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, 139 insertions, 0 deletions

diff --git a/server/tests/util/openai_mock.py b/server/tests/util/openai_mock.py
new file mode 100644
index 00000000..763c5647
--- /dev/null
+++ b/server/tests/util/openai_mock.py
@@ -0,0 +1,139 @@
+import asyncio
+import os
+import random
+import subprocess
+from typing import Dict, List, Optional
+
+from fastapi import FastAPI
+from fastapi.responses import StreamingResponse
+from pydantic import BaseModel
+
+openai = FastAPI()
+
+
+class CompletionBody(BaseModel):
+    prompt: str
+    max_tokens: Optional[int] = 60
+    stream: Optional[bool] = False
+
+    class Config:
+        extra = "allow"
+
+
+@openai.post("/completions")
+@openai.post("/v1/completions")
+async def mock_completion(item: CompletionBody):
+    prompt = item.prompt
+
+    text = "This is a fake completion."
+
+    if item.stream:
+
+        async def stream_text():
+            for i in range(len(text)):
+                word = random.choice(prompt.split())
+                yield {
+                    "choices": [
+                        {
+                            "delta": {"role": "assistant", "content": word},
+                            "finish_reason": None,
+                            "index": 0,
+                        }
+                    ],
+                    "created": 1677825464,
+                    "id": "chatcmpl-6ptKyqKOGXZT6iQnqiXAH8adNLUzD",
+                    "model": "gpt-3.5-turbo-0301",
+                    "object": "chat.completion.chunk",
+                }
+                await asyncio.sleep(0.1)
+
+        return StreamingResponse(stream_text(), media_type="text/plain")
+
+    return {
+        "id": "cmpl-uqkvlQyYK7bGYrRHQ0eXlWi7",
+        "object": "text_completion",
+        "created": 1589478378,
+        "model": "gpt-3.5-turbo",
+        "choices": [
+            {
+                "text": text,
+                "index": 0,
+                "logprobs": None,
+                "finish_reason": "length",
+            }
+        ],
+        "usage": {"prompt_tokens": 5, "completion_tokens": 7, "total_tokens": 12},
+    }
+
+
+class ChatBody(BaseModel):
+    messages: List[Dict[str, str]]
+    max_tokens: Optional[int] = None
+    stream: Optional[bool] = False
+
+    class Config:
+        extra = "allow"
+
+
+@openai.post("/v1/chat/completions")
+async def mock_chat_completion(item: ChatBody):
+    text = "This is a fake completion."
+
+    if item.stream:
+
+        async def stream_text():
+            for i in range(len(text)):
+                word = text[i]
+                yield {
+                    "choices": [
+                        {
+                            "delta": {"role": "assistant", "content": word},
+                            "finish_reason": None,
+                            "index": 0,
+                        }
+                    ],
+                    "created": 1677825464,
+                    "id": "chatcmpl-6ptKyqKOGXZT6iQnqiXAH8adNLUzD",
+                    "model": "gpt-3.5-turbo-0301",
+                    "object": "chat.completion.chunk",
+                }
+                await asyncio.sleep(0.1)
+
+        return StreamingResponse(stream_text(), media_type="text/plain")
+
+    return {
+        "id": "chatcmpl-123",
+        "object": "chat.completion",
+        "created": 1677652288,
+        "model": "gpt-3.5-turbo-0613",
+        "choices": [
+            {
+                "index": 0,
+                "message": {
+                    "role": "assistant",
+                    "content": text,
+                },
+                "finish_reason": "stop",
+            }
+        ],
+        "usage": {"prompt_tokens": 9, "completion_tokens": 12, "total_tokens": 21},
+    }
+
+
+def start_openai(port: int = 8000):
+    server = subprocess.Popen(
+        [
+            "uvicorn",
+            "openai_mock:openai",
+            "--host",
+            "127.0.0.1",
+            "--port",
+            str(port),
+        ],
+        cwd=os.path.dirname(__file__),
+    )
+    return server
+
+
+if __name__ == "__main__":
+    start_openai()