Update get_similar_profiles.py

get_similar_profiles.py

@@ -17,9 +17,30 @@ def _get_embedding(text, model="text-embedding-3-large"):
         None
     return client.embeddings.create(input = [text], model=model).data[0].embedding
 
+def build_complementary(profile):
+    complementary = client.chat.completions.create(
+    model="gpt-4",
+    messages=[
+    {
+      "role": "system",
+      "content": "Follow the Entrepreneur First Edge method to list out as bullet points the main complementary characteristic of the proposed profiles. We aim at building the teams that are most likely to success"
+    },
+    {
+      "role": "user",
+      "content": f"PROFILE: \n\n{profile}\n\nCOMPLEMENTARY PROFILE:"
+        }
+      ],
+      temperature=1,
+      max_tokens=1110,
+      top_p=1,
+      frequency_penalty=0,
+      presence_penalty=0
+    ).choices[0].message.content
+    return complementary
 
 def get_similar_profiles(profile, prefix, k=20):
   query = prefix + profile + cohort_data[profile]
+  complementary = build_complementary(query)
   df = pd.read_csv("embedded_cohort.csv")
   embedding_query = _get_embedding(query, model="text-embedding-3-large")
   df['similarity'] = df.embeddings.apply(lambda x: cosine_similarity(eval(x), embedding_query))
@@ -38,5 +59,4 @@ def get_similar_profiles(profile, prefix, k=20):
     for result in results:
         final_md += "### " + result.replace("\n","\n\n")
     
-    # breakpoint()
   return final_md