Skip to content

GitLab

"lib/runtime/deny.toml" did not exist on "d39695b734398d1f0980c53bcadc16bd97ae6558"
Unverified Commit 641b1ee7 authored by Hongxin Liu's avatar Hongxin Liu Committed by GitHub
Browse files

[devops] remove post commit ci (#5566) 

* [devops] remove post commit ci

* [misc] run pre-commit on all files

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci



---------
Co-authored-by: default avatarpre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
parent 341263df
Expand all Hide whitespace changes
Inline Side-by-side
Showing with 295 additions and 355 deletions
applications/ColossalQA/colossalqa/data_loader/table_dataloader.py
View file @ 641b1ee7
''' """
Class for loading table type data. please refer to Pandas-Input/Output for file format details. Class for loading table type data. please refer to Pandas-Input/Output for file format details.
''' """
import os
import glob import glob
import os
import pandas as pd import pandas as pd
from sqlalchemy import create_engine
from colossalqa.utils import drop_table
from colossalqa.mylogging import get_logger from colossalqa.mylogging import get_logger
from colossalqa.utils import drop_table
from sqlalchemy import create_engine
logger = get_logger() logger = get_logger()
SUPPORTED_DATA_FORMAT = ['.csv','.xlsx', '.xls','.json','.html','.h5', '.hdf5','.parquet','.feather','.dta'] SUPPORTED_DATA_FORMAT = [".csv", ".xlsx", ".xls", ".json", ".html", ".h5", ".hdf5", ".parquet", ".feather", ".dta"]
class TableLoader: class TableLoader:
''' """
Load tables from different files and serve a sql database for database operations Load tables from different files and serve a sql database for database operations
''' """
def __init__(self, files: str,
sql_path:str='sqlite:///mydatabase.db', def __init__(self, files: str, sql_path: str = "sqlite:///mydatabase.db", verbose=False, **kwargs) -> None:
verbose=False, **kwargs) -> None: """
'''
Args: Args:
files: list of files (list[file path, name]) files: list of files (list[file path, name])
sql_path: how to serve the sql database sql_path: how to serve the sql database
**kwargs: keyword type arguments, useful for certain document types **kwargs: keyword type arguments, useful for certain document types
''' """
self.data = {} self.data = {}
self.verbose = verbose self.verbose = verbose
self.sql_path = sql_path self.sql_path = sql_path
self.kwargs = kwargs self.kwargs = kwargs
self.sql_engine = create_engine(self.sql_path) self.sql_engine = create_engine(self.sql_path)
drop_table(self.sql_engine) drop_table(self.sql_engine)
self.sql_engine = create_engine(self.sql_path) self.sql_engine = create_engine(self.sql_path)
for item in files: for item in files:
path = item[0] path = item[0]
...@@ -42,68 +43,68 @@ class TableLoader: ...@@ -42,68 +43,68 @@ class TableLoader:
raise FileNotFoundError(f"{path} doesn't exists") raise FileNotFoundError(f"{path} doesn't exists")
if not any([path.endswith(i) for i in SUPPORTED_DATA_FORMAT]): if not any([path.endswith(i) for i in SUPPORTED_DATA_FORMAT]):
raise TypeError(f"{path} not supported. Supported type {SUPPORTED_DATA_FORMAT}") raise TypeError(f"{path} not supported. Supported type {SUPPORTED_DATA_FORMAT}")
logger.info("loading data", verbose=self.verbose) logger.info("loading data", verbose=self.verbose)
self.load_data(path) self.load_data(path)
logger.info("data loaded", verbose=self.verbose) logger.info("data loaded", verbose=self.verbose)
self.to_sql(path, dataset_name) self.to_sql(path, dataset_name)
def load_data(self, path): def load_data(self, path):
''' """
Load data and serve the data as sql database. Load data and serve the data as sql database.
Data must be in pandas format Data must be in pandas format
''' """
files = [] files = []
# Handle glob expression # Handle glob expression
try: try:
files = glob.glob(path) files = glob.glob(path)
except Exception as e: except Exception as e:
logger.error(e) logger.error(e)
if len(files)==0: if len(files) == 0:
raise ValueError("Unsupported file/directory format. For directories, please use glob expression") raise ValueError("Unsupported file/directory format. For directories, please use glob expression")
elif len(files)==1: elif len(files) == 1:
path = files[0] path = files[0]
else: else:
for file in files: for file in files:
self.load_data(file) self.load_data(file)
if path.endswith('.csv'): if path.endswith(".csv"):
# Load csv # Load csv
self.data[path] = pd.read_csv(path) self.data[path] = pd.read_csv(path)
elif path.endswith('.xlsx') or path.endswith('.xls'): elif path.endswith(".xlsx") or path.endswith(".xls"):
# Load excel # Load excel
self.data[path] = pd.read_excel(path) # You can adjust the sheet_name as needed self.data[path] = pd.read_excel(path) # You can adjust the sheet_name as needed
elif path.endswith('.json'): elif path.endswith(".json"):
# Load json # Load json
self.data[path] = pd.read_json(path) self.data[path] = pd.read_json(path)
elif path.endswith('.html'): elif path.endswith(".html"):
# Load html # Load html
html_tables = pd.read_html(path) html_tables = pd.read_html(path)
# Choose the desired table from the list of DataFrame objects # Choose the desired table from the list of DataFrame objects
self.data[path] = html_tables[0] # You may need to adjust this index self.data[path] = html_tables[0] # You may need to adjust this index
elif path.endswith('.h5') or path.endswith('.hdf5'): elif path.endswith(".h5") or path.endswith(".hdf5"):
# Load h5 # Load h5
self.data[path] = pd.read_hdf(path, key=self.kwargs.get('key', 'data')) # You can adjust the key as needed self.data[path] = pd.read_hdf(path, key=self.kwargs.get("key", "data")) # You can adjust the key as needed
elif path.endswith('.parquet'): elif path.endswith(".parquet"):
# Load parquet # Load parquet
self.data[path] = pd.read_parquet(path, engine='fastparquet') self.data[path] = pd.read_parquet(path, engine="fastparquet")
elif path.endswith('.feather'): elif path.endswith(".feather"):
# Load feather # Load feather
self.data[path] = pd.read_feather(path) self.data[path] = pd.read_feather(path)
elif path.endswith('.dta'): elif path.endswith(".dta"):
# Load dta # Load dta
self.data[path] = pd.read_stata(path) self.data[path] = pd.read_stata(path)
else: else:
raise ValueError("Unsupported file format") raise ValueError("Unsupported file format")
def to_sql(self, path, table_name): def to_sql(self, path, table_name):
''' """
Serve the data as sql database. Serve the data as sql database.
''' """
self.data[path].to_sql(table_name, con=self.sql_engine, if_exists='replace', index=False) self.data[path].to_sql(table_name, con=self.sql_engine, if_exists="replace", index=False)
logger.info(f"Loaded to Sqlite3\nPath: {path}", verbose=self.verbose) logger.info(f"Loaded to Sqlite3\nPath: {path}", verbose=self.verbose)
return self.sql_path return self.sql_path
def get_sql_path(self): def get_sql_path(self):
return self.sql_path return self.sql_path
...@@ -113,7 +114,3 @@ class TableLoader: ...@@ -113,7 +114,3 @@ class TableLoader:
self.sql_engine.dispose() self.sql_engine.dispose()
del self.data del self.data
del self.sql_engine del self.sql_engine
applications/ColossalQA/colossalqa/local/colossalcloud_llm.py
View file @ 641b1ee7
...@@ -21,7 +21,7 @@ print(resp) # super-heavyweight awesome-natured yawning Australian creature! ...@@ -21,7 +21,7 @@ print(resp) # super-heavyweight awesome-natured yawning Australian creature!
""" """
import json import json
from typing import Any, List, Mapping, Optional from typing import Any, Mapping
import requests import requests
from langchain.llms.base import LLM from langchain.llms.base import LLM
...@@ -31,31 +31,31 @@ from langchain.utils import get_from_dict_or_env ...@@ -31,31 +31,31 @@ from langchain.utils import get_from_dict_or_env
class ColossalCloudLLM(LLM): class ColossalCloudLLM(LLM):
""" """
A custom LLM class that integrates LLMs running on the ColossalCloud Platform A custom LLM class that integrates LLMs running on the ColossalCloud Platform
""" """
n: int
gen_config: dict = None n: int
gen_config: dict = None
auth_config: dict = None auth_config: dict = None
valid_gen_para: list = ['max_new_tokens', 'top_k', valid_gen_para: list = ["max_new_tokens", "top_k", "top_p", "temperature", "repetition_penalty"]
'top_p', 'temperature', 'repetition_penalty']
def __init__(self, gen_config=None, **kwargs): def __init__(self, gen_config=None, **kwargs):
""" """
Args: Args:
gen_config: config for generation, gen_config: config for generation,
max_new_tokens: 50 by default max_new_tokens: 50 by default
top_k: (1, vocab_size) top_k: (1, vocab_size)
top_p: (0, 1) if not None top_p: (0, 1) if not None
temperature: (0, inf) if not None temperature: (0, inf) if not None
repetition_penalty: (1, inf) if not None repetition_penalty: (1, inf) if not None
""" """
super(ColossalCloudLLM, self).__init__(**kwargs) super(ColossalCloudLLM, self).__init__(**kwargs)
if gen_config is None: if gen_config is None:
self.gen_config = {"max_new_tokens": 50} self.gen_config = {"max_new_tokens": 50}
else: else:
assert "max_new_tokens" in gen_config, "max_new_tokens is a compulsory key in the gen config" assert "max_new_tokens" in gen_config, "max_new_tokens is a compulsory key in the gen config"
self.gen_config = gen_config self.gen_config = gen_config
@property @property
def _identifying_params(self) -> Mapping[str, Any]: def _identifying_params(self) -> Mapping[str, Any]:
"""Get the identifying parameters.""" """Get the identifying parameters."""
