├── README.md ├── requirements.txt ├── bot ├── conf.py ├── misc.py ├── cache.py ├── util_meta.py ├── util_openai.py └── app.py ├── .gitignore └── LICENSE /README.md: -------------------------------------------------------------------------------- 1 | # discord-bot 2 | Discord Bot for Core Devs Discord server 3 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | discord.py==2.2.2 2 | openai-async==0.0.3 3 | tiktoken==0.3.1 4 | httpx==0.23.3 5 | -------------------------------------------------------------------------------- /bot/conf.py: -------------------------------------------------------------------------------- 1 | import os 2 | 3 | DISCORD_TOKEN = os.getenv("DISCORD_TOKEN") 4 | OPEN_AI_API_KEY = os.getenv("OPEN_AI_API_KEY") 5 | -------------------------------------------------------------------------------- /bot/misc.py: -------------------------------------------------------------------------------- 1 | import logging 2 | import sys 3 | 4 | 5 | def get_logger(name: str) -> logging.Logger: 6 | logger = logging.getLogger(name) 7 | logger.setLevel(logging.INFO) 8 | handler = logging.StreamHandler(sys.stdout) 9 | handler.setLevel(logging.DEBUG) 10 | formatter = logging.Formatter("%(asctime)s:%(levelname)s:%(name)s: %(message)s") 11 | handler.setFormatter(formatter) 12 | logger.addHandler(handler) 13 | return logger 14 | -------------------------------------------------------------------------------- /bot/cache.py: -------------------------------------------------------------------------------- 1 | import time 2 | from collections import OrderedDict 3 | 4 | 5 | class SimpleTTLCache: 6 | def __init__(self, capacity): 7 | self.capacity = capacity 8 | self.cache = OrderedDict() 9 | 10 | def get(self, key: str) -> str | None: 11 | if key not in self.cache: 12 | return None 13 | self.cache.move_to_end(key) 14 | value, expire_at = self.cache[key] 15 | if expire_at < time.time(): 16 | self.cache.pop(key) 17 | return None 18 | return value 19 | 20 | def put(self, key: str, value: str, ttl: int) -> None: 21 | self.cache[key] = (value, time.time() + ttl) 22 | self.cache.move_to_end(key) 23 | if len(self.cache) > self.capacity: 24 | self.cache.popitem(last=False) 25 | -------------------------------------------------------------------------------- /bot/util_meta.py: -------------------------------------------------------------------------------- 1 | import httpx 2 | 3 | 4 | async def get_gh_discuss(issue_number: int) -> str: 5 | def extract_content(res: dict) -> str: 6 | user = res["user"]["login"] 7 | body = res["body"] 8 | return f"{user} said '{body}'" 9 | 10 | async with httpx.AsyncClient() as client: 11 | root_target = ( 12 | f"https://api.github.com/repos/python/cpython/issues/{issue_number}" 13 | ) 14 | comment_target = f"https://api.github.com/repos/python/cpython/issues/{issue_number}/comments" 15 | root = await client.get(root_target) 16 | root = root.json() 17 | texts = [] 18 | text = extract_content(root) 19 | texts.append(text) 20 | comments = await client.get(comment_target) 21 | comments = comments.json() 22 | for comment in comments: 23 | text = extract_content(comment) 24 | texts.append(text) 25 | 26 | return "\n\n".join(texts) 27 | 28 | 29 | async def get_pep_text(target_pep: str) -> str: 30 | async with httpx.AsyncClient() as client: 31 | target = f"https://raw.githubusercontent.com/python/peps/main/{target_pep}.rst" 32 | res = await client.get(target) 33 | if res.status_code != 200: 34 | # fallback 35 | target = ( 36 | f"https://raw.githubusercontent.com/python/peps/main/{target_pep}.txt" 37 | ) 38 | res = await client.get(target) 39 | if res.status_code != 200: 40 | raise RuntimeError("Not found") 41 | return res.text 42 | -------------------------------------------------------------------------------- /bot/util_openai.py: -------------------------------------------------------------------------------- 1 | import os 2 | from typing import Generator 3 | 4 | import