mirror of
https://github.com/hwchase17/langchain
synced 2024-10-29 17:07:25 +00:00
78 lines
2.0 KiB
Plaintext
78 lines
2.0 KiB
Plaintext
|
{
|
||
|
|
"cells": [
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"id": "d86853d2",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"# Twitter (via Apify)\n",
|
||
|
|
"\n",
|
||
|
|
"This notebook shows how to load chat messages from Twitter to finetune on. We do this by utilizing Apify. \n",
|
||
|
|
"\n",
|
||
|
|
"First, use Apify to export tweets. An example"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 1,
|
||
|
|
"id": "e5034b4e",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"import json\n",
|
||
|
|
"from langchain.schema import AIMessage\n",
|
||
|
|
"from langchain.adapters.openai import convert_message_to_dict"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 2,
|
||
|
|
"id": "8bf0fb93",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"with open('example_data/dataset_twitter-scraper_2023-08-23_22-13-19-740.json') as f:\n",
|
||
|
|
" data = json.load(f)"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 3,
|
||
|
|
"id": "468124fa",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"# Filter out tweets that reference other tweets, because it's a bit weird\n",
|
||
|
|
"tweets = [d[\"full_text\"] for d in data if \"t.co\" not in d['full_text']]\n",
|
||
|
|
"# Create them as AI messages\n",
|
||
|
|
"messages = [AIMessage(content=t) for t in tweets]\n",
|
||
|
|
"# Add in a system message at the start\n",
|
||
|
|
"# TODO: we could try to extract the subject from the tweets, and put that in the system message.\n",
|
||
|
|
"system_message = {\"role\": \"system\", \"content\": \"write a tweet\"}\n",
|
||
|
|
"data = [[system_message, convert_message_to_dict(m)] for m in messages]"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"kernelspec": {
|
||
|
|
"display_name": "Python 3 (ipykernel)",
|
||
|
|
"language": "python",
|
||
|
|
"name": "python3"
|
||
|
|
},
|
||
|
|
"language_info": {
|
||
|
|
"codemirror_mode": {
|
||
|
|
"name": "ipython",
|
||
|
|
"version": 3
|
||
|
|
},
|
||
|
|
"file_extension": ".py",
|
||
|
|
"mimetype": "text/x-python",
|
||
|
|
"name": "python",
|
||
|
|
"nbconvert_exporter": "python",
|
||
|
|
"pygments_lexer": "ipython3",
|
||
|
|
"version": "3.10.1"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"nbformat": 4,
|
||
|
|
"nbformat_minor": 5
|
||
|
|
}
|