...@@ -63,17 +63,17 @@ class ColossalCloudLLM(LLM): ...@@ -63,17 +63,17 @@ class ColossalCloudLLM(LLM):
@property @property
def _llm_type(self) -> str: def _llm_type(self) -> str:
return 'ColossalCloudLLM' return "ColossalCloudLLM"
def set_auth_config(self, **kwargs): def set_auth_config(self, **kwargs):
url = get_from_dict_or_env(kwargs, "url", "URL") url = get_from_dict_or_env(kwargs, "url", "URL")
host = get_from_dict_or_env(kwargs, "host", "HOST") host = get_from_dict_or_env(kwargs, "host", "HOST")
auth_config = {} auth_config = {}
auth_config['endpoint'] = url auth_config["endpoint"] = url
auth_config['Host'] = host auth_config["Host"] = host
self.auth_config = auth_config self.auth_config = auth_config
def _call(self, prompt: str, stop=None, **kwargs: Any) -> str: def _call(self, prompt: str, stop=None, **kwargs: Any) -> str:
""" """
Args: Args:
...@@ -81,15 +81,17 @@ class ColossalCloudLLM(LLM): ...@@ -81,15 +81,17 @@ class ColossalCloudLLM(LLM):
stop: A list of strings to stop generation when encountered stop: A list of strings to stop generation when encountered
Returns: Returns:
The string generated by the model The string generated by the model
""" """
# Update the generation arguments # Update the generation arguments
for key, value in kwargs.items(): for key, value in kwargs.items():
if key not in self.valid_gen_para: if key not in self.valid_gen_para:
raise KeyError(f"Invalid generation parameter: '{key}'. Valid keys are: {', '.join(self.valid_gen_para)}") raise KeyError(
f"Invalid generation parameter: '{key}'. Valid keys are: {', '.join(self.valid_gen_para)}"
)
if key in self.gen_config: if key in self.gen_config:
self.gen_config[key] = value self.gen_config[key] = value
resp_text = self.text_completion(prompt, self.gen_config, self.auth_config) resp_text = self.text_completion(prompt, self.gen_config, self.auth_config)
# TODO: This may cause excessive tokens count # TODO: This may cause excessive tokens count
if stop is not None: if stop is not None:
...@@ -97,29 +99,19 @@ class ColossalCloudLLM(LLM): ...@@ -97,29 +99,19 @@ class ColossalCloudLLM(LLM):
if stopping_words in resp_text: if stopping_words in resp_text:
resp_text = resp_text.split(stopping_words)[0] resp_text = resp_text.split(stopping_words)[0]
return resp_text return resp_text
def text_completion(self, prompt, gen_config, auth_config): def text_completion(self, prompt, gen_config, auth_config):
# Required Parameters # Required Parameters
endpoint = auth_config.pop('endpoint') endpoint = auth_config.pop("endpoint")
max_new_tokens = gen_config.pop('max_new_tokens') max_new_tokens = gen_config.pop("max_new_tokens")
# Optional Parameters # Optional Parameters
optional_params = ['top_k', 'top_p', 'temperature', 'repetition_penalty'] # Self.optional optional_params = ["top_k", "top_p", "temperature", "repetition_penalty"] # Self.optional
gen_config = {key: gen_config[key] for key in optional_params if key in gen_config} gen_config = {key: gen_config[key] for key in optional_params if key in gen_config}
# Define the data payload # Define the data payload
data = { data = {"max_new_tokens": max_new_tokens, "history": [{"instruction": prompt, "response": ""}], **gen_config}
"max_new_tokens": max_new_tokens, headers = {"Content-Type": "application/json", **auth_config} # 'Host',
"history": [
{"instruction": prompt, "response": ""}
],
**gen_config
}
headers = {
"Content-Type": "application/json",
**auth_config # 'Host',
}
# Make the POST request # Make the POST request
response = requests.post(endpoint, headers=headers, data=json.dumps(data)) response = requests.post(endpoint, headers=headers, data=json.dumps(data))
response.raise_for_status() # raise error if return code is not 200(success) response.raise_for_status() # raise error if return code is not 200(success)
# Check the response # Check the response
return response.text return response.text
applications/ColossalQA/colossalqa/local/llm.py
View file @ 641b1ee7
...@@ -193,4 +193,3 @@ class VllmLLM(LLM): ...@@ -193,4 +193,3 @@ class VllmLLM(LLM):
def _identifying_params(self) -> Mapping[str, int]: def _identifying_params(self) -> Mapping[str, int]:
"""Get the identifying parameters.""" """Get the identifying parameters."""
return {"n": self.n} return {"n": self.n}
applications/ColossalQA/colossalqa/prompt/prompt.py
View file @ 641b1ee7
...@@ -4,7 +4,6 @@ All custom prompt templates are defined here. ...@@ -4,7 +4,6 @@ All custom prompt templates are defined here.
from langchain.prompts.prompt import PromptTemplate from langchain.prompts.prompt import PromptTemplate
# Below are Chinese retrieval qa prompts # Below are Chinese retrieval qa prompts
_CUSTOM_SUMMARIZER_TEMPLATE_ZH = """请递进式地总结所提供的当前对话，将当前对话的摘要内容添加到先前已有的摘要上，返回一个融合了当前对话的新的摘要。 _CUSTOM_SUMMARIZER_TEMPLATE_ZH = """请递进式地总结所提供的当前对话，将当前对话的摘要内容添加到先前已有的摘要上，返回一个融合了当前对话的新的摘要。
......
applications/ColossalQA/colossalqa/retriever.py
View file @ 641b1ee7
...@@ -99,13 +99,7 @@ class CustomRetriever(BaseRetriever): ...@@ -99,13 +99,7 @@ class CustomRetriever(BaseRetriever):
def clear_documents(self): def clear_documents(self):
"""Clear all document vectors from database""" """Clear all document vectors from database"""
for source in self.vector_stores: for source in self.vector_stores:
index( index([], self.record_managers[source], self.vector_stores[source], cleanup="full", source_id_key="source")
[],
self.record_managers[source],
self.vector_stores[source],
cleanup="full",
source_id_key="source"
)
self.vector_stores = {} self.vector_stores = {}
self.sql_index_database = {} self.sql_index_database = {}
self.record_managers = {} self.record_managers = {}
......
applications/ColossalQA/data/data_sample/companies.txt
View file @ 641b1ee7
Overview The Straits Times is the English flagship daily of SPH Media, one of the leading media companies in Asia. Launched on July 15, 1845, its comprehensive coverage of news from home and around the world makes The Straits Times the most-read newspaper in Singapore. Quality news, in-depth analyses, impactful commentaries and breaking stories are packaged to give readers riveting accounts of events in Singapore, the region, and beyond. The most read newspaper in Singapore, both in terms of print and digital, it reaches 1.33 million people every day. The Straits Times'​ key strength is in its world class coverage of news outside Singapore. With 20 bureaus in major cities around the world, The Straits Times correspondents bring world news to readers on a Singapore platter, helping readers to appreciate world events from a Singaporean perspective. Website http://www.straitstimes.com Phone 63196319Phone number is 63196319 Industry Newspaper Publishing Company size 1,001-5,000 employees 183 on LinkedIn Includes members with current employer listed as The Straits Times, including part-time roles. Headquarters Singapore, Singapore Founded 1845 Specialties News and Digital media Overview The Straits Times is the English flagship daily of SPH Media, one of the leading media companies in Asia. Launched on July 15, 1845, its comprehensive coverage of news from home and around the world makes The Straits Times the most-read newspaper in Singapore. Quality news, in-depth analyses, impactful commentaries and breaking stories are packaged to give readers riveting accounts of events in Singapore, the region, and beyond. The most read newspaper in Singapore, both in terms of print and digital, it reaches 1.33 million people every day. The Straits Times'​ key strength is in its world class coverage of news outside Singapore. With 20 bureaus in major cities around the world, The Straits Times correspondents bring world news to readers on a Singapore platter, helping readers to appreciate world events from a Singaporean perspective. Website http://www.straitstimes.com Phone 63196319Phone number is 63196319 Industry Newspaper Publishing Company size 1,001-5,000 employees 183 on LinkedIn Includes members with current employer listed as The Straits Times, including part-time roles. Headquarters Singapore, Singapore Founded 1845 Specialties News and Digital media
About With over 500 properties worldwide, Marriott Hotels has reimagined hospitality to exceed the expectations of business, group, and leisure travelers. About With over 500 properties worldwide, Marriott Hotels has reimagined hospitality to exceed the expectations of business, group, and leisure travelers.
