Spaces:
Sleeping
Sleeping
Update README.md
Browse files
README.md
CHANGED
|
@@ -10,7 +10,18 @@ pinned: false
|
|
| 10 |
hf_oauth: true
|
| 11 |
hf_oauth_scopes:
|
| 12 |
- inference-api
|
| 13 |
-
short_description: 'Contextual Chatbot using Python, LangChain, Llama3.2 (3B)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
---
|
| 15 |
|
| 16 |
An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).
|
|
|
|
| 10 |
hf_oauth: true
|
| 11 |
hf_oauth_scopes:
|
| 12 |
- inference-api
|
| 13 |
+
short_description: 'Contextual Chatbot using Python, LangChain, Llama3.2 (3B)'
|
| 14 |
+
long_description : 'This project is a Contextual PDF ChatBot built with Python, Ollama, LangChain, and ChromaDB.
|
| 15 |
+
It enables users to upload documents (PDFs or images) and interact with them through natural language queries.
|
| 16 |
+
|
| 17 |
+
- **Flask** powers the backend APIs for document upload, query handling, and retrieval.
|
| 18 |
+
- **MongoDB** stores document metadata and conversation history, ensuring persistent and contextual chat.
|
| 19 |
+
- **ChromaDB** manages vector embeddings for efficient semantic search and retrieval.
|
| 20 |
+
- **Llama 3.2 (3B)** is used as the language model, running locally via Ollama.
|
| 21 |
+
|
| 22 |
+
Together, this system provides an end-to-end RAG (Retrieval-Augmented Generation) pipeline for intelligent,
|
| 23 |
+
document-aware conversations.
|
| 24 |
+
'
|
| 25 |
---
|
| 26 |
|
| 27 |
An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).
|