Update main.py

main.py

@@ -1,23 +1,15 @@
-from fastapi import FastAPI
-from fastapi.staticfiles import StaticFiles
-from fastapi.responses import FileResponse
-
 from sentence_transformers import SentenceTransformer
-from sklearn.metrics.pairwise import cosine_similarity
-from transformers import pipeline
+from sklearn.metrics.pairwise import cosine_similarity 
+import subprocess
 
-import requests
+from flask import Flask
+app = Flask(__name__)
 
-app = FastAPI()
- 
-@app.get("/infer_t5")
-def t5(input): 
-    return {"output": "-"}
- 
+def run_command():
+    return subprocess.Popen("./mxbai-embed-large-v1-f16.llamafile --server --nobrowser", shell=False, stdout=subprocess.PIPE).stdout.read()
 
-@app.get("/")
-def index(): 
-    
+@app.route('/app')
+def command_app():   
     # List of sentences to be processed
     sentences = [
         "Poor beggar of the trans gender community begs for instant coffee",
@@ -37,6 +29,48 @@ def index():
     similarity_scores = cosine_similarity([sentence_embeddings[0]], sentence_embeddings[1:])
     return similarity_scores
     
+@app.route('/')
+def command_server():
+    
+    print("command run")
+    return "hi"
+
+
+
+
+
+
+# import requests
+
+# app = FastAPI()
+ 
+# @app.get("/infer_t5")
+# def t5(input): 
+#     return {"output": "-"}
+ 
+
+# @app.get("/")
+# def index(): 
+    
+#     # List of sentences to be processed
+#     sentences = [
+#         "Poor beggar of the trans gender community begs for instant coffee",
+#         "The fish dreamed of escaping the fishbowl and into the toilet where he saw his friend go.",
+#         "The person box was packed with jelly many dozens of months later.",
+#         "Gay drinks both instant coffee and energy drink"
+#     ]
+    
+#     # Initializing the Sentence Transformer model using BERT with mean-tokens pooling
+#     model = SentenceTransformer('bert-base-nli-mean-tokens')
+    
+#     # Encoding the sentences to obtain their embeddings
+#     sentence_embeddings = model.encode(sentences)
+    
+#     # Calculating the cosine similarity between the first sentence embedding and the rest of the embeddings
+#     # The result will be a list of similarity scores between the first sentence and each of the other sentences
+#     similarity_scores = cosine_similarity([sentence_embeddings[0]], sentence_embeddings[1:])
+#     return similarity_scores
+    
 # import requests
 
 # API_URL = "https://api-inference.huggingface.co/models/sentence-transformers/all-MiniLM-L6-v2"