Update app.py

app.py

@@ -9,7 +9,17 @@ openai.api_key = os.environ["OPENAI_API_KEY"]
 embedding = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
 vectordb = Chroma(persist_directory='db-DA',
                   embedding_function=embedding)
-retriever = vectordb.as_retriever(search_kwargs={"k": 2})
+retriever = vectordb.as_retriever(search_kwargs={"k": 3})
+
+def remove_duplicates(input_list):
+    return list(dict.fromkeys(input_list))
+
+def format_sources(doc):
+    string = doc.metadata['source'][13:-4]
+    if string == "home":
+        return "https://dupperanalytics.com/"
+    else:
+        return "https://dupperanalytics.com/" + string
 
 def answer(message):
     ctx = retriever.get_relevant_documents(message)
@@ -29,14 +39,12 @@ def answer(message):
         ],
         temperature=0
     )
+    sources_list = remove_duplicates([format_sources(doc) for doc in ctx])
 
-    # long one-liner to format sources into proper url
-    format_sources = lamda doc: "https://dupperanalytics.com/" + doc.metadata['source'][13:-4] if doc.metadata['source'] != "home.txt" else "https://dupperanalytics.com/"
-    
-    sources = "\n\nSources:\n" + "\n".join([format_sources(doc) for doc in ctx])
+    sources = "\n\nSources:\n" + "\n".join(sources_list)
 
     ans = response['choices'][0]['message']['content'] + sources
     return ans
 
-iface = gr.Interface(fn=answer, inputs="text", outputs="text")
+iface = gr.Interface(fn=answer, inputs="text", outputs="text", examples=["Why might I choose DupperAnalytics over other providers?", "What makes the CEO unique?", "What cloud servers do Dupper Analytics use?"])
 iface.launch()