Marriott Hotels, Marriott’s flagship brand of quality-tier, full-service hotels and resorts, provides consistent, dependable and genuinely caring experiences to guests on their terms. Marriott is a brilliant host to guests who effortlessly blend life and work, and who are inspired by how modern travel enhances them both. Our hotels offer warm, professional service; sophisticated yet functional guest room design; lobby spaces that facilitate working, dining and socializing; restaurants and bars serving international cuisine prepared simply and from the freshest ingredients; meeting and event spaces and services that are gold standard; and expansive, 24-hour fitness facilities. Marriott Hotels, Marriott’s flagship brand of quality-tier, full-service hotels and resorts, provides consistent, dependable and genuinely caring experiences to guests on their terms. Marriott is a brilliant host to guests who effortlessly blend life and work, and who are inspired by how modern travel enhances them both. Our hotels offer warm, professional service; sophisticated yet functional guest room design; lobby spaces that facilitate working, dining and socializing; restaurants and bars serving international cuisine prepared simply and from the freshest ingredients; meeting and event spaces and services that are gold standard; and expansive, 24-hour fitness facilities.
Overview AERCO International, Inc. is a recognized leader in delivering cost-effective, condensing commercial boilers, high-efficiency water heaters across a variety of markets including education, lodging, government, office buildings, healthcare, industrial and multifamily housing. AERCO's system design approach provides customer-specific solutions that deliver superior building performance at a lower operating cost while assuring uptime reliability. When AERCO was founded in 1949, it introduced a revolutionary design for an indirect-fired water heater that heated water on demand, and without storage, at a controlled temperature. This innovation became today's standard for water heaters, maximizing the recovery of latent heat energy and significantly increasing operating efficiency. AERCO continued to innovate and in 1988, introduced the first condensing and fully modulating boiler and water heater to the commercial market. The modulating capability of these products, still unsurpassed more than 25 years later, matches the equipment's output to real-time heating demand, ensuring the units draw no more fuel to operate than is absolutely necessary. This not only saves precious energy, but also ensures money doesn't needlessly disappear "up the stack."​ AERCO differentiates itself through a solution-based model, leveraging decades of engineering experience and industry application expertise to understand each customer’s unique needs. By partnering directly with customers and end-users to understand their project-specific requirements, AERCO provides tailored application solutions that are comprised of original product technologies including high efficiency condensing products, compact footprints, high turndown ratios, unique fuel delivery, leading control systems and proprietary design elements that combine to deliver up to 99% efficiency. Website http://www.aerco.com Phone 845-580-8000Phone number is 845-580-8000 Industry Industrial Machinery Manufacturing Company size 51-200 employees 119 on LinkedIn Includes members with current employer listed as AERCO International, Inc., including part-time roles. Headquarters Blauvelt, NY Founded 1949 Specialties Leading manufacturer of condensing boilers, water heating and energy recovery products and The originator of semi-instantaneous water heating Overview AERCO International, Inc. is a recognized leader in delivering cost-effective, condensing commercial boilers, high-efficiency water heaters across a variety of markets including education, lodging, government, office buildings, healthcare, industrial and multifamily housing. AERCO's system design approach provides customer-specific solutions that deliver superior building performance at a lower operating cost while assuring uptime reliability. When AERCO was founded in 1949, it introduced a revolutionary design for an indirect-fired water heater that heated water on demand, and without storage, at a controlled temperature. This innovation became today's standard for water heaters, maximizing the recovery of latent heat energy and significantly increasing operating efficiency. AERCO continued to innovate and in 1988, introduced the first condensing and fully modulating boiler and water heater to the commercial market. The modulating capability of these products, still unsurpassed more than 25 years later, matches the equipment's output to real-time heating demand, ensuring the units draw no more fuel to operate than is absolutely necessary. This not only saves precious energy, but also ensures money doesn't needlessly disappear "up the stack."​ AERCO differentiates itself through a solution-based model, leveraging decades of engineering experience and industry application expertise to understand each customer’s unique needs. By partnering directly with customers and end-users to understand their project-specific requirements, AERCO provides tailored application solutions that are comprised of original product technologies including high efficiency condensing products, compact footprints, high turndown ratios, unique fuel delivery, leading control systems and proprietary design elements that combine to deliver up to 99% efficiency. Website http://www.aerco.com Phone 845-580-8000Phone number is 845-580-8000 Industry Industrial Machinery Manufacturing Company size 51-200 employees 119 on LinkedIn Includes members with current employer listed as AERCO International, Inc., including part-time roles. Headquarters Blauvelt, NY Founded 1949 Specialties Leading manufacturer of condensing boilers, water heating and energy recovery products and The originator of semi-instantaneous water heating
Prince PLC: Overview We are a global leader of quality water solutions for residential, industrial, municipal, and commercial settings. Our family of brands offers one of the most varied product lines in the world, with world-class, water-related solutions focused on: • Plumbing & Flow Control • Water Quality & Conditioning • Water Reuse & Drainage • HVAC • Municipal Waterworks Strategic Goals Watts Water is traded on the New York Stock Exchange under the symbol “WTS.” As a public company, growing shareholder value is critical. To that end, we focus on a five-part Global Strategy: Growth, Commercial Excellence, Operational Excellence, “One Watts Water,” and a Talent & Performance Culture. Follow us on all social media platforms @WattsWater Website http://www.watts.com/ Industry Wholesale Building Materials Company size 5,001-10,000 employees 2,248 on LinkedIn Includes members with current employer listed as Watts Water Technologies, including part-time roles. Headquarters North Andover, MA Specialties Plumbing, HVAC, Water Quality, Gas, Conditioning, Waterworks, and Drainage Prince PLC: Overview We are a global leader of quality water solutions for residential, industrial, municipal, and commercial settings. Our family of brands offers one of the most varied product lines in the world, with world-class, water-related solutions focused on: • Plumbing & Flow Control • Water Quality & Conditioning • Water Reuse & Drainage • HVAC • Municipal Waterworks Strategic Goals Watts Water is traded on the New York Stock Exchange under the symbol “WTS.” As a public company, growing shareholder value is critical. To that end, we focus on a five-part Global Strategy: Growth, Commercial Excellence, Operational Excellence, “One Watts Water,” and a Talent & Performance Culture. Follow us on all social media platforms @WattsWater Website http://www.watts.com/ Industry Wholesale Building Materials Company size 5,001-10,000 employees 2,248 on LinkedIn Includes members with current employer listed as Watts Water Technologies, including part-time roles. Headquarters North Andover, MA Specialties Plumbing, HVAC, Water Quality, Gas, Conditioning, Waterworks, and Drainage
About Courtyard Hotels is Marriott International’s largest hotel brand, with more than 1,100 hotels in over 50 countries worldwide. So, no matter where passion takes you, you’ll find us there to help you follow it. Proud members of Marriott Bonvoy. About Courtyard Hotels is Marriott International’s largest hotel brand, with more than 1,100 hotels in over 50 countries worldwide. So, no matter where passion takes you, you’ll find us there to help you follow it. Proud members of Marriott Bonvoy.
