thamognya
/
internet_ml
1
1
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

update: look at todo

main
Thamognya Kodi 2023-01-12 17:41:31 +07:00
parent afc6a95177
commit 581ec23b2a
5 changed files with 158 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
internet_ml/NLP/no_context/QA.py
View File

@ -66,19 +66,18 @@ def answer(
conversation_id=CHATGPT_CONVERSATION_ID,
parent_id=CHATGPT_PARENT_ID,
)
prompt = f"Utilize the following context: {' '.join(filter(lambda x: isinstance(x, str), results[0]))[:10000]} and answer the question only with the given context: {query}"
prompt = f"Utilize the following context: {' '.join(filter(lambda x: isinstance(x, str), results[0]))[:4000]} and answer the question only with the given context: {query}"
response = chatbot.ask(
prompt=prompt,
conversation_id=CHATGPT_CONVERSATION_ID,
parent_id=CHATGPT_PARENT_ID,
)
print(response)
return (response["message"], results[1])
else:
if model == "openai-text-davinci-003":
results: tuple[list[str], list[str]] = internet.Google(
query, GOOGLE_SEARCH_API_KEY, GOOGLE_SEARCH_ENGINE_ID
).google(filter_irrelevant=True)
).google(filter_irrelevant=False)
context = " ".join(results[0])
context[: (4097 - len(query) - 10)]
response = openai.Completion.create(
@ -102,5 +101,10 @@ def answer(
# print(os.environ)
print(answer(query="What is the latest Pokemon Game in 2022?", model="openai-chatgpt"))
print(
answer(
query="What is Club is Crisitano Ronaldo in 2023?",
model="openai-text-davinci-003",
)
)
# def custom_answer

35
internet_ml/tools/NLP/data/adremover.py 100644
View File

@ -0,0 +1,35 @@
from typing import List
from concurrent.futures import ThreadPoolExecutor, as_completed
import requests
class AdRemover:
def __init__(self, rules: list[str]):
self.rules = set()
with ThreadPoolExecutor(max_workers=500) as executor:
future_to_rule = {
executor.submit(requests.get, rule): rule for rule in rules
}
for future in as_completed(future_to_rule):
rule = future_to_rule[future]
try:
response = future.result()
self.rules.update(response.text.splitlines())
except Exception as e:
print(f"{rule} generated an exception: {e}")
def remove_ads(self, html: str) -> str:
"""Remove ads from the HTML based on the ad block rules"""
with ThreadPoolExecutor(max_workers=500) as executor:
future_to_rule = {
executor.submit(html.replace, rule, ""): rule for rule in self.rules
}
for future in as_completed(future_to_rule):
rule = future_to_rule[future]
try:
html = future.result()
except Exception as e:
print(f"{rule} generated an exception: {e}")
return html

7
internet_ml/tools/NLP/data/internet.py
View File

@ -24,6 +24,7 @@ import re
import aiohttp
import config
from adremover import AdRemover
from bs4 import BeautifulSoup
from keywords import get_keywords
from normalize import normalizer
@ -59,6 +60,11 @@ class Google:
)
)
self.__content: list[str] = []
ADBLOCK_RULES = [
"https://easylist-downloads.adblockplus.org/ruadlist+easylist.txt",
"https://filters.adtidy.org/extension/chromium/filters/1.txt",
]
self.__ad_remover = AdRemover(ADBLOCK_RULES)
def __get_urls(self: "Google") -> None:
# Send the request to the Google Search API
@ -84,6 +90,7 @@ class Google:
try:
async with session.get(url, headers=HTTP_USERAGENT) as response:
html = await response.text()
html = self.__ad_remover.remove_ads(html)
soup = BeautifulSoup(html, "html.parser")
text = soup.get_text()
normalized_text = normalizer(text)

