Preview (#541)

* 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 <action@github.com>

1 files changed, 108 insertions, 0 deletions

diff --git a/server/continuedev/libs/llm/proxy_server.py b/server/continuedev/libs/llm/proxy_server.py
new file mode 100644
index 00000000..7c3462eb
--- /dev/null
+++ b/server/continuedev/libs/llm/proxy_server.py
@@ -0,0 +1,108 @@
+import json
+import traceback
+from typing import List
+
+import aiohttp
+
+from ...core.main import ChatMessage
+from ..util.telemetry import posthog_logger
+from .base import LLM
+
+# SERVER_URL = "http://127.0.0.1:8080"
+SERVER_URL = "https://proxy-server-l6vsfbzhba-uw.a.run.app"
+
+MAX_TOKENS_FOR_MODEL = {
+    "gpt-3.5-turbo": 4096,
+    "gpt-3.5-turbo-0613": 4096,
+    "gpt-3.5-turbo-16k": 16384,
+    "gpt-4": 8192,
+}
+
+
+class ProxyServer(LLM):
+    _client_session: aiohttp.ClientSession
+
+    class Config:
+        arbitrary_types_allowed = True
+
+    async def start(
+        self,
+        **kwargs,
+    ):
+        await super().start(**kwargs)
+        self._client_session = self.create_client_session()
+
+        self.context_length = MAX_TOKENS_FOR_MODEL[self.model]
+
+    async def stop(self):
+        await self._client_session.close()
+
+    def get_headers(self):
+        return {"unique_id": self.unique_id}
+
+    async def _complete(self, prompt: str, options):
+        args = self.collect_args(options)
+
+        async with self._client_session.post(
+            f"{SERVER_URL}/complete",
+            json={"messages": [{"role": "user", "content": prompt}], **args},
+            headers=self.get_headers(),
+            proxy=self.proxy,
+        ) as resp:
+            resp_text = await resp.text()
+            if resp.status != 200:
+                raise Exception(resp_text)
+
+            return resp_text
+
+    async def _stream_chat(self, messages: List[ChatMessage], options):
+        args = self.collect_args(options)
+        async with self._client_session.post(
+            f"{SERVER_URL}/stream_chat",
+            json={"messages": messages, **args},
+            headers=self.get_headers(),
+            proxy=self.proxy,
+        ) as resp:
+            if resp.status != 200:
+                raise Exception(await resp.text())
+
+            async for line in resp.content.iter_chunks():
+                if line[1]:
+                    try:
+                        json_chunk = line[0].decode("utf-8")
+                        json_chunk = "{}" if json_chunk == "" else json_chunk
+                        chunks = json_chunk.split("\n")
+                        for chunk in chunks:
+                            if chunk.strip() != "":
+                                loaded_chunk = json.loads(chunk)
+                                yield loaded_chunk
+
+                    except Exception as e:
+                        posthog_logger.capture_event(
+                            "proxy_server_parse_error",
+                            {
+                                "error_title": "Proxy server stream_chat parsing failed",
+                                "error_message": "\n".join(
+                                    traceback.format_exception(e)
+                                ),
+                            },
+                        )
+                else:
+                    break
+
+    async def _stream_complete(self, prompt, options):
+        args = self.collect_args(options)
+
+        async with self._client_session.post(
+            f"{SERVER_URL}/stream_complete",
+            json={"messages": [{"role": "user", "content": prompt}], **args},
+            headers=self.get_headers(),
+            proxy=self.proxy,
+        ) as resp:
+            if resp.status != 200:
+                raise Exception(await resp.text())
+
+            async for line in resp.content.iter_any():
+                if line:
+                    decoded_line = line.decode("utf-8")
+                    yield decoded_line