\ No newline at end of file
applications/ColossalQA/data/data_sample/companies_zh.txt
View file @ 641b1ee7
...@@ -3,4 +3,4 @@ ...@@ -3,4 +3,4 @@
万豪酒店(Marriott Hotels)是万豪旗下优质、全方位服务酒店和度假村的旗舰品牌，为客人提供始终如一、可靠和真诚关怀的体验。万豪是一个出色的主人，客人可以轻松地将生活和工作融合在一起，并受到现代旅行如何增强两者的启发。我们的酒店提供热情、专业的服务;精致而实用的客房设计;大堂空间，方便工作、餐饮和社交;餐厅和酒吧提供简单的国际美食和最新鲜的食材;会议及活动场地及服务均属黄金标准;还有宽敞的24小时健身设施。 万豪酒店(Marriott Hotels)是万豪旗下优质、全方位服务酒店和度假村的旗舰品牌，为客人提供始终如一、可靠和真诚关怀的体验。万豪是一个出色的主人，客人可以轻松地将生活和工作融合在一起，并受到现代旅行如何增强两者的启发。我们的酒店提供热情、专业的服务;精致而实用的客房设计;大堂空间，方便工作、餐饮和社交;餐厅和酒吧提供简单的国际美食和最新鲜的食材;会议及活动场地及服务均属黄金标准;还有宽敞的24小时健身设施。
AERCO International, Inc.是公认的领导者，为教育、住宿、政府、办公楼、医疗保健、工业和多户住宅等各种市场提供具有成本效益的冷凝商用锅炉和高效热水器。AERCO的系统设计方法为客户提供特定的解决方案，以较低的运营成本提供卓越的建筑性能，同时确保正常运行时间的可靠性。AERCO成立于1949年，它推出了一种革命性的设计，用于间接燃烧热水器，在控制温度下按需加热水，而无需储存。这一创新成为当今热水器的标准，最大限度地回收潜热能量，显著提高运行效率。AERCO不断创新，并于1988年向商业市场推出了第一台冷凝和全调制锅炉和热水器。这些产品的调制能力，在超过25年后仍然无与伦比，使设备的输出与实时加热需求相匹配，确保机组不会消耗更多的燃料来运行，除非绝对必要。这不仅节省了宝贵的能源，还确保了钱不会不必要地消失在“堆栈”上。AERCO通过基于解决方案的模式脱颖而出，利用数十年的工程经验和行业应用专业知识来了解每个客户的独特需求。通过与客户和最终用户直接合作，了解他们的项目具体要求，AERCO提供量身定制的应用解决方案，这些解决方案由原创产品技术组成，包括高效冷凝产品，紧凑的足迹，高降压比，独特的燃料输送，领先的控制系统和专有设计元素，结合起来可提供高达99%的效率。网址http://www.aerco.com电话845-580- 8000电话号码845-580-8000工业工业机械制造公司规模51-200名员工LinkedIn上包括当前雇主AERCO International, Inc的成员，包括兼职职位。总部成立于1949年，纽约州布劳维尔特，专长:冷凝锅炉，水加热和能源回收产品的领先制造商，半瞬时水加热的鼻祖 AERCO International, Inc.是公认的领导者，为教育、住宿、政府、办公楼、医疗保健、工业和多户住宅等各种市场提供具有成本效益的冷凝商用锅炉和高效热水器。AERCO的系统设计方法为客户提供特定的解决方案，以较低的运营成本提供卓越的建筑性能，同时确保正常运行时间的可靠性。AERCO成立于1949年，它推出了一种革命性的设计，用于间接燃烧热水器，在控制温度下按需加热水，而无需储存。这一创新成为当今热水器的标准，最大限度地回收潜热能量，显著提高运行效率。AERCO不断创新，并于1988年向商业市场推出了第一台冷凝和全调制锅炉和热水器。这些产品的调制能力，在超过25年后仍然无与伦比，使设备的输出与实时加热需求相匹配，确保机组不会消耗更多的燃料来运行，除非绝对必要。这不仅节省了宝贵的能源，还确保了钱不会不必要地消失在“堆栈”上。AERCO通过基于解决方案的模式脱颖而出，利用数十年的工程经验和行业应用专业知识来了解每个客户的独特需求。通过与客户和最终用户直接合作，了解他们的项目具体要求，AERCO提供量身定制的应用解决方案，这些解决方案由原创产品技术组成，包括高效冷凝产品，紧凑的足迹，高降压比，独特的燃料输送，领先的控制系统和专有设计元素，结合起来可提供高达99%的效率。网址http://www.aerco.com电话845-580- 8000电话号码845-580-8000工业工业机械制造公司规模51-200名员工LinkedIn上包括当前雇主AERCO International, Inc的成员，包括兼职职位。总部成立于1949年，纽约州布劳维尔特，专长:冷凝锅炉，水加热和能源回收产品的领先制造商，半瞬时水加热的鼻祖
Prince PLC:概述Prince PLC是为住宅、工业、市政和商业环境提供优质水解决方案的全球领导者。我们的品牌家族提供世界上最多样化的产品线之一，拥有世界级的水相关解决方案，专注于:•管道和流量控制•水质和调理•水再利用和排水•hvac•市政水务战略目标瓦茨水务在纽约证券交易所上市，代码为“WTS”。作为一家上市公司，股东价值的增长至关重要。为此，我们将重点放在五部分全球战略上:增长、卓越商业、卓越运营、“一瓦茨水”以及人才与绩效文化。在所有社交媒体平台关注我们@WattsWater网站http://www.watts.com/行业批发建材公司规模5,001-10,000名员工领英2,248名包括目前雇主为WattsWater Technologies的成员，包括兼职职位。总部北安多弗，MA专业管道，暖通空调，水质，气体，空调，自来水厂和排水 Prince PLC:概述Prince PLC是为住宅、工业、市政和商业环境提供优质水解决方案的全球领导者。我们的品牌家族提供世界上最多样化的产品线之一，拥有世界级的水相关解决方案，专注于:•管道和流量控制•水质和调理•水再利用和排水•hvac•市政水务战略目标瓦茨水务在纽约证券交易所上市，代码为“WTS”。作为一家上市公司，股东价值的增长至关重要。为此，我们将重点放在五部分全球战略上:增长、卓越商业、卓越运营、“一瓦茨水”以及人才与绩效文化。在所有社交媒体平台关注我们@WattsWater网站http://www.watts.com/行业批发建材公司规模5,001-10,000名员工领英2,248名包括目前雇主为WattsWater Technologies的成员，包括兼职职位。总部北安多弗，MA专业管道，暖通空调，水质，气体，空调，自来水厂和排水
万怡酒店是万豪国际最大的酒店品牌，在全球50多个国家拥有1100多家酒店。所以，无论你的激情带你去哪里，你都会发现我们会帮助你追随它。万豪酒店的骄傲会员。 万怡酒店是万豪国际最大的酒店品牌，在全球50多个国家拥有1100多家酒店。所以，无论你的激情带你去哪里，你都会发现我们会帮助你追随它。万豪酒店的骄傲会员。
\ No newline at end of file
applications/ColossalQA/data/data_sample/csv_organization_100.csv
View file @ 641b1ee7
...@@ -98,4 +98,4 @@ Index,Organization Id,Company Name,Website,Country,Description,Founded,Industry, ...@@ -98,4 +98,4 @@ Index,Organization Id,Company Name,Website,Country,Description,Founded,Industry,
97,BA6Cd9Dae2Efd62,Good Ltd,http://duffy.com/,Anguilla,Reverse-engineered composite moratorium,1971,Consumer Services,4292 97,BA6Cd9Dae2Efd62,Good Ltd,http://duffy.com/,Anguilla,Reverse-engineered composite moratorium,1971,Consumer Services,4292
98,E7df80C60Abd7f9,Clements-Espinoza,http://www.flowers.net/,Falkland Islands (Malvinas),Progressive modular hub,1991,Broadcast Media,236 98,E7df80C60Abd7f9,Clements-Espinoza,http://www.flowers.net/,Falkland Islands (Malvinas),Progressive modular hub,1991,Broadcast Media,236
99,AFc285dbE2fEd24,Mendez Inc,https://www.burke.net/,Kyrgyz Republic,User-friendly exuding migration,1993,Education Management,339 99,AFc285dbE2fEd24,Mendez Inc,https://www.burke.net/,Kyrgyz Republic,User-friendly exuding migration,1993,Education Management,339
100,e9eB5A60Cef8354,Watkins-Kaiser,http://www.herring.com/,Togo,Synergistic background access,2009,Financial Services,2785 100,e9eB5A60Cef8354,Watkins-Kaiser,http://www.herring.com/,Togo,Synergistic background access,2009,Financial Services,2785
\ No newline at end of file
applications/ColossalQA/data/tests/64KB.json
View file @ 641b1ee7
...@@ -4,4 +4,4 @@ ...@@ -4,4 +4,4 @@
{"content":"Aliquam sollicitudin ante ligula, eget malesuada nibh efficitur et. Pellentesque massa sem, scelerisque sit amet odio id, cursus tempor urna. Etiam congue dignissim volutpat. Vestibulum pharetra libero et velit gravida euismod."} {"content":"Aliquam sollicitudin ante ligula, eget malesuada nibh efficitur et. Pellentesque massa sem, scelerisque sit amet odio id, cursus tempor urna. Etiam congue dignissim volutpat. Vestibulum pharetra libero et velit gravida euismod."}
], ],
"name":"player" "name":"player"
} }
\ No newline at end of file
applications/ColossalQA/data/tests/test.html
View file @ 641b1ee7
<!DOCTYPE html> <!DOCTYPE html>
<!-- saved from url=(0046)https://docs.python.org/3/library/logging.html --> <!-- saved from url=(0046)https://docs.python.org/3/library/logging.html -->
<html><head><meta http-equiv="Content-Type" content="text/html; charset=UTF-8"> <html><head><meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0"><meta name="generator" content="Docutils 0.17.1: http://docutils.sourceforge.net/"> <meta name="viewport" content="width=device-width, initial-scale=1.0"><meta name="generator" content="Docutils 0.17.1: http://docutils.sourceforge.net/">
<meta property="og:title" content="logging — Logging facility for Python"> <meta property="og:title" content="logging — Logging facility for Python">
<meta property="og:type" content="website"> <meta property="og:type" content="website">
...@@ -16,18 +16,18 @@ ...@@ -16,18 +16,18 @@
<meta name="theme-color" content="#3776ab"> <meta name="theme-color" content="#3776ab">
<title>logging — Logging facility for Python — Python 3.11.5 documentation</title><meta name="viewport" content="width=device-width, initial-scale=1.0"> <title>logging — Logging facility for Python — Python 3.11.5 documentation</title><meta name="viewport" content="width=device-width, initial-scale=1.0">
<link rel="stylesheet" type="text/css" href="./test_files/pygments.css"> <link rel="stylesheet" type="text/css" href="./test_files/pygments.css">
<link rel="stylesheet" type="text/css" href="./test_files/pydoctheme.css"> <link rel="stylesheet" type="text/css" href="./test_files/pydoctheme.css">
<link id="pygments_dark_css" media="(prefers-color-scheme: dark)" rel="stylesheet" type="text/css" href="./test_files/pygments_dark.css"> <link id="pygments_dark_css" media="(prefers-color-scheme: dark)" rel="stylesheet" type="text/css" href="./test_files/pygments_dark.css">
<script data-url_root="../" id="documentation_options" src="./test_files/documentation_options.js.download"></script> <script data-url_root="../" id="documentation_options" src="./test_files/documentation_options.js.download"></script>
<script src="./test_files/jquery.js.download"></script> <script src="./test_files/jquery.js.download"></script>
<script src="./test_files/underscore.js.download"></script> <script src="./test_files/underscore.js.download"></script>
<script src="./test_files/doctools.js.download"></script> <script src="./test_files/doctools.js.download"></script>
<script src="./test_files/sidebar.js.download"></script> <script src="./test_files/sidebar.js.download"></script>
<link rel="search" type="application/opensearchdescription+xml" title="Search within Python 3.11.5 documentation" href="https://docs.python.org/3/_static/opensearch.xml"> <link rel="search" type="application/opensearchdescription+xml" title="Search within Python 3.11.5 documentation" href="https://docs.python.org/3/_static/opensearch.xml">
