trial inf-app

app.py

@@ -1,86 +1,86 @@
 import gradio as gr
 
-# import openai
-# import pinecone
+import openai
+import pinecone
 import requests
 
-# openai.api_key = "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"
-
-# pinecone.init(
-#     api_key="d307ef27-f3ee-4335-b89d-c866395df920",
-#     environment="us-east1-gcp",
-# )
-
-# limit = 5000
-# # 3750
-
-# embed_model = "text-embedding-ada-002"
-
-# index_name = 'gen-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
-#     res = openai.Completion.create(
-#         engine='text-davinci-003',
-#         prompt=prompt,
-#         temperature=0,
-#         max_tokens=500,
-#         top_p=1,
-#         frequency_penalty=0,
-#         presence_penalty=0,
-#         stop=None
-#     )
-#     return res['choices'][0]['text'].strip()
+openai.api_key = "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"
+
+pinecone.init(
+    api_key="d307ef27-f3ee-4335-b89d-c866395df920",
+    environment="us-east1-gcp",
+)
+
+limit = 5000
+# 3750
+
+embed_model = "text-embedding-ada-002"
+
+index_name = 'gen-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
+    res = openai.Completion.create(
+        engine='text-davinci-003',
+        prompt=prompt,
+        temperature=0,
+        max_tokens=500,
+        top_p=1,
+        frequency_penalty=0,
+        presence_penalty=0,
+        stop=None
+    )
+    return res['choices'][0]['text'].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)
+    query_with_contexts = retrieve(query)
+    # return only the main answer
+    result = complete(query_with_contexts)
     response = requests.post("https://siddh4rth-narrify.hf.space/run/predict", json={
         "data": [
             query,