107
poetry.lock generated
View File

@ -628,6 +628,18 @@ files = [
[package.dependencies]
coverage = "*"
[[package]]
name = "cssselect"
version = "1.2.0"
description = "cssselect parses CSS3 Selectors and translates them to XPath 1.0"
category = "main"
optional = false
python-versions = ">=3.7"
files = [
{file = "cssselect-1.2.0-py2.py3-none-any.whl", hash = "sha256:da1885f0c10b60c03ed5eccbb6b68d6eff248d91976fcde348f395d54c9fd35e"},
{file = "cssselect-1.2.0.tar.gz", hash = "sha256:666b19839cfaddb9ce9d36bfe4c969132c647b92fc9088c4e23f786b30f1b3dc"},
]
[[package]]
name = "cymem"
version = "2.0.7"
@ -1214,6 +1226,99 @@ files = [
{file = "lazy_object_proxy-1.9.0-cp39-cp39-win_amd64.whl", hash = "sha256:db1c1722726f47e10e0b5fdbf15ac3b8adb58c091d12b3ab713965795036985f"},
]
[[package]]
name = "lxml"
version = "4.9.2"
description = "Powerful and Pythonic XML processing library combining libxml2/libxslt with the ElementTree API."
category = "main"
optional = false
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, != 3.4.*"
files = [
{file = "lxml-4.9.2-cp27-cp27m-macosx_10_15_x86_64.whl", hash = "sha256:76cf573e5a365e790396a5cc2b909812633409306c6531a6877c59061e42c4f2"},
{file = "lxml-4.9.2-cp27-cp27m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:b1f42b6921d0e81b1bcb5e395bc091a70f41c4d4e55ba99c6da2b31626c44892"},
{file = "lxml-4.9.2-cp27-cp27m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:9f102706d0ca011de571de32c3247c6476b55bb6bc65a20f682f000b07a4852a"},
{file = "lxml-4.9.2-cp27-cp27m-win32.whl", hash = "sha256:8d0b4612b66ff5d62d03bcaa043bb018f74dfea51184e53f067e6fdcba4bd8de"},
{file = "lxml-4.9.2-cp27-cp27m-win_amd64.whl", hash = "sha256:4c8f293f14abc8fd3e8e01c5bd86e6ed0b6ef71936ded5bf10fe7a5efefbaca3"},
{file = "lxml-4.9.2-cp27-cp27mu-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:2899456259589aa38bfb018c364d6ae7b53c5c22d8e27d0ec7609c2a1ff78b50"},
{file = "lxml-4.9.2-cp27-cp27mu-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:6749649eecd6a9871cae297bffa4ee76f90b4504a2a2ab528d9ebe912b101975"},
{file = "lxml-4.9.2-cp310-cp310-macosx_10_15_x86_64.whl", hash = "sha256:a08cff61517ee26cb56f1e949cca38caabe9ea9fbb4b1e10a805dc39844b7d5c"},
{file = "lxml-4.9.2-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:85cabf64adec449132e55616e7ca3e1000ab449d1d0f9d7f83146ed5bdcb6d8a"},
{file = "lxml-4.9.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_24_aarch64.whl", hash = "sha256:8340225bd5e7a701c0fa98284c849c9b9fc9238abf53a0ebd90900f25d39a4e4"},
{file = "lxml-4.9.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:1ab8f1f932e8f82355e75dda5413a57612c6ea448069d4fb2e217e9a4bed13d4"},
{file = "lxml-4.9.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:699a9af7dffaf67deeae27b2112aa06b41c370d5e7633e0ee0aea2e0b6c211f7"},
{file = "lxml-4.9.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:b9cc34af337a97d470040f99ba4282f6e6bac88407d021688a5d585e44a23184"},
{file = "lxml-4.9.2-cp310-cp310-win32.whl", hash = "sha256:d02a5399126a53492415d4906ab0ad0375a5456cc05c3fc0fc4ca11771745cda"},
{file = "lxml-4.9.2-cp310-cp310-win_amd64.whl", hash = "sha256:a38486985ca49cfa574a507e7a2215c0c780fd1778bb6290c21193b7211702ab"},