<link rel="author" title="About these documents" href="https://docs.python.org/3/about.html"> <link rel="author" title="About these documents" href="https://docs.python.org/3/about.html">
<link rel="index" title="Index" href="https://docs.python.org/3/genindex.html"> <link rel="index" title="Index" href="https://docs.python.org/3/genindex.html">
...@@ -36,11 +36,11 @@ ...@@ -36,11 +36,11 @@
<link rel="next" title="logging.config — Logging configuration" href="https://docs.python.org/3/library/logging.config.html"> <link rel="next" title="logging.config — Logging configuration" href="https://docs.python.org/3/library/logging.config.html">
<link rel="prev" title="getopt — C-style parser for command line options" href="https://docs.python.org/3/library/getopt.html"> <link rel="prev" title="getopt — C-style parser for command line options" href="https://docs.python.org/3/library/getopt.html">
<link rel="canonical" href="https://docs.python.org/3/library/logging.html"> <link rel="canonical" href="https://docs.python.org/3/library/logging.html">
<style> <style>
@media only screen { @media only screen {
table.full-width-table { table.full-width-table {
...@@ -52,7 +52,7 @@ ...@@ -52,7 +52,7 @@
<link rel="shortcut icon" type="image/png" href="./test_files/py.svg"> <link rel="shortcut icon" type="image/png" href="./test_files/py.svg">
<script type="text/javascript" src="./test_files/copybutton.js.download"></script> <script type="text/javascript" src="./test_files/copybutton.js.download"></script>
<script type="text/javascript" src="./test_files/menu.js.download"></script> <script type="text/javascript" src="./test_files/menu.js.download"></script>
<script type="text/javascript" src="./test_files/themetoggle.js.download"></script> <script type="text/javascript" src="./test_files/themetoggle.js.download"></script>
</head> </head>
<body data-new-gr-c-s-check-loaded="14.1038.0" data-gr-ext-installed=""> <body data-new-gr-c-s-check-loaded="14.1038.0" data-gr-ext-installed="">
...@@ -79,7 +79,7 @@ ...@@ -79,7 +79,7 @@
<div class="menu-wrapper"> <div class="menu-wrapper">
<nav class="menu" role="navigation" aria-label="main navigation" tabindex="-1"> <nav class="menu" role="navigation" aria-label="main navigation" tabindex="-1">
<div class="language_switcher_placeholder"><select id="language_select"><option value="en" selected="selected">English</option><option value="es">Spanish</option><option value="fr">French</option><option value="ja">Japanese</option><option value="ko">Korean</option><option value="pt-br">Brazilian Portuguese</option><option value="tr">Turkish</option><option value="zh-cn">Simplified Chinese</option><option value="zh-tw">Traditional Chinese</option></select></div> <div class="language_switcher_placeholder"><select id="language_select"><option value="en" selected="selected">English</option><option value="es">Spanish</option><option value="fr">French</option><option value="ja">Japanese</option><option value="ko">Korean</option><option value="pt-br">Brazilian Portuguese</option><option value="tr">Turkish</option><option value="zh-cn">Simplified Chinese</option><option value="zh-tw">Traditional Chinese</option></select></div>
<label class="theme-selector-label"> <label class="theme-selector-label">
Theme Theme
<select class="theme-selector" oninput="activateTheme(this.value)"> <select class="theme-selector" oninput="activateTheme(this.value)">
...@@ -131,7 +131,7 @@ ...@@ -131,7 +131,7 @@
</div> </div>
</div> </div>
<div class="related" role="navigation" aria-label="related navigation"> <div class="related" role="navigation" aria-label="related navigation">
<h3>Navigation</h3> <h3>Navigation</h3>
<ul> <ul>
...@@ -151,7 +151,7 @@ ...@@ -151,7 +151,7 @@
<div class="version_switcher_placeholder"><select id="version_select"><option value="3.13">dev (3.13)</option><option value="3.12">pre (3.12)</option><option value="3.11" selected="selected">3.11.5</option><option value="3.10">3.10</option><option value="3.9">3.9</option><option value="3.8">3.8</option><option value="3.7">3.7</option><option value="3.6">3.6</option><option value="3.5">3.5</option><option value="2.7">2.7</option></select></div> <div class="version_switcher_placeholder"><select id="version_select"><option value="3.13">dev (3.13)</option><option value="3.12">pre (3.12)</option><option value="3.11" selected="selected">3.11.5</option><option value="3.10">3.10</option><option value="3.9">3.9</option><option value="3.8">3.8</option><option value="3.7">3.7</option><option value="3.6">3.6</option><option value="3.5">3.5</option><option value="2.7">2.7</option></select></div>
</li> </li>
<li> <li>
</li> </li>
<li id="cpython-language-and-version"> <li id="cpython-language-and-version">
<a href="https://docs.python.org/3/index.html">3.11.5 Documentation</a> » <a href="https://docs.python.org/3/index.html">3.11.5 Documentation</a> »
...@@ -161,7 +161,7 @@ ...@@ -161,7 +161,7 @@
<li class="nav-item nav-item-2"><a href="https://docs.python.org/3/library/allos.html" accesskey="U">Generic Operating System Services</a> »</li> <li class="nav-item nav-item-2"><a href="https://docs.python.org/3/library/allos.html" accesskey="U">Generic Operating System Services</a> »</li>
<li class="nav-item nav-item-this"><a href="https://docs.python.org/3/library/logging.html"><code class="xref py py-mod docutils literal notranslate"><span class="pre">logging</span></code> — Logging facility for Python</a></li> <li class="nav-item nav-item-this"><a href="https://docs.python.org/3/library/logging.html"><code class="xref py py-mod docutils literal notranslate"><span class="pre">logging</span></code> — Logging facility for Python</a></li>
<li class="right"> <li class="right">
<div class="inline-search" role="search"> <div class="inline-search" role="search">
<form class="inline-search" action="https://docs.python.org/3/search.html" method="get"> <form class="inline-search" action="https://docs.python.org/3/search.html" method="get">
...@@ -180,15 +180,15 @@ ...@@ -180,15 +180,15 @@
<option value="dark">Dark</option> <option value="dark">Dark</option>
</select> </select>
</label> |</li> </label> |</li>
</ul> </ul>
</div> </div>
<div class="document"> <div class="document">
<div class="documentwrapper"> <div class="documentwrapper">
<div class="bodywrapper"> <div class="bodywrapper">
<div class="body" role="main"> <div class="body" role="main">
<section id="module-logging"> <section id="module-logging">
<span id="logging-logging-facility-for-python"></span><h1><a class="reference internal" href="https://docs.python.org/3/library/logging.html#module-logging" title="logging: Flexible event logging system for applications."><code class="xref py py-mod docutils literal notranslate"><span class="pre">logging</span></code></a> — Logging facility for Python<a class="headerlink" href="https://docs.python.org/3/library/logging.html#module-logging" title="Permalink to this headline"></a></h1> <span id="logging-logging-facility-for-python"></span><h1><a class="reference internal" href="https://docs.python.org/3/library/logging.html#module-logging" title="logging: Flexible event logging system for applications."><code class="xref py py-mod docutils literal notranslate"><span class="pre">logging</span></code></a> — Logging facility for Python<a class="headerlink" href="https://docs.python.org/3/library/logging.html#module-logging" title="Permalink to this headline"></a></h1>
<p><strong>Source code:</strong> <a class="reference external" href="https://github.com/python/cpython/tree/3.11/Lib/logging/__init__.py">Lib/logging/__init__.py</a></p> <p><strong>Source code:</strong> <a class="reference external" href="https://github.com/python/cpython/tree/3.11/Lib/logging/__init__.py">Lib/logging/__init__.py</a></p>
...@@ -1871,7 +1871,7 @@ library.</p> ...@@ -1871,7 +1871,7 @@ library.</p>
</div> </div>
<div id="sidebarbutton"><span>«</span></div></div> <div id="sidebarbutton"><span>«</span></div></div>
