Spaces:
Sleeping
Sleeping
File size: 2,123 Bytes
11ac44e a98d978 11ac44e 09d4b23 11ac44e f18d0df 11ac44e f18d0df 11ac44e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 |
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="asia-southeast1-gcp-free",
)
limit = 5000
# 3750
embed_model = "text-embedding-ada-002"
index_name = 'consulting-docs'
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)
return result
iface = gr.Interface(fn=greet, inputs="text", outputs="text")
iface.launch()
|