{file = "lxml-4.9.2-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:c83203addf554215463b59f6399835201999b5e48019dc17f182ed5ad87205c9"},
{file = "lxml-4.9.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_24_aarch64.whl", hash = "sha256:2a87fa548561d2f4643c99cd13131acb607ddabb70682dcf1dff5f71f781a4bf"},
{file = "lxml-4.9.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:d6b430a9938a5a5d85fc107d852262ddcd48602c120e3dbb02137c83d212b380"},
{file = "lxml-4.9.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:3efea981d956a6f7173b4659849f55081867cf897e719f57383698af6f618a92"},
{file = "lxml-4.9.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:df0623dcf9668ad0445e0558a21211d4e9a149ea8f5666917c8eeec515f0a6d1"},
{file = "lxml-4.9.2-cp311-cp311-win32.whl", hash = "sha256:da248f93f0418a9e9d94b0080d7ebc407a9a5e6d0b57bb30db9b5cc28de1ad33"},
{file = "lxml-4.9.2-cp311-cp311-win_amd64.whl", hash = "sha256:3818b8e2c4b5148567e1b09ce739006acfaa44ce3156f8cbbc11062994b8e8dd"},
{file = "lxml-4.9.2-cp35-cp35m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:ca989b91cf3a3ba28930a9fc1e9aeafc2a395448641df1f387a2d394638943b0"},
{file = "lxml-4.9.2-cp35-cp35m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:822068f85e12a6e292803e112ab876bc03ed1f03dddb80154c395f891ca6b31e"},
{file = "lxml-4.9.2-cp35-cp35m-win32.whl", hash = "sha256:be7292c55101e22f2a3d4d8913944cbea71eea90792bf914add27454a13905df"},
{file = "lxml-4.9.2-cp35-cp35m-win_amd64.whl", hash = "sha256:998c7c41910666d2976928c38ea96a70d1aa43be6fe502f21a651e17483a43c5"},
{file = "lxml-4.9.2-cp36-cp36m-macosx_10_15_x86_64.whl", hash = "sha256:b26a29f0b7fc6f0897f043ca366142d2b609dc60756ee6e4e90b5f762c6adc53"},
{file = "lxml-4.9.2-cp36-cp36m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:ab323679b8b3030000f2be63e22cdeea5b47ee0abd2d6a1dc0c8103ddaa56cd7"},
{file = "lxml-4.9.2-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:689bb688a1db722485e4610a503e3e9210dcc20c520b45ac8f7533c837be76fe"},
{file = "lxml-4.9.2-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:f49e52d174375a7def9915c9f06ec4e569d235ad428f70751765f48d5926678c"},
{file = "lxml-4.9.2-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:36c3c175d34652a35475a73762b545f4527aec044910a651d2bf50de9c3352b1"},
{file = "lxml-4.9.2-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:a35f8b7fa99f90dd2f5dc5a9fa12332642f087a7641289ca6c40d6e1a2637d8e"},
{file = "lxml-4.9.2-cp36-cp36m-musllinux_1_1_aarch64.whl", hash = "sha256:58bfa3aa19ca4c0f28c5dde0ff56c520fbac6f0daf4fac66ed4c8d2fb7f22e74"},
{file = "lxml-4.9.2-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:bc718cd47b765e790eecb74d044cc8d37d58562f6c314ee9484df26276d36a38"},
{file = "lxml-4.9.2-cp36-cp36m-win32.whl", hash = "sha256:d5bf6545cd27aaa8a13033ce56354ed9e25ab0e4ac3b5392b763d8d04b08e0c5"},
{file = "lxml-4.9.2-cp36-cp36m-win_amd64.whl", hash = "sha256:3ab9fa9d6dc2a7f29d7affdf3edebf6ece6fb28a6d80b14c3b2fb9d39b9322c3"},
{file = "lxml-4.9.2-cp37-cp37m-macosx_10_15_x86_64.whl", hash = "sha256:05ca3f6abf5cf78fe053da9b1166e062ade3fa5d4f92b4ed688127ea7d7b1d03"},
{file = "lxml-4.9.2-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:a5da296eb617d18e497bcf0a5c528f5d3b18dadb3619fbdadf4ed2356ef8d941"},