<div class="clearer"></div> <div class="clearer"></div>
</div> </div>
<div class="related" role="navigation" aria-label="related navigation"> <div class="related" role="navigation" aria-label="related navigation">
<h3>Navigation</h3> <h3>Navigation</h3>
<ul> <ul>
...@@ -1891,7 +1891,7 @@ library.</p> ...@@ -1891,7 +1891,7 @@ library.</p>
<div class="version_switcher_placeholder"><select id="version_select"><option value="3.13">dev (3.13)</option><option value="3.12">pre (3.12)</option><option value="3.11" selected="selected">3.11.5</option><option value="3.10">3.10</option><option value="3.9">3.9</option><option value="3.8">3.8</option><option value="3.7">3.7</option><option value="3.6">3.6</option><option value="3.5">3.5</option><option value="2.7">2.7</option></select></div> <div class="version_switcher_placeholder"><select id="version_select"><option value="3.13">dev (3.13)</option><option value="3.12">pre (3.12)</option><option value="3.11" selected="selected">3.11.5</option><option value="3.10">3.10</option><option value="3.9">3.9</option><option value="3.8">3.8</option><option value="3.7">3.7</option><option value="3.6">3.6</option><option value="3.5">3.5</option><option value="2.7">2.7</option></select></div>
</li> </li>
<li> <li>
</li> </li>
<li id="cpython-language-and-version"> <li id="cpython-language-and-version">
<a href="https://docs.python.org/3/index.html">3.11.5 Documentation</a> » <a href="https://docs.python.org/3/index.html">3.11.5 Documentation</a> »
...@@ -1901,7 +1901,7 @@ library.</p> ...@@ -1901,7 +1901,7 @@ library.</p>
<li class="nav-item nav-item-2"><a href="https://docs.python.org/3/library/allos.html">Generic Operating System Services</a> »</li> <li class="nav-item nav-item-2"><a href="https://docs.python.org/3/library/allos.html">Generic Operating System Services</a> »</li>
<li class="nav-item nav-item-this"><a href="https://docs.python.org/3/library/logging.html"><code class="xref py py-mod docutils literal notranslate"><span class="pre">logging</span></code> — Logging facility for Python</a></li> <li class="nav-item nav-item-this"><a href="https://docs.python.org/3/library/logging.html"><code class="xref py py-mod docutils literal notranslate"><span class="pre">logging</span></code> — Logging facility for Python</a></li>
<li class="right"> <li class="right">
<div class="inline-search" role="search"> <div class="inline-search" role="search">
<form class="inline-search" action="https://docs.python.org/3/search.html" method="get"> <form class="inline-search" action="https://docs.python.org/3/search.html" method="get">
...@@ -1920,9 +1920,9 @@ library.</p> ...@@ -1920,9 +1920,9 @@ library.</p>
<option value="dark">Dark</option> <option value="dark">Dark</option>
</select> </select>
</label> |</li> </label> |</li>
</ul> </ul>
</div> </div>
<div class="footer"> <div class="footer">
© <a href="https://docs.python.org/3/copyright.html">Copyright</a> 2001-2023, Python Software Foundation. © <a href="https://docs.python.org/3/copyright.html">Copyright</a> 2001-2023, Python Software Foundation.
<br> <br>
...@@ -1946,7 +1946,7 @@ library.</p> ...@@ -1946,7 +1946,7 @@ library.</p>
</div> </div>
<script type="text/javascript" src="./test_files/switchers.js.download"></script> <script type="text/javascript" src="./test_files/switchers.js.download"></script>
<div id="hl-aria-live-message-container" aria-live="polite" class="visually-hidden"></div><div id="hl-aria-live-alert-container" role="alert" aria-live="assertive" class="visually-hidden"></div></body><grammarly-desktop-integration data-grammarly-shadow-root="true"><template shadowrootmode="open"><style> <div id="hl-aria-live-message-container" aria-live="polite" class="visually-hidden"></div><div id="hl-aria-live-alert-container" role="alert" aria-live="assertive" class="visually-hidden"></div></body><grammarly-desktop-integration data-grammarly-shadow-root="true"><template shadowrootmode="open"><style>
div.grammarly-desktop-integration { div.grammarly-desktop-integration {
position: absolute; position: absolute;
...@@ -1967,4 +1967,4 @@ library.</p> ...@@ -1967,4 +1967,4 @@ library.</p>
div.grammarly-desktop-integration:before { div.grammarly-desktop-integration:before {
content: attr(data-content); content: attr(data-content);
} }
</style><div aria-label="grammarly-integration" role="group" tabindex="-1" class="grammarly-desktop-integration" data-content="{&quot;mode&quot;:&quot;limited&quot;,&quot;isActive&quot;:false,&quot;isUserDisabled&quot;:false}"></div></template></grammarly-desktop-integration></html> </style><div aria-label="grammarly-integration" role="group" tabindex="-1" class="grammarly-desktop-integration" data-content="{&quot;mode&quot;:&quot;limited&quot;,&quot;isActive&quot;:false,&quot;isUserDisabled&quot;:false}"></div></template></grammarly-desktop-integration></html>
\ No newline at end of file
applications/ColossalQA/data/tests/test.md
View file @ 641b1ee7
...@@ -34,9 +34,9 @@ python api_server.py --host localhost --port $PORT_NUMBER --model $PATH_TO_MODEL ...@@ -34,9 +34,9 @@ python api_server.py --host localhost --port $PORT_NUMBER --model $PATH_TO_MODEL
### Collect your data ### Collect your data
For ChatGPT based Agent we support document retrieval and simple sql search. For ChatGPT based Agent we support document retrieval and simple sql search.
If you want to run the demo locally, we provided document retrieval based conversation system built upon langchain. It accept a wide range of documents. If you want to run the demo locally, we provided document retrieval based conversation system built upon langchain. It accept a wide range of documents.
Read comments under ./colossalqa/data_loader for more detail Read comments under ./colossalqa/data_loader for more detail
### Serving ### Serving
Currently use vllm will replace with colossal inference when ready. Please refer class VllmLLM. Currently use vllm will replace with colossal inference when ready. Please refer class VllmLLM.
......
applications/ColossalQA/data/tests/test.txt
View file @ 641b1ee7
Your Name Your Name
Lorem ipsum dolor sit amet, consectetuer adipiscing elit Lorem ipsum dolor sit amet, consectetuer adipiscing elit
123 Your Street 123 Your Street
Your City, ST 12345 Your City, ST 12345
(123) 456-7890 (123) 456-7890
no_reply@example.com no_reply@example.com
EXPERIENCE EXPERIENCE
Company, Location — Job Title Company, Location — Job Title
MONTH 20XX - PRESENT MONTH 20XX - PRESENT
Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh. Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh.
Company, Location — Job Title Company, Location — Job Title
MONTH 20XX - MONTH 20XX MONTH 20XX - MONTH 20XX
Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh. Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh.
Company, Location — Job Title Company, Location — Job Title
MONTH 20XX - MONTH 20XX MONTH 20XX - MONTH 20XX
Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh. Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh.
EDUCATION EDUCATION
School Name, Location — Degree School Name, Location — Degree
MONTH 20XX - MONTH 20XX MONTH 20XX - MONTH 20XX
Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh euismod tincidunt ut laoreet dolore. Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh euismod tincidunt ut laoreet dolore.
School Name, Location — Degree School Name, Location — Degree
MONTH 20XX - MONTH 20XX MONTH 20XX - MONTH 20XX
Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam. Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam.
PROJECTS PROJECTS
Project Name — Detail Project Name — Detail
Lorem ipsum dolor sit amet, consectetuer adipiscing elit. Lorem ipsum dolor sit amet, consectetuer adipiscing elit.
SKILLS SKILLS
* Lorem ipsum dolor sit amet. * Lorem ipsum dolor sit amet.
* Consectetuer adipiscing elit. * Consectetuer adipiscing elit.
* Sed diam nonummy nibh euismod tincidunt. * Sed diam nonummy nibh euismod tincidunt.
