Very good. Did you find some tutorial about covering all this process?
upvoting this! Any tutorials? Did you find some tutorial about covering all this process?
1 Like
You can ref this notebook to use embedding to answer questions based on own knowlage.
{
"cells": [
{
"cell_type": "markdown",
"id": "c4ca8276-e829-4cff-8905-47534e4b4d4e",
"metadata": {},
"source": [
"# Question Answering using Embeddings\n",
"\n",
"Many use cases require GPT-3 to respond to user questions with insightful answers. For example, a customer support chatbot may need to provide answers to common questions. The GPT models have picked up a lot of general knowledge in training, but we often need to ingest and use a large library of more specific information.\n",
"\n",
"In this notebook we will demonstrate a method for enabling GPT-3 to answer questions using a library of text as a reference, by using document embeddings and retrieval. We'll be using a dataset of Wikipedia articles about the 2020 Summer Olympic Games. Please see [this notebook](fine-tuned_qa/olympics-1-collect-data.ipynb) to follow the data gathering process."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "9e3839a6-9146-4f60-b74b-19abbc24278d",
"metadata": {},
"outputs": [],
show original
1 Like
@i-technology you can use “langchain” lib to ingest the data ( pdf,txt,json etc) … Same lib offers text Chunking/spiltting, Embeddings , Vector store database , and now you can ask questions on your entire data
Thanks, but my post was from over 3 months ago
So yes I’ve done this and it’s actually quite limited since in the end you are just sending back a few snippets to gpt for summarization
So outside those snippets, gpt has virtually no clue what you are talking about
