Update app.py

app.py

@@ -4,7 +4,11 @@ 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")
+#client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+import google.generativeai as genai
+os.environ["API_KEY"] = 'AIzaSyB8Hj4oCbBH9arFWSgybHnbpZLs2sa4p1w'
+os.environ["GOOGLE_API_KEY"] = 'AIzaSyBjuYTWBlHg4W2wGaQCKKbigz6deZuLUJc'
+genai.configure(api_key=os.environ["API_KEY"])
 
 global context
 
@@ -383,6 +387,49 @@ Link: https://www.deeplearning.ai/short-courses/ai-agents-in-langgraph/
 
 '''
 
+os.environ["LANGCHAIN_API_KEY"] = "ls__92a67c6930624f93aa427f1c1ad3f59b"
+os.environ["LANGCHAIN_TRACING_V2"] = "true"
+os.environ["LANGCHAIN_PROJECT"] = "agenta"
+generation_config = {
+  "temperature": 0.2,
+  "top_p": 0.95,
+  "top_k": 0,
+  "max_output_tokens": 8192,
+}
+
+safety_settings = [
+  {
+    "category": "HARM_CATEGORY_HARASSMENT",
+    "threshold": "BLOCK_MEDIUM_AND_ABOVE"
+  },
+  {
+    "category": "HARM_CATEGORY_HATE_SPEECH",
+    "threshold": "BLOCK_MEDIUM_AND_ABOVE"
+  },
+  {
+    "category": "HARM_CATEGORY_SEXUALLY_EXPLICIT",
+    "threshold": "BLOCK_MEDIUM_AND_ABOVE"
+  },
+  {
+    "category": "HARM_CATEGORY_DANGEROUS_CONTENT",
+    "threshold": "BLOCK_MEDIUM_AND_ABOVE"
+  },
+]
+
+system_instruction = context
+import re
+
+model = genai.GenerativeModel(model_name="gemini-1.5-pro-latest",
+                              generation_config=generation_config,
+                              system_instruction=system_instruction,
+                              safety_settings=safety_settings)
+
+
+def model_response(text):
+    #model = genai.GenerativeModel('gemini-pro')
+    response = model.generate_content(text)
+    return response.text
+
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -397,19 +444,10 @@ def respond(
 
     messages.append({"role": "user", "content": message})
 
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=768,
-        stream=True,
-        temperature=0.3,
-        top_p=0.3,
-    ):
-        token = message.choices[0].delta.content
+    #response = ""
+    response = model_response(messages)
+    return response
 
-        response += token
-        yield response
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface