Create app.py

app.py

@@ -0,0 +1,64 @@
+import streamlit as st
+from transformers import AutoTokenizer, AutoModelForCausalLM, AutoModel
+import os
+import pandas as pd
+import numpy as np
+from transformers import pipeline
+from sklearn.metrics.pairwise import cosine_similarity, manhattan_distances, euclidean_distances
+
+
+
+@st.cache
+def load_model():
+    tokenizer = AutoTokenizer.from_pretrained("stanford-crfm/pubmedgpt")
+    model = AutoModel.from_pretrained("stanford-crfm/pubmedgpt")
+    return tokenizer, model
+
+tokenizer, model = load_model()
+pipe = pipeline('feature-extraction', model=model, tokenizer=tokenizer)
+def get_embedding(desc):
+    return np.squeeze(pipe(desc)).mean(axis=0)
+
+
+st.set_page_config(
+    page_title="Clinical Trials Best Match [Eye Diseases]",
+    page_icon="🧑‍💻",
+    layout="wide",
+)
+
+# Constants
+embs = []
+
+# Heading
+st.title('Clinical Trials Search')
+
+
+# Gene File, 128 dim embeddings
+data = np.load("data.npy")
+
+
+@st.cache(allow_output_mutation=True)
+def get_sim(emb_desc, data):
+    ids = []
+    scores = []
+    for i in data:
+        score = cosine_similarity(emb_desc, i['data'])
+        ids.append(i['ids'])
+        scores.append(score)
+    df = pd.DataFrame(data={"url": ids, "scores": scores}).sort_values(by='scores')
+
+    return df
+
+st.subheader("🖮 Enter your clinical trial study description")
+text = st.text_area('Example')
+
+with st.spinner():
+    emb = get_embedding(text)
+
+
+st.subheader("💻 Hit Search")
+
+if st.button("Compute"):
+    with st.spinner('Searching...'):
+        df = get_sim(emb, data=data)
+        st.dataframe(df)