{file = "lxml-4.9.2-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_24_aarch64.whl", hash = "sha256:04876580c050a8c5341d706dd464ff04fd597095cc8c023252566a8826505726"},
{file = "lxml-4.9.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:c9ec3eaf616d67db0764b3bb983962b4f385a1f08304fd30c7283954e6a7869b"},
{file = "lxml-4.9.2-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:2a29ba94d065945944016b6b74e538bdb1751a1db6ffb80c9d3c2e40d6fa9894"},
{file = "lxml-4.9.2-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:a82d05da00a58b8e4c0008edbc8a4b6ec5a4bc1e2ee0fb6ed157cf634ed7fa45"},
{file = "lxml-4.9.2-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:223f4232855ade399bd409331e6ca70fb5578efef22cf4069a6090acc0f53c0e"},
{file = "lxml-4.9.2-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:d17bc7c2ccf49c478c5bdd447594e82692c74222698cfc9b5daae7ae7e90743b"},
{file = "lxml-4.9.2-cp37-cp37m-win32.whl", hash = "sha256:b64d891da92e232c36976c80ed7ebb383e3f148489796d8d31a5b6a677825efe"},
{file = "lxml-4.9.2-cp37-cp37m-win_amd64.whl", hash = "sha256:a0a336d6d3e8b234a3aae3c674873d8f0e720b76bc1d9416866c41cd9500ffb9"},
{file = "lxml-4.9.2-cp38-cp38-macosx_10_15_x86_64.whl", hash = "sha256:da4dd7c9c50c059aba52b3524f84d7de956f7fef88f0bafcf4ad7dde94a064e8"},
{file = "lxml-4.9.2-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:821b7f59b99551c69c85a6039c65b75f5683bdc63270fec660f75da67469ca24"},
{file = "lxml-4.9.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_24_aarch64.whl", hash = "sha256:e5168986b90a8d1f2f9dc1b841467c74221bd752537b99761a93d2d981e04889"},
{file = "lxml-4.9.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:8e20cb5a47247e383cf4ff523205060991021233ebd6f924bca927fcf25cf86f"},
{file = "lxml-4.9.2-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:13598ecfbd2e86ea7ae45ec28a2a54fb87ee9b9fdb0f6d343297d8e548392c03"},
{file = "lxml-4.9.2-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:880bbbcbe2fca64e2f4d8e04db47bcdf504936fa2b33933efd945e1b429bea8c"},
{file = "lxml-4.9.2-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:7d2278d59425777cfcb19735018d897ca8303abe67cc735f9f97177ceff8027f"},
{file = "lxml-4.9.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:5344a43228767f53a9df6e5b253f8cdca7dfc7b7aeae52551958192f56d98457"},
{file = "lxml-4.9.2-cp38-cp38-win32.whl", hash = "sha256:925073b2fe14ab9b87e73f9a5fde6ce6392da430f3004d8b72cc86f746f5163b"},
{file = "lxml-4.9.2-cp38-cp38-win_amd64.whl", hash = "sha256:9b22c5c66f67ae00c0199f6055705bc3eb3fcb08d03d2ec4059a2b1b25ed48d7"},
{file = "lxml-4.9.2-cp39-cp39-macosx_10_15_x86_64.whl", hash = "sha256:5f50a1c177e2fa3ee0667a5ab79fdc6b23086bc8b589d90b93b4bd17eb0e64d1"},
{file = "lxml-4.9.2-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:090c6543d3696cbe15b4ac6e175e576bcc3f1ccfbba970061b7300b0c15a2140"},
{file = "lxml-4.9.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_24_aarch64.whl", hash = "sha256:63da2ccc0857c311d764e7d3d90f429c252e83b52d1f8f1d1fe55be26827d1f4"},
{file = "lxml-4.9.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:5b4545b8a40478183ac06c073e81a5ce4cf01bf1734962577cf2bb569a5b3bbf"},
