test

app.py

@@ -20,6 +20,7 @@ from langchain.schema.runnable import RunnablePassthrough
 from langchain_core.messages import AIMessage, HumanMessage
 from langchain_community.llms import HuggingFaceEndpoint
 from dotenv import load_dotenv
+from huggingface_hub import InferenceApi
 
 #zero = torch.Tensor([0]).cuda()
 
@@ -49,23 +50,16 @@ def read_pdf(file_path):
 
 # Function to query Hugging Face endpoint
 #@spaces.GPU
-# def query_huggingface(text):
-#     print(zero.device)
-#     tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-9b-it")
-#     model = AutoModelForCausalLM.from_pretrained(
-#     "google/gemma-2-9b-it",
-#     device_map="auto",
-#     torch_dtype=torch.bfloat16,
-#         )
-#     input_ids = tokenizer(text, return_tensors="pt").to("cuda")
-#     outputs = model.generate(**input_ids, max_new_tokens=32)
-#     return tokenizer.decode(outputs[0])
+def query_huggingface(text):
+    api = InferenceApi(repo_id="google/gemma-2-9b-it", token="your_token_here")
+    response = api(inputs="Lê Duẩn là ai?")
+    return response
 
 # Gradio Interface for PDF Processing
 def process_file(file, query):
     pdf_output = read_pdf(file.name)
-    #huggingface_output = query_huggingface(query)
-    return pdf_output#, huggingface_output
+    huggingface_output = query_huggingface(query)
+    return pdf_output, huggingface_output
 
 # Create Gradio App
 interface = gr.Interface(

requirements.txt

@@ -17,3 +17,4 @@ sentence-transformers
 faiss-cpu
 bs4
 accelerate
+huggingface_hub