* L​​​‌​aoreet dolore magna aliquam erat volutpat. * L​​​‌​aoreet dolore magna aliquam erat volutpat.
AWARDS AWARDS
Lorem ipsum dolor sit amet Consectetuer adipiscing elit, Sed diam nonummy Lorem ipsum dolor sit amet Consectetuer adipiscing elit, Sed diam nonummy
Nibh euismod tincidunt ut laoreet dolore magna aliquam erat volutpat. Nibh euismod tincidunt ut laoreet dolore magna aliquam erat volutpat.
Lorem ipsum dolor sit amet Consectetuer adipiscing elit, Sed diam nonummy Lorem ipsum dolor sit amet Consectetuer adipiscing elit, Sed diam nonummy
Nibh euismod tincidunt ut laoreet dolore magna aliquam erat volutpat. Nibh euismod tincidunt ut laoreet dolore magna aliquam erat volutpat.
LANGUAGES LANGUAGES
Lorem ipsum, Dolor sit amet, Consectetuer Lorem ipsum, Dolor sit amet, Consectetuer
\ No newline at end of file
applications/ColossalQA/examples/retrieval_conversation_universal.py
View file @ 641b1ee7
import argparse import argparse
from colossalqa.retrieval_conversation_universal import UniversalRetrievalConversation from colossalqa.retrieval_conversation_universal import UniversalRetrievalConversation
if __name__ == '__main__': if __name__ == "__main__":
# Parse arguments # Parse arguments
parser = argparse.ArgumentParser() parser = argparse.ArgumentParser()
parser.add_argument('--en_model_path', type=str, default=None) parser.add_argument("--en_model_path", type=str, default=None)
parser.add_argument('--zh_model_path', type=str, default=None) parser.add_argument("--zh_model_path", type=str, default=None)
parser.add_argument('--zh_model_name', type=str, default=None) parser.add_argument("--zh_model_name", type=str, default=None)
parser.add_argument('--en_model_name', type=str, default=None) parser.add_argument("--en_model_name", type=str, default=None)
parser.add_argument('--sql_file_path', type=str, default=None, help='path to the a empty folder for storing sql files for indexing') parser.add_argument(
"--sql_file_path", type=str, default=None, help="path to the a empty folder for storing sql files for indexing"
)
args = parser.parse_args() args = parser.parse_args()
# Will ask for documents path in running time # Will ask for documents path in running time
session = UniversalRetrievalConversation(files_en=None, session = UniversalRetrievalConversation(
files_zh=None, files_en=None,
zh_model_path=args.zh_model_path, en_model_path=args.en_model_path, files_zh=None,
zh_model_name=args.zh_model_name, en_model_name=args.en_model_name, zh_model_path=args.zh_model_path,
sql_file_path=args.sql_file_path en_model_path=args.en_model_path,
) zh_model_name=args.zh_model_name,
en_model_name=args.en_model_name,
sql_file_path=args.sql_file_path,
)
session.start_test_session() session.start_test_session()
\ No newline at end of file
applications/ColossalQA/examples/webui_demo/RAG_ChatBot.py
View file @ 641b1ee7
...@@ -5,13 +5,7 @@ from colossalqa.chain.retrieval_qa.base import RetrievalQA ...@@ -5,13 +5,7 @@ from colossalqa.chain.retrieval_qa.base import RetrievalQA
from colossalqa.data_loader.document_loader import DocumentLoader from colossalqa.data_loader.document_loader import DocumentLoader
from colossalqa.memory import ConversationBufferWithSummary from colossalqa.memory import ConversationBufferWithSummary
from colossalqa.mylogging import get_logger from colossalqa.mylogging import get_logger
from colossalqa.prompt.prompt import ( from colossalqa.prompt.prompt import ZH_RETRIEVAL_QA_REJECTION_ANSWER, ZH_RETRIEVAL_QA_TRIGGER_KEYWORDS
PROMPT_DISAMBIGUATE_ZH,
PROMPT_RETRIEVAL_QA_ZH,
SUMMARY_PROMPT_ZH,
ZH_RETRIEVAL_QA_REJECTION_ANSWER,
ZH_RETRIEVAL_QA_TRIGGER_KEYWORDS,
)
from colossalqa.retriever import CustomRetriever from colossalqa.retriever import CustomRetriever
from langchain import LLMChain from langchain import LLMChain
from langchain.embeddings import HuggingFaceEmbeddings from langchain.embeddings import HuggingFaceEmbeddings
...@@ -116,13 +110,13 @@ class RAG_ChatBot: ...@@ -116,13 +110,13 @@ class RAG_ChatBot:
def split_docs(self, documents): def split_docs(self, documents):
doc_splits = self.text_splitter.split_documents(documents) doc_splits = self.text_splitter.split_documents(documents)
return doc_splits return doc_splits
def clear_docs(self, **kwargs): def clear_docs(self, **kwargs):
self.documents = [] self.documents = []
self.docs_names = [] self.docs_names = []
self.info_retriever.clear_documents() self.info_retriever.clear_documents()
self.memory.initiate_document_retrieval_chain(self.llm, kwargs["gen_qa_prompt"], self.info_retriever) self.memory.initiate_document_retrieval_chain(self.llm, kwargs["gen_qa_prompt"], self.info_retriever)
def reset_config(self, rag_config): def reset_config(self, rag_config):
self.rag_config = rag_config self.rag_config = rag_config
self.set_embed_model(**self.rag_config["embed"]) self.set_embed_model(**self.rag_config["embed"])
......
applications/ColossalQA/examples/webui_demo/README.md
View file @ 641b1ee7
...@@ -115,4 +115,4 @@ python webui.py --http_host "your-backend-api-host" --http_port "your-backend-ap ...@@ -115,4 +115,4 @@ python webui.py --http_host "your-backend-api-host" --http_port "your-backend-ap
After launching the script, you can upload files and engage with the chatbot through your web browser. After launching the script, you can upload files and engage with the chatbot through your web browser.
![ColossalQA Demo](https://raw.githubusercontent.com/hpcaitech/public_assets/main/applications/colossalqa/new_ui.png) ![ColossalQA Demo](https://raw.githubusercontent.com/hpcaitech/public_assets/main/applications/colossalqa/new_ui.png)
\ No newline at end of file
applications/ColossalQA/examples/webui_demo/config.py
View file @ 641b1ee7
from colossalqa.prompt.prompt import ( from colossalqa.prompt.prompt import PROMPT_DISAMBIGUATE_ZH, PROMPT_RETRIEVAL_QA_ZH, SUMMARY_PROMPT_ZH
PROMPT_DISAMBIGUATE_ZH,
PROMPT_RETRIEVAL_QA_ZH,
SUMMARY_PROMPT_ZH,
ZH_RETRIEVAL_QA_REJECTION_ANSWER,
ZH_RETRIEVAL_QA_TRIGGER_KEYWORDS,
)
from colossalqa.text_splitter import ChineseTextSplitter from colossalqa.text_splitter import ChineseTextSplitter
ALL_CONFIG = { ALL_CONFIG = {
"embed": { "embed": {
"embed_name": "m3e", # embedding model name "embed_name": "m3e", # embedding model name
"embed_model_name_or_path": "moka-ai/m3e-base", # path to embedding model, could be a local path or a huggingface path "embed_model_name_or_path": "moka-ai/m3e-base", # path to embedding model, could be a local path or a huggingface path
"embed_model_device": { "embed_model_device": {"device": "cpu"},
"device": "cpu"
}
}, },
"model": { "model": {
"mode": "api", # "local" for loading models, "api" for using model api "mode": "api", # "local" for loading models, "api" for using model api
"model_name": "chatgpt_api", # local model name, "chatgpt_api" or "pangu_api" "model_name": "chatgpt_api", # local model name, "chatgpt_api" or "pangu_api"
"model_path": "", # path to the model, could be a local path or a huggingface path. don't need if using an api "model_path": "", # path to the model, could be a local path or a huggingface path. don't need if using an api
"device": { "device": {"device": "cuda"},
"device": "cuda"
}
},
"splitter": {
"name": ChineseTextSplitter
},
"retrieval": {
"retri_top_k": 3,
"retri_kb_file_path": "./", # path to store database files
"verbose": True
}, },
"splitter": {"name": ChineseTextSplitter},
"retrieval": {"retri_top_k": 3, "retri_kb_file_path": "./", "verbose": True}, # path to store database files
"chain": { "chain": {
"mem_summary_prompt": SUMMARY_PROMPT_ZH, # summary prompt template "mem_summary_prompt": SUMMARY_PROMPT_ZH, # summary prompt template
"mem_human_prefix": "用户", "mem_human_prefix": "用户",
"mem_ai_prefix": "Assistant", "mem_ai_prefix": "Assistant",
"mem_max_tokens": 2000, "mem_max_tokens": 2000,
"mem_llm_kwargs": { "mem_llm_kwargs": {"max_new_tokens": 50, "temperature": 1, "do_sample": True},
"max_new_tokens": 50,
"temperature": 1,
"do_sample": True
},
"disambig_prompt": PROMPT_DISAMBIGUATE_ZH, # disambiguate prompt template "disambig_prompt": PROMPT_DISAMBIGUATE_ZH, # disambiguate prompt template
"disambig_llm_kwargs": { "disambig_llm_kwargs": {"max_new_tokens": 30, "temperature": 1, "do_sample": True},
"max_new_tokens": 30, "gen_llm_kwargs": {"max_new_tokens": 100, "temperature": 1, "do_sample": True},
