first push

app.py

@@ -0,0 +1,44 @@
+os.system('pip install openpyxl')
+from sklearn.neighbors import NearestNeighbors
+import numpy as np
+import pandas as pd
+
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer('all-mpnet-base-v2') #all-MiniLM-L6-v2 #all-mpnet-base-v2
+
+df = pd.read_parquet('df.parquet')
+df2 = pd.read_parquet('df2.parquet')
+df3 = pd.read_parquet('df3.parquet')
+
+#prepare model
+nbrs1 = NearestNeighbors(n_neighbors=3, algorithm='ball_tree').fit(df2['text_vector_'].values.tolist())
+nbrs2 = NearestNeighbors(n_neighbors=3, algorithm='ball_tree').fit(df3['text_vector_'].values.tolist())
+
+def search1(query, nbrs, full_df, cleaned_df):
+    product = model.encode(query).tolist()
+    # product = df.iloc[0]['text_vector_'] #use one of the products as sample
+
+    distances, indices = nbrs.kneighbors([product]) #input the vector of the reference object
+
+    #print out the description of every recommended product
+    output = cleaned_df.iloc[list(indices)[0]][['text']]
+    full_text =  full_df.loc[range(output.index[0]-1, output.index[0]+2)]['text'].values.tolist()
+    return '\n\n'.join(full_text)
+
+def search_sentences(df):
+    df2['text'].str.split('.', expand=True).stack().reset_index(level=1, drop=True).rename('B').reset_index(drop=True)[0:50]
+
+output = search1('how to speed up data movement', nbrs=nbrs1, full_df=df, cleaned_df=df2)
+output
+
+import gradio as gr
+import os
+
+#the first module becomes text1, the second module file1
+def greet(text1): 
+    return search1(text1, nbrs2, df3, df3)
+    # return search1(text1, df, df2)
+
+iface = gr.Interface(fn=greet, inputs=['text'], outputs=["text"])
+iface.launch(share=False)

df.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35168aa38c8f8decbcd3ce2737befe38cb758120a79ea51c5a7f82e6b204b6db
+size 2416098

df2.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b053d0d39698adeeae12140da1e48ec3c3c21c5d7e4b8246a2076ec2b35235c0
+size 2187807

df3.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9f5f3c6ebb46ca179837746f0ca02137879e26d9f722812eed0be77930e493c
+size 5695689