From 2795fba1941503620aab2e624a891ab09f5e3d3b Mon Sep 17 00:00:00 2001
From: James Shiffer <jamesnshiffer@gmail.com>
Date: Sun, 26 Dec 2021 11:55:19 -0800
Subject: [PATCH] Updated readme, minor configuration stuff

---
 README.md              |  61 ++++++++++++++++++++++++++++++++++++++++-
 requirements.txt       | Bin 1278 -> 1176 bytes
 src/scraper/scraper.py |   2 +-
 3 files changed, 61 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 6d1c17e..39dea30 100644
--- a/README.md
+++ b/README.md
@@ -1,3 +1,62 @@
 # miku
 
-Discord bot/companion for the group chatte, powered by the GPT-J language model and modified with a soft prompt to understand all of our esoteric, elaborate inside jokes.
+Discord bot/companion for the group chatte, powered by the GPT-~~J~~ Neo language model and modified with a soft prompt to understand all of our esoteric, elaborate inside jokes.
+
+## Setup
+
+Python 3.8+ and PyTorch required. CUDA strongly recommended.
+
+The `c1-1.3B` model used in development should work without needing beefy hardware. It has been tested on a 1050 Ti 4 GB.
+
+Set up a virtual environment:
+
+Linux/MacOS
+
+```shell
+python3 -m venv venv
+source venv/bin/activate
+```
+
+Windows
+
+```shell
+py -3 -m venv venv
+.\venv\Scripts\activate
+```
+
+Install required packages
+
+```shell
+pip install -r requirements.txt
+```
+
+Copy `.env.example` to `.env` and fill in the bot's `TOKEN`.
+
+For chat scraping, you will also need to get your own `USER_TOKEN`.
+
+* In Discord, hit Ctrl+Shift+I to open up developer tools
+* Go to the Network tab and filter by XHR requests
+* Open a new channel, or scroll up, or do something else that will trigger an authenticated request
+* Click on one that looks suitable (e.g. `messages?limit=50`)
+* Under the "Request" tab, copy the contents of the `Authorization` request header.
+
+## Usage
+
+Scrape the messages from the chat channel you wish to use for a soft prompt. You will be prompted for the channel ID, which you can get by having developer mode on in Discord and right-clicking, or copying the last part of the URL in the browser.
+
+```shell
+cd src
+python -m scraper
+```
+
+Train the soft prompt (TODO)
+
+Run the Hatsune Miku bot. The first time you do this, it will download the model, which is ~5 GB.
+
+```shell
+python -m miku
+```
+
+## Final Remarks
+
+sukima nuts
diff --git a/requirements.txt b/requirements.txt
index 92700e5434ee7f66658048ec41b55f85a6cc6882..7679e18076cda8d0fc3a4610dcb7ed3e4d00e184 100644
GIT binary patch
delta 200
zcmeyzIfHY8)<hkxi4igr%hV>$lbg8DM3RdknIVTE6G&z=*aD#igC2tc5F1bCXH=YQ
z#Hcbkf>B{|6{DUo7f@9SLmopSSe-Fg&3;DN$@dtyO`gW2G<g@3%;XzP3X^{U*>cP}
zlYN*aCZ{p0OzvS;n!JHoO`MCN7-&KTShpciw;_WW$gasBnbm==C}AiBnw|@mH35p7
bF&Keuh-cBB+{0ot`2dT;<VP$LOk4~Ay_GMd

delta 347
zcmbQi`Hypg79;OOO>KEz1}=s~h7uqwVkl;?1wtbRLk2w{smEZzz&kNt9jI=qJdoII
zDhpDa%#g#72_&<@iY>s(^caj8cqcP5Dl+m;R%BEKlCEHODx<zQNKYn13PT>y8j$hE
zKph~}%Nb>X>JBq*2a=Uc%0O~96G&t`6Udb7V3D6py3!#10SuK4kqnLuz6?HKGt3~4
zn{3MrvMZ4pq`R3}9jvw(Xj=tX704Tg3^26^nbqAvW|c7H1HGEekb$Je0IX6QC|U~C
sVF+>`SY;v5-ML_OCO{Qt;6MTUltmk8qc)2%kc?#kxwn=@k_Ds(0H9nso&W#<

diff --git a/src/scraper/scraper.py b/src/scraper/scraper.py
index 26251f6..b396a9e 100644
--- a/src/scraper/scraper.py
+++ b/src/scraper/scraper.py
@@ -113,7 +113,7 @@ def boot(token: str):
     if not token:
         token = input('Enter your Discord user token (Authorization request header): ')
     channel = input('Enter channel ID: ')
-    default_export = Path.cwd().parent / 'chats'
+    default_export = Path.cwd().parent.parent / 'chats'
     export = input('Enter path to export transcripts (default "chats"): ')
     scraper = Scraper(token, channel, Path(export) if export else default_export)
     scraper.scrape()