"temperature": 1,
"do_sample": True
},
"gen_llm_kwargs": {
"max_new_tokens": 100,
"temperature": 1,
"do_sample": True
},
"gen_qa_prompt": PROMPT_RETRIEVAL_QA_ZH, # generation prompt template "gen_qa_prompt": PROMPT_RETRIEVAL_QA_ZH, # generation prompt template
"verbose": True "verbose": True,
} },
} }
\ No newline at end of file
applications/ColossalQA/examples/webui_demo/server.py
View file @ 641b1ee7
import argparse import argparse
import os
from typing import List, Union from typing import List, Union
import config
import uvicorn
from colossalqa.local.llm import ColossalAPI, ColossalLLM from colossalqa.local.llm import ColossalAPI, ColossalLLM
from colossalqa.data_loader.document_loader import DocumentLoader
from colossalqa.mylogging import get_logger from colossalqa.mylogging import get_logger
from colossalqa.retrieval_conversation_zh import ChineseRetrievalConversation
from colossalqa.retriever import CustomRetriever
from enum import Enum
from fastapi import FastAPI, Request from fastapi import FastAPI, Request
from langchain.embeddings import HuggingFaceEmbeddings from pydantic import BaseModel
from langchain.text_splitter import RecursiveCharacterTextSplitter
from pydantic import BaseModel, Field
import uvicorn
import config
from RAG_ChatBot import RAG_ChatBot from RAG_ChatBot import RAG_ChatBot
from utils import DocAction from utils import DocAction
logger = get_logger() logger = get_logger()
def parseArgs(): def parseArgs():
parser = argparse.ArgumentParser() parser = argparse.ArgumentParser()
parser.add_argument("--http_host", default="0.0.0.0") parser.add_argument("--http_host", default="0.0.0.0")
...@@ -36,6 +27,7 @@ class DocUpdateReq(BaseModel): ...@@ -36,6 +27,7 @@ class DocUpdateReq(BaseModel):
doc_files: Union[List[str], str, None] = None doc_files: Union[List[str], str, None] = None
action: DocAction = DocAction.ADD action: DocAction = DocAction.ADD
class GenerationTaskReq(BaseModel): class GenerationTaskReq(BaseModel):
user_input: str user_input: str
...@@ -45,7 +37,7 @@ def update_docs(data: DocUpdateReq, request: Request): ...@@ -45,7 +37,7 @@ def update_docs(data: DocUpdateReq, request: Request):
if data.action == "add": if data.action == "add":
if isinstance(data.doc_files, str): if isinstance(data.doc_files, str):
data.doc_files = [data.doc_files] data.doc_files = [data.doc_files]
chatbot.load_doc_from_files(files = data.doc_files) chatbot.load_doc_from_files(files=data.doc_files)
all_docs = "" all_docs = ""
for doc in chatbot.docs_names: for doc in chatbot.docs_names:
all_docs += f"\t{doc}\n\n" all_docs += f"\t{doc}\n\n"
...@@ -79,17 +71,18 @@ if __name__ == "__main__": ...@@ -79,17 +71,18 @@ if __name__ == "__main__":
elif all_config["model"]["mode"] == "api": elif all_config["model"]["mode"] == "api":
if model_name == "pangu_api": if model_name == "pangu_api":
from colossalqa.local.pangu_llm import Pangu from colossalqa.local.pangu_llm import Pangu
gen_config = { gen_config = {
"user": "User", "user": "User",
"max_tokens": all_config["chain"]["disambig_llm_kwargs"]["max_new_tokens"], "max_tokens": all_config["chain"]["disambig_llm_kwargs"]["max_new_tokens"],
"temperature": all_config["chain"]["disambig_llm_kwargs"]["temperature"], "temperature": all_config["chain"]["disambig_llm_kwargs"]["temperature"],
"n": 1 # the number of responses generated "n": 1, # the number of responses generated
} }
llm = Pangu(gen_config=gen_config) llm = Pangu(gen_config=gen_config)
llm.set_auth_config() # verify user's auth info here llm.set_auth_config() # verify user's auth info here
elif model_name == "chatgpt_api": elif model_name == "chatgpt_api":
from langchain.llms import OpenAI from langchain.llms import OpenAI
llm = OpenAI() llm = OpenAI()
else: else:
raise ValueError("Unsupported mode.") raise ValueError("Unsupported mode.")
......
applications/ColossalQA/examples/webui_demo/webui.py
View file @ 641b1ee7
import argparse import argparse
import json import json
import os import os
import requests
import gradio as gr import gradio as gr
import requests
from utils import DocAction from utils import DocAction
def parseArgs(): def parseArgs():
parser = argparse.ArgumentParser() parser = argparse.ArgumentParser()
parser.add_argument("--http_host", default="0.0.0.0") parser.add_argument("--http_host", default="0.0.0.0")
parser.add_argument("--http_port", type=int, default=13666) parser.add_argument("--http_port", type=int, default=13666)
return parser.parse_args() return parser.parse_args()
def get_response(data, url): def get_response(data, url):
headers = {"Content-type": "application/json"} headers = {"Content-type": "application/json"}
response = requests.post(url, json=data, headers=headers) response = requests.post(url, json=data, headers=headers)
response = json.loads(response.content) response = json.loads(response.content)
return response return response
def add_text(history, text): def add_text(history, text):
history = history + [(text, None)] history = history + [(text, None)]
return history, gr.update(value=None, interactive=True) return history, gr.update(value=None, interactive=True)
...@@ -28,35 +30,28 @@ def add_file(history, files): ...@@ -28,35 +30,28 @@ def add_file(history, files):
files_string = "\n".join([os.path.basename(file.name) for file in files]) files_string = "\n".join([os.path.basename(file.name) for file in files])
doc_files = [file.name for file in files] doc_files = [file.name for file in files]
data = { data = {"doc_files": doc_files, "action": DocAction.ADD}
"doc_files": doc_files,
"action": DocAction.ADD
}
response = get_response(data, update_url)["response"] response = get_response(data, update_url)["response"]
history = history + [(files_string, response)] history = history + [(files_string, response)]
return history return history
def bot(history):
data = { def bot(history):
"user_input": history[-1][0].strip() data = {"user_input": history[-1][0].strip()}
}
response = get_response(data, gen_url) response = get_response(data, gen_url)
if response["error"] != "": if response["error"] != "":
raise gr.Error(response["error"]) raise gr.Error(response["error"])
history[-1][1] = response["response"] history[-1][1] = response["response"]
yield history yield history
def restart(chatbot, txt): def restart(chatbot, txt):
# Reset the conversation state and clear the chat history # Reset the conversation state and clear the chat history
data = { data = {"doc_files": "", "action": DocAction.CLEAR}
"doc_files": "", get_response(data, update_url)
"action": DocAction.CLEAR
}
response = get_response(data, update_url)
return gr.update(value=None), gr.update(value=None, interactive=True) return gr.update(value=None), gr.update(value=None, interactive=True)
...@@ -97,7 +92,7 @@ with gr.Blocks(css=CSS) as demo: ...@@ -97,7 +92,7 @@ with gr.Blocks(css=CSS) as demo:
txt_msg = txt.submit(add_text, [chatbot, txt], [chatbot, txt], queue=False).then(bot, chatbot, chatbot) txt_msg = txt.submit(add_text, [chatbot, txt], [chatbot, txt], queue=False).then(bot, chatbot, chatbot)
# Clear the original textbox # Clear the original textbox
txt_msg.then(lambda: gr.update(value=None, interactive=True), None, [txt], queue=False) txt_msg.then(lambda: gr.update(value=None, interactive=True), None, [txt], queue=False)
# Click Upload Button: 1. upload files 2. send config to backend, initalize model 3. get response "conversation_ready" = True/False # Click Upload Button: 1. upload files 2. send config to backend, initalize model 3. get response "conversation_ready" = True/False
file_msg = btn.upload(add_file, [chatbot, btn], [chatbot], queue=False) file_msg = btn.upload(add_file, [chatbot, btn], [chatbot], queue=False)
......
applications/ColossalQA/pytest.ini
View file @ 641b1ee7
[pytest] [pytest]
markers = markers =
dist: tests which are run in a multi-GPU or multi-machine environment (at least 4 GPUs) dist: tests which are run in a multi-GPU or multi-machine environment (at least 4 GPUs)
largedist: tests which are run in a multi-GPU or multi-machine environment (at least 8 GPUs) largedist: tests which are run in a multi-GPU or multi-machine environment (at least 8 GPUs)
\ No newline at end of file
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment