Initial upload of Streamlit app for keyword similarity

app.py

@@ -0,0 +1,71 @@
+import streamlit as st
+from sentence_transformers import SentenceTransformer
+from sklearn.metrics.pairwise import cosine_similarity
+import openai
+import numpy as np
+
+# App title
+st.title("Keyword Cosine Similarity Tool")
+
+# Inputs
+st.header("Input Parameters")
+primary_keyword = st.text_input("Primary Keyword", placeholder="Enter your primary keyword")
+keywords = st.text_area("Keywords to Compare", placeholder="Enter keywords separated by new lines")
+model_name = st.selectbox("Select Embedding Model", ["sentence-transformers/LaBSE", "all-MiniLM-L6-v2", "OpenAI Embeddings"])
+openai_api_key = st.text_input("OpenAI API Key (optional)", type="password")
+
+# Process Button
+if st.button("Calculate Similarities"):
+    if not primary_keyword or not keywords:
+        st.error("Please provide both the primary keyword and keywords to compare.")
+    else:
+        keyword_list = [kw.strip() for kw in keywords.split("\n") if kw.strip()]
+        
+        if model_name.startswith("sentence-transformers"):
+            # Load model
+            st.info(f"Loading model: {model_name}")
+            model = SentenceTransformer(model_name)
+            
+            # Generate embeddings
+            st.info("Generating embeddings...")
+            primary_embedding = model.encode(primary_keyword, convert_to_tensor=True)
+            keyword_embeddings = model.encode(keyword_list, convert_to_tensor=True)
+        
+        elif model_name == "OpenAI Embeddings":
+            if not openai_api_key:
+                st.error("Please provide your OpenAI API key for this model.")
+            else:
+                openai.api_key = openai_api_key
+                st.info("Generating OpenAI embeddings...")
+                
+                def get_openai_embedding(text):
+                    response = openai.Embedding.create(
+                        model="text-embedding-ada-002",
+                        input=text
+                    )
+                    return np.array(response['data'][0]['embedding'])
+                
+                primary_embedding = get_openai_embedding(primary_keyword)
+                keyword_embeddings = np.array([get_openai_embedding(kw) for kw in keyword_list])
+        
+        else:
+            st.error("Invalid model selection.")
+            st.stop()
+        
+        # Calculate cosine similarities
+        st.info("Calculating cosine similarities...")
+        similarities = cosine_similarity([primary_embedding], keyword_embeddings)[0]
+        
+        # Display results
+        st.header("Results")
+        results = [{"Keyword": kw, "Cosine Similarity": sim} for kw, sim in zip(keyword_list, similarities)]
+        st.table(results)
+        
+        # Debugging/Intermediate Data
+        st.header("Debugging Info")
+        st.write("Primary Embedding:", primary_embedding)
+        st.write("Keyword Embeddings:", keyword_embeddings)
+
+# Footer
+st.markdown("---")
+st.markdown("Created by [Your Name](https://huggingface.co/yourprofile)")

requirements.txt

@@ -0,0 +1,5 @@
+streamlit
+sentence-transformers
+scikit-learn
+openai
+numpy