
SessionRoutes["session_routes.py"]
|
105 |
+
UploadRoutes["upload_routes.py"]
|
106 |
+
UtilityRoutes["utility_routes.py"]
|
107 |
+
AppMain["app.py"]
|
108 |
+
end
|
109 |
+
subgraph subGraph2["Config & Models"]
|
110 |
+
direction TB
|
111 |
+
ConfigLoader["config.py"]
|
112 |
+
DataModels["models.py"]
|
113 |
+
end
|
114 |
+
subgraph subGraph3["Service Layer"]
|
115 |
+
direction TB
|
116 |
+
RAGService["rag_service.py"]
|
117 |
+
LLMService["llm_service.py"]
|
118 |
+
SessionService["session_service.py"]
|
119 |
+
end
|
120 |
+
subgraph subGraph4["Utility Layer"]
|
121 |
+
direction TB
|
122 |
+
TextProc["text_processing.py"]
|
123 |
+
FaissUtil["faiss_utils.py"]
|
124 |
+
SessionUtil["session_utils.py"]
|
125 |
+
end
|
126 |
+
subgraph Storage["Storage"]
|
127 |
+
direction TB
|
128 |
+
UploadStore["/uploads (PDFs & sessions)"]
|
129 |
+
FAISSIndex["FAISS Index (ephemeral/disk)"]
|
130 |
+
end
|
131 |
+
subgraph subGraph6["Docker Container"]
|
132 |
+
direction TB
|
133 |
+
subGraph1
|
134 |
+
subGraph2
|
135 |
+
subGraph3
|
136 |
+
subGraph4
|
137 |
+
Storage
|
138 |
+
end
|
139 |
+
subgraph subGraph7["External & DevOps"]
|
140 |
+
direction TB
|
141 |
+
GroqAPI["Groq LLM API"]
|
142 |
+
TavilyAPI["Tavily Web Search API"]
|
143 |
+
CI["GitHub Actions CI/CD"]
|
144 |
+
HFS["HuggingFace Spaces"]
|
145 |
+
DockerfileNode["Dockerfile"]
|
146 |
+
end
|
147 |
+
subgraph subGraph8["Static Assets"]
|
148 |
+
direction TB
|
149 |
+
StaticApp["Static Web App"]
|
150 |
+
end
|
151 |
+
Browser -- HTTP JSON --> StaticApp
|
152 |
+
StaticApp -- HTTP JSON --> AppMain
|
153 |
+
Android -- HTTP JSON --> AppMain
|
154 |
+
AppMain -- routes --> ChatRoutes & SessionRoutes & UploadRoutes & UtilityRoutes
|
155 |
+
ChatRoutes -- calls --> RAGService
|
156 |
+
SessionRoutes -- calls --> SessionService
|
157 |
+
UploadRoutes -- calls --> TextProc
|
158 |
+
UtilityRoutes -- calls --> SessionUtil
|
159 |
+
RAGService -- uses --> LLMService & FaissUtil
|
160 |
+
RAGService -- calls --> GroqAPI & TavilyAPI
|
161 |
+
LLMService -- uses --> ConfigLoader
|
162 |
+
SessionService -- uses --> SessionUtil
|
163 |
+
TextProc -- writes/reads --> UploadStore
|
164 |
+
SessionUtil -- writes/reads --> UploadStore
|
165 |
+
FaissUtil -- reads/writes --> FAISSIndex
|
166 |
+
CI -- build & deploy --> DockerfileNode
|
167 |
+
DockerfileNode -- deploy --> HFS
|
168 |
+
Browser:::frontend
|
169 |
+
Android:::frontend
|
170 |
+
APIGateway:::api
|
171 |
+
ChatRoutes:::api
|
172 |
+
SessionRoutes:::api
|
173 |
+
UploadRoutes:::api
|
174 |
+
UtilityRoutes:::api
|
175 |
+
AppMain:::api
|
176 |
+
ConfigLoader:::service
|
177 |
+
DataModels:::service
|
178 |
+
RAGService:::service
|
179 |
+
LLMService:::service
|
180 |
+
SessionService:::service
|
181 |
+
TextProc:::util
|
182 |
+
FaissUtil:::util
|
183 |
+
SessionUtil:::util
|
184 |
+
UploadStore:::util
|
185 |
+
FAISSIndex:::util
|
186 |
+
GroqAPI:::external
|
187 |
+
TavilyAPI:::external
|
188 |
+
CI:::devops
|
189 |
+
HFS:::devops
|
190 |
+
DockerfileNode:::devops
|
191 |
+
StaticApp:::frontend
|
192 |
+
classDef frontend fill:#CCE5FF,stroke:#333,stroke-width:1px
|
193 |
+
classDef api fill:#DFFFD6,stroke:#333,stroke-width:1px
|
194 |
+
classDef service fill:#FFE5B4,stroke:#333,stroke-width:1px
|
195 |
+
classDef util fill:#E3E4FA,stroke:#333,stroke-width:1px
|
196 |
+
classDef external fill:#E0E0E0,stroke:#333,stroke-width:1px
|
197 |
+
classDef devops fill:#CCFFFF,stroke:#333,stroke-width:1px
|
198 |
+
click Android "https://github.com/jatin-mehra119/pdf-insight-beta/blob/main/Android%20App/app/src/main/res/layout/activity_splash.xml"
|
199 |
+
click ChatRoutes "https://github.com/jatin-mehra119/pdf-insight-beta/blob/main/api/chat_routes.py"
|
200 |
+
click SessionRoutes "https://github.com/jatin-mehra119/pdf-insight-beta/blob/main/api/session_routes.py"
|
201 |
+
click UploadRoutes "https://github.com/jatin-mehra119/pdf-insight-beta/blob/main/api/upload_routes.py"
|
202 |
+
click UtilityRoutes "https://github.com/jatin-mehra119/pdf-insight-beta/blob/main/api/utility_routes.py"
|
203 |
+
click AppMain "https://github.com/jatin-mehra119/pdf-insight-beta/blob/main/app.py"
|
204 |
+
click ConfigLoader "https://github.com/jatin-mehra119/pdf-insight-beta/blob/main/configs/config.py"
|
205 |
+
click DataModels "https://github.com/jatin-mehra119/pdf-insight-beta/blob/main/models/models.py"
|
206 |
+
click RAGService "https://github.com/jatin-mehra119/pdf-insight-beta/blob/main/services/rag_service.py"
|
207 |
+
click LLMService "https://github.com/jatin-mehra119/pdf-insight-beta/blob/main/services/llm_service.py"
|
208 |
+
click SessionService "https://github.com/jatin-mehra119/pdf-insight-beta/blob/main/services/session_service.py"
|
209 |
+
click TextProc "https://github.com/jatin-mehra119/pdf-insight-beta/blob/main/utils/text_processing.py"
|
210 |
+
click FaissUtil "https://github.com/jatin-mehra119/pdf-insight-beta/blob/main/utils/faiss_utils.py"
|
211 |
+
click SessionUtil "https://github.com/jatin-mehra119/pdf-insight-beta/blob/main/utils/session_utils.py"
|
212 |
+
click CI "https://github.com/jatin-mehra119/pdf-insight-beta/blob/main/.github/workflows/sync_to_hf.yml"
|
213 |
+
click DockerfileNode "https://github.com/jatin-mehra119/pdf-insight-beta/tree/main/Dockerfile"
|
214 |
+
click StaticApp "https://github.com/jatin-mehra119/pdf-insight-beta/blob/main/static/js/app.js"
|
215 |
+
```
|
216 |
+
|
217 |
### Backend Components
|
218 |
|
219 |
1. **PDF Processing Module** (`preprocessing.py`):
|
|
|
359 |
- **Java source code**: Activity management, splash screen, and WebView configuration
|
360 |
- **Android resources**: UI layouts, icons, and mobile-specific configurations
|
361 |
|
|
|
362 |
## Technical Stack
|
363 |
|
364 |
### Backend
|
|
|
396 |
|
397 |
1. Clone the repository:
|
398 |
```bash
|
399 |
+
git clone https://github.com/Jatin-Mehra119/PDF-Insight-Beta.git
|
400 |
cd PDF-Insight-Beta
|
401 |
```
|
402 |
|