Update app.py

app.py

@@ -7,7 +7,19 @@ from datasets import load_dataset
 openai.api_key="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"
 from openai.embeddings_utils import get_embedding
 from openai.embeddings_utils import cosine_similarity
+import requests
+model_id = "sentence-transformers/all-MiniLM-L6-v2"
+import json
+hf_token = "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"
+import re
+from sklearn.metrics.pairwise import cosine_similarity
 
+def generate_embeddings(texts, model_id, hf_token):
+    api_url = f"https://api-inference.huggingface.co/pipeline/feature-extraction/{model_id}"
+    headers = {"Authorization": f"Bearer {hf_token}"}
+    response = requests.post(api_url, headers=headers, json={"inputs": texts, "options":{"wait_for_model":True}})
+    embeddings = response.json()
+    return embeddings
 Bio_embeddings = load_dataset('vjain/biology_AP_embeddings')
 
 df = pd.DataFrame(Bio_embeddings['train'])
@@ -17,8 +29,8 @@ df = pd.DataFrame(Bio_embeddings['train'])
 def reply(input):
     
     input = input
-    input_vector = get_embedding(input, engine="text-embedding-ada-002")
-    df["similiarities"]=df["embedding"].apply(lambda x: cosine_similarity(x,input_vector))
+    input_vector = get_embedding(input, mdoel_id,hf_token)
+    df["similiarities"]=df["embedding"].apply(lambda x: cosine_similarity([x],[input_vector])[0][0])
     data = df.sort_values("similiarities", ascending=False).head(20)
     data.to_csv("sorted.csv")
     context = []