Add app file

app.py

@@ -0,0 +1,95 @@
+import gradio as gr
+import os
+import openai
+import pinecone
+
+openai.api_key = os.environ["OPENAI-API-KEY"]
+
+pinecone.init(
+    api_key=os.environ["PINECONE-API-KEY"],
+    environment="us-east1-gcp",
+)
+
+limit = 5000
+# 3750
+
+embed_model = "text-embedding-ada-002"
+
+index_name = 'extractive-qa'
+index = pinecone.Index(index_name)
+
+# retrieve relevant answers
+def retrieve(query):
+    res = openai.Embedding.create(
+        input=[query],
+        engine=embed_model,
+    )
+
+    # retrieve from Pinecone
+    xq = res['data'][0]['embedding']
+
+    # get relevant contexts
+    res = index.query(xq, top_k=3, include_metadata=True)
+    contexts = [
+        x['metadata']['text'] for x in res['matches']
+    ]
+
+    # build our prompt with the retrieved contexts included
+    prompt_start = (
+        "Answer the question based on the context below.\n\n"+
+        "Context:\n"
+    )
+    prompt_end = (
+        f"\n\nQuestion: {query}\nAnswer:"
+    )
+
+    # append contexts until hitting limit
+    for i in range(1, len(contexts)):
+        if len("\n\n---\n\n".join(contexts[:i])) >= limit:
+            prompt = (
+                prompt_start +
+                "\n\n---\n\n".join(contexts[:i-1]) +
+                prompt_end
+            )
+            break
+        elif i == len(contexts)-1:
+            prompt = (
+                prompt_start +
+                "\n\n---\n\n".join(contexts) +
+                prompt_end
+            )
+    return prompt
+
+# then we complete the context-infused query
+def complete(prompt):
+    # query text-davinci-003
+    response = openai.ChatCompletion.create(
+        model="gpt-4",
+        messages=[
+            {
+                "role": "system",
+                "content": "Answer the question based on the context below."
+            },
+            {
+                "role": "user",
+                "content": prompt
+            }
+        ],
+        temperature=0.5,
+        max_tokens=128,
+        top_p=1.0,
+        frequency_penalty=0.0,
+        presence_penalty=0.0
+    )
+    return response.choices[0].message.content.strip()
+
+def greet(query):
+    # first we retrieve relevant items from Pinecone
+    query_with_contexts = retrieve(query)
+    # return only the main answer
+    result = complete(query_with_contexts)
+    return result
+
+iface = gr.Interface(fn=greet, inputs="text", outputs="text")
+iface.launch()
+