updates on quality of life and output changes

app.py

@@ -4,7 +4,7 @@ import mdforest
 import utils
 import os
 
-st.title("Welcome to Concepting")
+st.title("Welcome to Embeddr")
 
 col1, mid, col2 = st.columns([30,5,20])
 with col1:
@@ -57,7 +57,10 @@ if file1 is not None and file2 is not None:
         st.success("Done!")
         
     st.title("Insights generated")
-
+    st.markdown("### The following insights are common to both documents.")
     for result in results:
-        with st.expander("See explanation"):
-            st.write(result)
+        with st.expander(result["name"]):
+            st.write(result["description"])
+            st.markdown("Related Concepts:")
+            for insight in result["concepts"]:
+                st.markdown(f" - {insight}")

insights.prompt

@@ -15,13 +15,10 @@ The more complex concepts in document 2 is : {{complex2}}
 The sentences in one of the clusters is : {{sentences}}
 
 From the sentences and topics above, explain the common idea between the documents and write a paragraph about it and give me 3 new concepts that are linked to this idea. 
-You output format should be:
-
-"""
-name: <FILL-CONCEPT-NAME-HERE>
-description: <FILL-CONCEPT-DESCRIPTION-HERE>
-related:
-- <FILL-RELATED-CONCEPT-1>
-- <FILL-RELATED-CONCEPT-2>
-- <FILL-RELATED-CONCEPT-3>
-"""
+You output format should be in a json format as follows:
+
+{ 
+    "name": "name of the idea",
+    "description": "description of the idea",
+    "concepts": ["concept1", "concept2", "concept3"]
+}

utils.py

@@ -131,7 +131,8 @@ def generate_insights(topics:dict, name1:str, name2:str, text1:str, text2:str, c
 	for cluster_id, sentences in clusters.items():  
 		
 		# print(cluster_id, " ", sentences)
-		final_prompt = PROMPT.replace("{{sentences}}", "\n".join(sentences))
+		final_sentences = "\n".join(sentences)[:4000]
+		final_prompt = PROMPT.replace("{{sentences}}", final_sentences)
 	
 		# with open(f"prompter/insights_{cluster_id}.prompt", "w") as f:
 		# 	f.write(final_prompt)
@@ -141,26 +142,16 @@ def generate_insights(topics:dict, name1:str, name2:str, text1:str, text2:str, c
 			model="text-davinci-003",
 			prompt=final_prompt,
 			max_tokens=200,
-			temperature=0.4,
+			temperature=0.7,
 			top_p=1,
 			frequency_penalty=0.0,
 			presence_penalty=0.0,
 		)
 
 		text = response['choices'][0]['text']
-		# name_location = text.find("Name:")
+		jsonify = json.loads(text)
 		
-		# description_location = text.find("Description:")
-		# name_of_insight = text[name_location+6:name_location+6+text[name_location+6:].find("\n")]
-		# print(name_of_insight)
-		# description = text[:name_location] + text[description_location+13:description_location+13+text[description_location+13:].find("\n")]
-		# print(description)
-		# final_insights.append({"name": name_of_insight, "description": description})
-		
-		# with open(f"prompter/insights_{cluster_id}.prompt", "a") as f:
-		# 	f.write(text)
-   
-		final_insights.append(text)
+		final_insights.append(jsonify)
 	return final_insights