Update app.py

app.py

@@ -1,20 +1,141 @@
+# import gradio as gr
+# from huggingface_hub import InferenceClient
+
+# """
+# For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
+# """
+# client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+
+
+# def respond(
+#     message,
+#     history: list[tuple[str, str]],
+#     system_message,
+#     max_tokens,
+#     temperature,
+#     top_p,
+# ):
+#     messages = [{"role": "system", "content": system_message}]
+
+#     for val in history:
+#         if val[0]:
+#             messages.append({"role": "user", "content": val[0]})
+#         if val[1]:
+#             messages.append({"role": "assistant", "content": val[1]})
+
+#     messages.append({"role": "user", "content": message})
+
+#     response = ""
+
+#     for message in client.chat_completion(
+#         messages,
+#         max_tokens=max_tokens,
+#         stream=True,
+#         temperature=temperature,
+#         top_p=top_p,
+#     ):
+#         token = message.choices[0].delta.content
+
+#         response += token
+#         yield response
+
+# """
+# For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+# """
+# demo = gr.ChatInterface(
+#     respond,
+#     additional_inputs=[
+#         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+#         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+#         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
+#         gr.Slider(
+#             minimum=0.1,
+#             maximum=1.0,
+#             value=0.95,
+#             step=0.05,
+#             label="Top-p (nucleus sampling)",
+#         ),
+#     ],
+# )
+
+
+# if __name__ == "__main__":
+#     demo.launch()
+
+
+
 import gradio as gr
 from huggingface_hub import InferenceClient
+import torch
+from transformers import RagRetriever, RagSequenceForGeneration, AutoTokenizer
 
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+
+def strip_title(title):
+    if title.startswith('"'):
+        title = title[1:]
+    if title.endswith('"'):
+        title = title[:-1]
+    return title
+
+def retrieved_info(rag_model, query):
+    # Tokenize query
+    retriever_input_ids = rag_model.retriever.question_encoder_tokenizer.batch_encode_plus(
+        [query],
+        return_tensors="pt",
+        padding=True,
+        truncation=True,
+    )["input_ids"].to(device)
+
+    # Retrieve documents
+    question_enc_outputs = rag_model.rag.question_encoder(retriever_input_ids)
+    question_enc_pool_output = question_enc_outputs[0]
+
+    result = rag_model.retriever(
+        retriever_input_ids,
+        question_enc_pool_output.cpu().detach().to(torch.float32).numpy(),
+        prefix=rag_model.rag.generator.config.prefix,
+        n_docs=rag_model.config.n_docs,
+        return_tensors="pt",
+    )
+
+    # Display retrieved documents including URLs
+    all_docs = rag_model.retriever.index.get_doc_dicts(result.doc_ids)
+    retrieved_context = []
+    for docs in all_docs:
+        titles = [strip_title(title) for title in docs["title"]]
+        texts = docs["text"]
+        for title, text in zip(titles, texts):
+            #print(f"Title: {title}")
+            #print(f"Context: {text}")
+            retrieved_context.append(f"{title}: {text}")
+
+    answer = retrieved_context
+
+
 
 
 def respond(
     message,
     history: list[tuple[str, str]],
     system_message,
-    max_tokens,
-    temperature,
-    top_p,
 ):
+    # Load model
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    
+    dataset_path = "/IndexedDataFiles/my_knowledge_dataset"
+    index_path = "/IndexedDataFiles/my_knowledge_dataset_hnsw_index.faiss"
+    
+    tokenizer = AutoTokenizer.from_pretrained("facebook/rag-sequence-nq")
+    retriever = RagRetriever.from_pretrained("facebook/rag-sequence-nq", index_name="custom",
+                                             passages_path = dataset_path,
+                                             index_path = index_path,
+                                             n_docs = 1)
+    rag_model = RagSequenceForGeneration.from_pretrained('facebook/rag-sequence-nq', retriever=retriever)
+    rag_model.retriever.init_retrieval()
+    rag_model.to(device)
     messages = [{"role": "system", "content": system_message}]
 
     for val in history:
@@ -25,19 +146,11 @@ def respond(
 
     messages.append({"role": "user", "content": message})
 
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+    #response = ""
+    
+    response = retrieved_info(rag_model, message)
 
-        response += token
-        yield response
+    yield response
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
@@ -60,4 +173,4 @@ demo = gr.ChatInterface(
 
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()