Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| from sentence_transformers import SentenceTransformer, util | |
| import torch | |
| import faiss | |
| import chromadb | |
| # Load the SentenceTransformer model for vector embeddings | |
| model = SentenceTransformer('all-MiniLM-L6-v2') | |
| # FAQ dataset (this can be expanded) | |
| faq_data = [ | |
| ("What is Hugging Face?", "Hugging Face is a company specializing in AI and machine learning, known for their open-source models and datasets."), | |
| ("What is AI?", "Artificial Intelligence (AI) is the simulation of human intelligence in machines.") | |
| # Add more FAQ pairs... | |
| ] | |
| corpus = [item[0] for item in faq_data] # Questions only | |
| answers = {item[0]: item[1] for item in faq_data} # Map questions to answers | |
| corpus_embeddings = model.encode(corpus, convert_to_tensor=True) | |
| # Initialize FAISS Index | |
| index = faiss.IndexFlatL2(corpus_embeddings.shape[1]) | |
| index.add(corpus_embeddings.cpu().numpy()) | |
| # Initialize Chroma vector store | |
| client = chromadb.Client() | |
| collection = client.create_collection(name="faq_data") | |
| for i, text in enumerate(corpus): | |
| collection.add( | |
| ids=[f"faq_{i}"], # Unique ID for each document (using the index i) | |
| documents=[text], | |
| metadatas=[{"source": f"faq_{i}"}], | |
| embeddings=[corpus_embeddings[i].cpu().numpy()], | |
| ) | |
| # Retrieval function using FAISS and Chroma | |
| def retrieve(query): | |
| query_embedding = model.encode(query, convert_to_tensor=True).cpu().numpy() | |
| # Use FAISS for nearest neighbor search | |
| faiss_results = index.search(query_embedding, k=1) | |
| faiss_top_result_idx = faiss_results[1][0][0] | |
| faiss_top_score = faiss_results[0][0][0] | |
| # Use Chroma for semantic search | |
| chroma_results = collection.query(query_embeddings=[query_embedding], n_results=1) | |
| chroma_top_result = chroma_results['documents'][0] | |
| # Combining results from FAISS and Chroma | |
| if faiss_top_score > 0.5: | |
| return answers[corpus[faiss_top_result_idx]] | |
| else: | |
| return chroma_top_result or "Sorry, I didn’t understand that. Could you try asking something else?" | |
| # Gradio interface to interact with the bot | |
| iface = gr.Interface(fn=retrieve, | |
| inputs="text", | |
| outputs="text", | |
| live=True, | |
| title="RAG AI Bot with OCI AI Skills", | |
| description="Ask me anything related to Hugging Face, Oracle OCI AI, or general knowledge!") | |
| # Launch the Gradio interface | |
| iface.launch() |