{file = "lxml-4.9.2-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:2e430cd2824f05f2d4f687701144556646bae8f249fd60aa1e4c768ba7018947"},
{file = "lxml-4.9.2-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:6804daeb7ef69e7b36f76caddb85cccd63d0c56dedb47555d2fc969e2af6a1a5"},
{file = "lxml-4.9.2-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:a6e441a86553c310258aca15d1c05903aaf4965b23f3bc2d55f200804e005ee5"},
{file = "lxml-4.9.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:ca34efc80a29351897e18888c71c6aca4a359247c87e0b1c7ada14f0ab0c0fb2"},
{file = "lxml-4.9.2-cp39-cp39-win32.whl", hash = "sha256:6b418afe5df18233fc6b6093deb82a32895b6bb0b1155c2cdb05203f583053f1"},
{file = "lxml-4.9.2-cp39-cp39-win_amd64.whl", hash = "sha256:f1496ea22ca2c830cbcbd473de8f114a320da308438ae65abad6bab7867fe38f"},
{file = "lxml-4.9.2-pp37-pypy37_pp73-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:b264171e3143d842ded311b7dccd46ff9ef34247129ff5bf5066123c55c2431c"},
{file = "lxml-4.9.2-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:0dc313ef231edf866912e9d8f5a042ddab56c752619e92dfd3a2c277e6a7299a"},
{file = "lxml-4.9.2-pp38-pypy38_pp73-macosx_10_15_x86_64.whl", hash = "sha256:16efd54337136e8cd72fb9485c368d91d77a47ee2d42b057564aae201257d419"},
{file = "lxml-4.9.2-pp38-pypy38_pp73-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:0f2b1e0d79180f344ff9f321327b005ca043a50ece8713de61d1cb383fb8ac05"},
{file = "lxml-4.9.2-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:7b770ed79542ed52c519119473898198761d78beb24b107acf3ad65deae61f1f"},
{file = "lxml-4.9.2-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:efa29c2fe6b4fdd32e8ef81c1528506895eca86e1d8c4657fda04c9b3786ddf9"},
{file = "lxml-4.9.2-pp39-pypy39_pp73-macosx_10_15_x86_64.whl", hash = "sha256:7e91ee82f4199af8c43d8158024cbdff3d931df350252288f0d4ce656df7f3b5"},
{file = "lxml-4.9.2-pp39-pypy39_pp73-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:b23e19989c355ca854276178a0463951a653309fb8e57ce674497f2d9f208746"},
{file = "lxml-4.9.2-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:01d36c05f4afb8f7c20fd9ed5badca32a2029b93b1750f571ccc0b142531caf7"},
{file = "lxml-4.9.2-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:7b515674acfdcadb0eb5d00d8a709868173acece5cb0be3dd165950cbfdf5409"},
{file = "lxml-4.9.2.tar.gz", hash = "sha256:2455cfaeb7ac70338b3257f41e21f0724f4b5b0c0e7702da67ee6c3640835b67"},
]
[package.extras]
cssselect = ["cssselect (>=0.7)"]
html5 = ["html5lib"]
htmlsoup = ["BeautifulSoup4"]
source = ["Cython (>=0.29.7)"]
[[package]]
name = "markdown"
version = "3.3.7"
@ -4140,4 +4245,4 @@ testing = ["flake8 (<5)", "func-timeout", "jaraco.functools", "jaraco.itertools"
[metadata]
lock-version = "2.0"
python-versions = "^3.10"
content-hash = "8bf46a1e925db8ce484fdc929f72dd07d3f9c49359c26c1efe646d96f8ff9482"
content-hash = "1df84c766da2dc5f82a0b58b6e7749131d09312bf750fff149bcb519f393af9e"

2
pyproject.toml
View File

@ -56,6 +56,8 @@ diffusers = "^0.11.1"
openai = "^0.26.0"
huggingface-hub = "^0.11.1"
revchatgpt = "^0.1.1"
cssselect = "^1.2.0"
lxml = "^4.9.2"
[tool.poetry.group.dev.dependencies]
bandit = "^1.7.4"