test

app.py

@@ -20,11 +20,13 @@ 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
+from huggingface_hub import InferenceClient
 
 #zero = torch.Tensor([0]).cuda()
 load_dotenv()
 api_token = os.getenv("HF_TOKEN")
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+
 #@spaces.GPU
 def read_pdf(file_path):
     output = ''
@@ -51,15 +53,43 @@ def read_pdf(file_path):
 
 # Function to query Hugging Face endpoint
 #@spaces.GPU
-def query_huggingface(text):
-    api = InferenceApi(repo_id="google/gemma-2-9b-it", token=api_token)
-    response = api(inputs=text)
-    return response
+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
 
 # Gradio Interface for PDF Processing
 def process_file(file, query):
     pdf_output = read_pdf(file.name)
-    huggingface_output = query_huggingface(query)
+    huggingface_output = respond(query, history=[], system_message="You are a friendly Chatbot.",
+                                max_tokens=1024, temperature=0.0, top_p=1.0 )
     return pdf_output, huggingface_output
 
 # Create Gradio App