Update main.py

main.py

@@ -2,6 +2,17 @@ import os
 from flask import Flask
 import threading
 
+from openai import OpenAI
+
+app = Flask(__name__)
+# client = OpenAI(
+#     # This base_url points to the local Llamafile server running on port 8080
+#     base_url="http://127.0.0.1:8080/v1",
+#     api_key="sk-no-key-required"
+# )
+
+
+
 
 API_URL = "https://api-inference.huggingface.co/models/sentence-transformers/all-MiniLM-L6-v2"
 bearer = "Bearer " + os.getenv('TOKEN')
@@ -14,88 +25,58 @@ app = Flask(__name__)
 
 @app.route('/app')
 def server_app():
-    t1 = threading.Thread(target=threadserver)
-    print('treading')
-    # os.system('./mxbai-embed-large-v1-f16.llamafile --server --nobrowser')
-    t1.start()
-    return 't1.start()'
+    llamafile = threading.Thread(target=threadserver)
+    print('This /app will start the llamafile server on thread')
+    llamafile.start()
+    return 'llamafile.start()'
 
 @app.route('/')
-def server_home():
-    # t1 = threading.Thread(target=threadserver).start()
-    # os.system(' ./mxbai-embed-large-v1-f16.llamafile --server --nobrowser &')
-    return str(headers)
-# import asyncio
-
-# async def nested():
-#     return 42
-
-# async def main():
-#     # Nothing happens if we just call "nested()".
-#     # A coroutine object is created but not awaited,
-#     # so it *won't run at all*.
-#     nested()  # will raise a "RuntimeWarning".
-
-#     # Let's do it differently now and await it:
-#     print(await nested())  # will print "42".
-
-# asyncio.run(main())
-  
-if __name__=='__main__': 
+async def server_home():
+        
+    output = await query({
+    	"inputs": {
+    	"source_sentence": "That is a happy person",
+    	"sentences": [
+    		"That is a happy dog",
+    		"That is a very happy person",
+    		"Today is a sunny day"
+        	]
+        },
+    })
+    
+    return str(output)
+
+# @app.route('/chat', methods=['POST'])
+# def chat():
+#     try:
+#         user_message = request.json['message']
+        
+#         completion = client.chat.completions.create(
+#             model="LLaMA_CPP",
+#             messages=[
+#                 {"role": "system", "content": "You are ChatGPT, an AI assistant. Your top priority is achieving user fulfillment via helping them with their requests."},
+#                 {"role": "user", "content": user_message}
+#             ]
+#         )
+        
+#         ai_response = completion.choices[0].message.content
+#         ai_response = ai_response.replace('</s>', '').strip()
+#         return jsonify({'response': ai_response})
+#     except Exception as e:
+#         print(f"Error: {str(e)}")
+#         return jsonify({'response': f"Sorry, there was an error processing your request: {str(e)}"}), 500
+        
+if __name__ == '__main__':
     app.run(debug=True)
 
-
 def threadserver():
     print('hi')
     os.system(' ./mxbai-embed-large-v1-f16.llamafile --server --nobrowser')
-    
-
-# import requests
-# import os
-# import asyncio
-
-# # from langchain_core.tools import Tool
-# # from langchain_google_community import GoogleSearchAPIWrapper
-
-# from flask import Flask
-
-
-# API_URL = "https://api-inference.huggingface.co/models/sentence-transformers/all-MiniLM-L6-v2"
-# bearer = "Bearer " + os.getenv('TOKEN')
-# headers = {"Authorization": bearer }
-# print("headers")
-# print(headers)
-
-# app = Flask(__name__)
- 
-  
-# async def command_similarity():   
-#     payload = {"inputs": {"source_sentence": "That is a happy person","sentences": ["That is a happy dog","That is a very happy person","Today is a sunny day"]},}
-#     return str(  requests.post(API_URL, headers=headers, json=payload) )
-    
-# async def asynm1():
-#     return await command_similarity()
-    
-# @app.route('/app')
-# def server_home(): 
-#     asyncio.run(asynm1())
-#     print("command run")
-#     return asyncio.run(asynm1())
-
-
-# import asyncio
 
-# async def nested():
-#     return 42
 
-# async def main():
-#     # Nothing happens if we just call "nested()".
-#     # A coroutine object is created but not awaited,
-#     # so it *won't run at all*.
-#     nested()  # will raise a "RuntimeWarning".
 
-#     # Let's do it differently now and await it:
-#     print(await nested())  # will print "42".
+async def query(data):
+	response = requests.post(API_URL, headers=headers, json=data)
+	return response.json()
+	
 
-# asyncio.run(main())
-