From f09150617ed2454f3074bcf93f53aae5ae637d40 Mon Sep 17 00:00:00 2001 From: Nate Sesti <33237525+sestinj@users.noreply.github.com> Date: Mon, 9 Oct 2023 18:37:27 -0700 Subject: Preview (#541) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit * Strong typing (#533) * refactor: :recycle: get rid of continuedev.src.continuedev structure * refactor: :recycle: switching back to server folder * feat: :sparkles: make config.py imports shorter * feat: :bookmark: publish as pre-release vscode extension * refactor: :recycle: refactor and add more completion params to ui * build: :building_construction: download from preview S3 * fix: :bug: fix paths * fix: :green_heart: package:pre-release * ci: :green_heart: more time for tests * fix: :green_heart: fix build scripts * fix: :bug: fix import in run.py * fix: :bookmark: update version to try again * ci: 💚 Update package.json version [skip ci] * refactor: :fire: don't check for old extensions version * fix: :bug: small bug fixes * fix: :bug: fix config.py import paths * ci: 💚 Update package.json version [skip ci] * ci: :green_heart: platform-specific builds test #1 * feat: :green_heart: ship with binary * fix: :green_heart: fix copy statement to include.exe for windows * fix: :green_heart: cd extension before packaging * chore: :loud_sound: count tokens generated * fix: :green_heart: remove npm_config_arch * fix: :green_heart: publish as pre-release! * chore: :bookmark: update version * perf: :green_heart: hardcode distro paths * fix: :bug: fix yaml syntax error * chore: :bookmark: update version * fix: :green_heart: update permissions and version * feat: :bug: kill old server if needed * feat: :lipstick: update marketplace icon for pre-release * ci: 💚 Update package.json version [skip ci] * feat: :sparkles: auto-reload for config.py * feat: :wrench: update default config.py imports * feat: :sparkles: codelens in config.py * feat: :sparkles: select model param count from UI * ci: 💚 Update package.json version [skip ci] * feat: :sparkles: more model options, ollama error handling * perf: :zap: don't show server loading immediately * fix: :bug: fixing small UI details * ci: 💚 Update package.json version [skip ci] * feat: :rocket: headers param on LLM class * fix: :bug: fix headers for openai.;y * feat: :sparkles: highlight code on cmd+shift+L * ci: 💚 Update package.json version [skip ci] * feat: :lipstick: sticky top bar in gui.tsx * fix: :loud_sound: websocket logging and horizontal scrollbar * ci: 💚 Update package.json version [skip ci] * feat: :sparkles: allow AzureOpenAI Service through GGML * ci: 💚 Update package.json version [skip ci] * fix: :bug: fix automigration * ci: 💚 Update package.json version [skip ci] * ci: :green_heart: upload binaries in ci, download apple silicon * chore: :fire: remove notes * fix: :green_heart: use curl to download binary * fix: :green_heart: set permissions on apple silicon binary * fix: :green_heart: testing * fix: :green_heart: cleanup file * fix: :green_heart: fix preview.yaml * fix: :green_heart: only upload once per binary * fix: :green_heart: install rosetta * ci: :green_heart: download binary after tests * ci: 💚 Update package.json version [skip ci] * ci: :green_heart: prepare ci for merge to main --------- Co-authored-by: GitHub Action --- server/continuedev/libs/llm/queued.py | 77 +++++++++++++++++++++++++++++++++++ 1 file changed, 77 insertions(+) create mode 100644 server/continuedev/libs/llm/queued.py (limited to 'server/continuedev/libs/llm/queued.py') diff --git a/server/continuedev/libs/llm/queued.py b/server/continuedev/libs/llm/queued.py new file mode 100644 index 00000000..2db749eb --- /dev/null +++ b/server/continuedev/libs/llm/queued.py @@ -0,0 +1,77 @@ +import asyncio +from typing import Any, List, Union + +from pydantic import Field + +from ...core.main import ChatMessage +from .base import LLM, CompletionOptions + + +class QueuedLLM(LLM): + """ + QueuedLLM exists to make up for LLM servers that cannot handle multiple requests at once. It uses a lock to ensure that only one request is being processed at a time. + + If you are already using another LLM class and are experiencing this problem, you can just wrap it with the QueuedLLM class like this: + + ```python title="~/.continue/config.py" + from continuedev.libs.llm.queued import QueuedLLM + + config = ContinueConfig( + ... + models=Models( + default=QueuedLLM(llm=) + ) + ) + ``` + """ + + llm: LLM = Field(..., description="The LLM to wrap with a lock") + _lock: asyncio.Lock + + model: str = "queued" + + def dict(self, **kwargs): + return self.llm.dict(**kwargs) + + async def start(self, *args, **kwargs): + await super().start(*args, **kwargs) + await self.llm.start(*args, **kwargs) + self._lock = asyncio.Lock() + self.model = self.llm.model + self.template_messages = self.llm.template_messages + self.prompt_templates = self.llm.prompt_templates + self.context_length = self.llm.context_length + + async def stop(self): + await self.llm.stop() + + def collect_args(self, options: CompletionOptions): + return self.llm.collect_args(options) + + def compile_chat_messages( + self, + options: CompletionOptions, + msgs: List[ChatMessage], + functions: Union[List[Any], None] = None, + ): + return self.llm.compile_chat_messages(options, msgs, functions) + + def template_prompt_like_messages(self, prompt: str) -> str: + return self.llm.template_prompt_like_messages(prompt) + + async def _complete(self, prompt: str, options: CompletionOptions): + async with self._lock: + resp = await self.llm._complete(prompt, options) + return resp + + async def _stream_complete(self, prompt: str, options: CompletionOptions): + async with self._lock: + async for chunk in self.llm._stream_complete(prompt, options): + yield chunk + + async def _stream_chat( + self, messages: List[ChatMessage], options: CompletionOptions + ): + async with self._lock: + async for chunk in self.llm._stream_chat(messages, options): + yield chunk -- cgit v1.2.3-70-g09d2