httpx 5 | import openai_async 6 | 7 | from conf import OPEN_AI_API_KEY 8 | 9 | 10 | def tokens_to_chunks( 11 | tokens: list[int], chunk_size: int = 3000, overlap: int = 100 12 | ) -> Generator[list[int], None, None]: 13 | num_tokens = len(tokens) 14 | for i in range(0, num_tokens, chunk_size - overlap): 15 | chunk = tokens[i : i + chunk_size] 16 | yield chunk 17 | 18 | 19 | async def send_partial_text(text: str, target_doc: str) -> str: 20 | messages = [ 21 | {"role": "system", "content": f"This is text summarization for {target_doc}"}, 22 | {"role": "user", "content": f"Summarize this documentation: {text}"}, 23 | ] 24 | try: 25 | response = await openai_async.chat_complete( 26 | OPEN_AI_API_KEY, 27 | timeout=60, 28 | payload={ 29 | "model": "gpt-3.5-turbo", 30 | "messages": messages, 31 | "temperature": 0.3, 32 | "max_tokens": 500, 33 | "top_p": 1.0, 34 | "frequency_penalty": 0.0, 35 | "presence_penalty": 1, 36 | }, 37 | ) 38 | res = response.json() 39 | return res["choices"][0]["message"]["content"].strip() 40 | except httpx.TimeoutException as e: 41 | raise RuntimeError(f"Timeout while summarizing {target_pep}") 42 | 43 | 44 | async def summarize(link: str, text: str) -> str: 45 | prompt_request = f"Please summarize the text with bullet points: {text}" 46 | try: 47 | response = await openai_async.complete( 48 | OPEN_AI_API_KEY, 49 | timeout=60, 50 | payload={ 51 | "model": "text-davinci-003", 52 | "prompt": prompt_request, 53 | "temperature": 0.3, 54 | "max_tokens": 150, 55 | "top_p": 1.0, 56 | "frequency_penalty": 0.0, 57 | "presence_penalty": 1, 58 | }, 59 | ) 60 | res = response.json() 61 | content = res["choices"][0]["text"].strip() 62 | summary = f"{content}\n\nFor more information: {link}" 63 | return summary 64 | except httpx.TimeoutException as e: 65 | raise RuntimeError(f"Timeout while summarizing {link}") 66 | -------------------------------------------------------------------------------- /bot/app.py: -------------------------------------------------------------------------------- 1 | import discord 2 | import tiktoken 3 | from discord.ext import commands 4 | 5 | from conf import DISCORD_TOKEN 6 | from cache import SimpleTTLCache 7 | from misc import get_logger 8 | from util_meta import get_gh_discuss, get_pep_text 9 | from util_openai import tokens_to_chunks, send_partial_text, summarize 10 | 11 | 12 | logger = get_logger(__name__) 13 | intents = discord.Intents.default() 14 | intents.message_content = True 15 | cache = SimpleTTLCache(100) 16 | bot = commands.Bot(command_prefix="!", intents=intents) 17 | 18 | 19 | @bot.event 20 | async def on_ready(): 21 | logger.info(f"Logged in as {bot.user.name}({bot.user.id})") 22 | 23 | 24 | @bot.command(name="ping") 25 | async def ping(ctx): 26 | await ctx.send("pong") 27 | 28 | 29 | @bot.command(name="tldr") 30 | async def tldr(ctx, target: str, number: int): 31 | requester = ctx.message.author 32 | logger.info(f"requester: {requester}, target: {target}, number: {number}") 33 | target = target.lower() 34 | if target not in ["pep", "gh"]: 35 | await ctx.send("Only supports PEP and GitHub right now.") 36 | return 37 | try: 38 | target_doc = f"{target}-{number:04d}" 39 | cached_result = cache.get(target_doc) 40 | author = ctx.message.author 41 | if cached_result: 42 | await ctx.send(f"{author.mention} Here you go:\n{cached_result}") 43 | return 44 | if target == "pep": 45 | text = await get_pep_text(target_doc) 46 | link = f"https://peps.python.org/{target_doc}" 47 | else: 48 | text = await get_gh_discuss(number) 49 | link = f"https://github.com/python/cpython/issues/{number}" 50 | 51 | encoding = tiktoken.encoding_for_model("gpt-3.5-turbo") 52 | tokens = encoding.encode(text) 53 | if len(tokens) > 3000: 54 | # If the text exceeds the allowed token limit, it can be shortened using an LLM model. 55 | responses = [] 56 | for chunk in tokens_to_chunks(tokens): 57 | decoded_text = encoding.decode(chunk) 58 | res = await send_partial_text(decoded_text, target_doc) 59 | responses.append(res) 60 | final_text = "\n".join(responses) 61 | else: 62 | # By pass to the final text if the text is allowed. 63 | final_text = text 64 | 65 | summary = await summarize(link, final_text) 66 | # Caching for 10 mins 67 | cache.put(target_doc, summary, 60 * 10) 68 | await ctx.send(f"{author.mention} Here you go:\n{summary}") 69 | except Exception as e: 70 | logger.error("An exception was thrown!", exc_info=True) 71 | await ctx.send(f"Error: {e}") 72 | 73 | 74 | if __name__ == "__main__": 75 | bot.run(DISCORD_TOKEN) 76 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | share/python-wheels/ 24 | *.egg-info/ 25 | .installed.cfg 26 | *.egg 27 | MANIFEST 28 | 29 | # PyInstaller 30 | # Usually these files are written by a python script from a template 31 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 32 | *.manifest 33 | *.spec 34 | 35 | # Installer logs 36 | pip-log.txt 37 | pip-delete-this-directory.txt 38 | 39 | # Unit test / coverage reports 40 | htmlcov/ 41 | .tox/ 42 | .nox/ 43 | .coverage 44 | .coverage.* 45 | .cache 46 | nosetests.xml 47 | coverage.xml 48 | *.cover 49 | *.py,cover 50 | .hypothesis/ 51 | .pytest_cache/ 52 | cover/ 53 | 54 | # Translations 55 | *.mo 56 | *.pot 57 | 58 | # Django stuff: 59 | *.log 60 | local_settings.py 61 | db.sqlite3 62 | db.sqlite3-journal 63 | 64 | # Flask stuff: 65 | instance/ 66 | .webassets-cache 67 | 68 | # Scrapy stuff: 69 | .scrapy 70 | 71 | # Sphinx documentation 72 | docs/_build/ 73 | 74 | # PyBuilder 75 | .pybuilder/ 76 | target/ 77 | 78 | # Jupyter Notebook 79 | .ipynb_checkpoints 80 | 81 | # IPython 82 | profile_default/ 83 | ipython_config.py 84 | 85 | # pyenv 86 | # For a library or package, you might want to ignore these files since the code is 87 | # intended to run in multiple environments; otherwise, check them in: 88 | # .python-version 89 | 90 | # pipenv 91 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 92 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 93 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 94 | # install all needed dependencies. 95 | #Pipfile.lock 96 | 97 | # poetry 98 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. 99 | # This is especially recommended for binary packages to ensure reproducibility, and is more 100 | # commonly ignored for libraries. 101 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control 102 | #poetry.lock 103 | 104 | # pdm 105 | # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. 106 | #pdm.lock 107 | # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it 108 | # in version control. 109 | # https://pdm.fming.dev/#use-with-ide 110 | .pdm.toml 111 | 112 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm 113 | __pypackages__/ 114 | 115 | # Celery stuff 116 | celerybeat-schedule 117 | celerybeat.pid 118 | 119 | # SageMath parsed files 120 | *.sage.py 121 | 122 | # Environments 123 | .env 124 | .venv 125 | env/ 126 | venv/ 127 | ENV/ 128 | env.bak/ 129 | venv.bak/ 130 | 131 | # Spyder project settings 132 | .spyderproject 133 | .spyproject 134 | 135 | # Rope project settings 136 | .ropeproject 137 | 138 | # mkdocs documentation 139 | /site 140 | 141 | # mypy 142 | .mypy_cache/ 143 | .dmypy.json 144 | dmypy.json 145 | 146 | # Pyre type checker 147 | .pyre/ 148 | 149 | # pytype static type analyzer 150 | .pytype/ 151 | 152 | # Cython debug symbols 153 | cython_debug/ 154 | 155 | # PyCharm 156 | # JetBrains specific template is maintained in a separate JetBrains.gitignore that can 157 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore 158 | # and can be added to the global gitignore or merged into this file. For a more nuclear 159 | # option (not recommended) you can uncomment the following to ignore the entire idea folder. 160 | #.idea/ 161 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | --------------------------------------------------------------------------------