Update README.md
Browse files
README.md
CHANGED
|
@@ -33,7 +33,6 @@ Unlike traditional RAG (Retrieval Augmented Generation) apps, this project lever
|
|
| 33 |
IngestTool[π₯ Ingestion Tool]
|
| 34 |
SearchTool[π Search Tool]
|
| 35 |
GenTool[β¨ Generative Tool]
|
| 36 |
-
VoiceTool[π£οΈ Voice Tool]
|
| 37 |
PodTool[π§ Podcast Tool]
|
| 38 |
end
|
| 39 |
end
|
|
@@ -59,14 +58,16 @@ Unlike traditional RAG (Retrieval Augmented Generation) apps, this project lever
|
|
| 59 |
IngestTool --> DocStore
|
| 60 |
SearchTool --> VecStore
|
| 61 |
GenTool --> LLM
|
| 62 |
-
|
| 63 |
-
VoiceTool --> LlamaIndex
|
| 64 |
PodTool --> ElevenLabs
|
| 65 |
PodTool --> LLM
|
| 66 |
```
|
| 67 |
|
| 68 |
|
| 69 |
-
|
|
|
|
|
|
|
|
|
|
| 70 |
|
| 71 |
## π Quick Start
|
| 72 |
|
|
@@ -74,7 +75,7 @@ Check out [QUICKSTART.md](QUICKSTART.md) for detailed local setup instructions.
|
|
| 74 |
|
| 75 |
1. **Clone & Install**:
|
| 76 |
```bash
|
| 77 |
-
git clone https://huggingface.co/spaces/
|
| 78 |
pip install -r requirements.txt
|
| 79 |
```
|
| 80 |
2. **Configure**: Add your `OPENAI_API_KEY` and `ELEVENLABS_API_KEY` to `.env`.
|
|
@@ -83,17 +84,17 @@ Check out [QUICKSTART.md](QUICKSTART.md) for detailed local setup instructions.
|
|
| 83 |
## π‘ How It Works
|
| 84 |
|
| 85 |
### 1. The MCP Core
|
| 86 |
-
At the heart of the application is the `
|
| 87 |
|
| 88 |
### 2. Voice & Podcast Generation
|
| 89 |
We use **ElevenLabs** for state-of-the-art text-to-speech.
|
| 90 |
-
- **
|
| 91 |
- **Podcast Mode**: An LLM first generates a script based on your documents, then we use multi-speaker synthesis to create a realistic dialogue.
|
| 92 |
|
| 93 |
## π Hackathon Tracks
|
| 94 |
|
| 95 |
We are submitting to:
|
| 96 |
-
- **Building MCP**: For our custom `
|
| 97 |
- **MCP in Action (Consumer/Creative)**: For the innovative Podcast and Voice interfaces that make personal knowledge management accessible and fun.
|
| 98 |
|
| 99 |
## π License
|
|
|
|
| 33 |
IngestTool[π₯ Ingestion Tool]
|
| 34 |
SearchTool[π Search Tool]
|
| 35 |
GenTool[β¨ Generative Tool]
|
|
|
|
| 36 |
PodTool[π§ Podcast Tool]
|
| 37 |
end
|
| 38 |
end
|
|
|
|
| 58 |
IngestTool --> DocStore
|
| 59 |
SearchTool --> VecStore
|
| 60 |
GenTool --> LLM
|
| 61 |
+
PodTool --> LlamaIndex
|
|
|
|
| 62 |
PodTool --> ElevenLabs
|
| 63 |
PodTool --> LLM
|
| 64 |
```
|
| 65 |
|
| 66 |
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+

|
| 70 |
+
|
| 71 |
|
| 72 |
## π Quick Start
|
| 73 |
|
|
|
|
| 75 |
|
| 76 |
1. **Clone & Install**:
|
| 77 |
```bash
|
| 78 |
+
git clone https://huggingface.co/spaces/Nihal2000/AiDigitalLibraryAssistant
|
| 79 |
pip install -r requirements.txt
|
| 80 |
```
|
| 81 |
2. **Configure**: Add your `OPENAI_API_KEY` and `ELEVENLABS_API_KEY` to `.env`.
|
|
|
|
| 84 |
## π‘ How It Works
|
| 85 |
|
| 86 |
### 1. The MCP Core
|
| 87 |
+
At the heart of the application is the `AiDigitalLibraryAssistant`. It exposes atomic capabilities (Tools) that the frontend consumes. This means the same tools powering this UI could be connected to Claude Desktop or any other MCP client!
|
| 88 |
|
| 89 |
### 2. Voice & Podcast Generation
|
| 90 |
We use **ElevenLabs** for state-of-the-art text-to-speech.
|
| 91 |
+
- **Podcast Mode**: Uses a dedicated LlamaIndex agent to maintain conversation context, converting speech-to-text, querying the library, and streaming audio back.
|
| 92 |
- **Podcast Mode**: An LLM first generates a script based on your documents, then we use multi-speaker synthesis to create a realistic dialogue.
|
| 93 |
|
| 94 |
## π Hackathon Tracks
|
| 95 |
|
| 96 |
We are submitting to:
|
| 97 |
+
- **Building MCP**: For our custom `AiDigitalLibraryAssistant` MCP server implementation.
|
| 98 |
- **MCP in Action (Consumer/Creative)**: For the innovative Podcast and Voice interfaces that make personal knowledge management accessible and fun.
|
| 99 |
|
| 100 |
## π License
|