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, 114 insertions, 0 deletions

diff --git a/server/continuedev/libs/llm/text_gen_interface.py b/server/continuedev/libs/llm/text_gen_interface.py
new file mode 100644
index 00000000..225fd3b6
--- /dev/null
+++ b/server/continuedev/libs/llm/text_gen_interface.py
@@ -0,0 +1,114 @@
+import json
+from typing import Any, Callable, Dict, List, Union
+
+import websockets
+from pydantic import Field
+
+from ...core.main import ChatMessage
+from .base import LLM
+from .prompts.chat import llama2_template_messages
+from .prompts.edit import simplest_edit_prompt
+
+
+class TextGenUI(LLM):
+    """
+    TextGenUI is a comprehensive, open-source language model UI and local server. You can set it up with an OpenAI-compatible server plugin, but if for some reason that doesn't work, you can use this class like so:
+
+    ```python title="~/.continue/config.py"
+    from continuedev.libs.llm.text_gen_interface import TextGenUI
+
+    config = ContinueConfig(
+        ...
+        models=Models(
+            default=TextGenUI(
+                model="<MODEL_NAME>",
+            )
+        )
+    )
+    ```
+    """
+
+    model: str = "text-gen-ui"
+    server_url: str = Field(
+        "http://localhost:5000", description="URL of your TextGenUI server"
+    )
+    streaming_url: str = Field(
+        "http://localhost:5005",
+        description="URL of your TextGenUI streaming server (separate from main server URL)",
+    )
+
+    prompt_templates = {
+        "edit": simplest_edit_prompt,
+    }
+
+    template_messages: Union[
+        Callable[[List[Dict[str, str]]], str], None
+    ] = llama2_template_messages
+
+    class Config:
+        arbitrary_types_allowed = True
+
+    def collect_args(self, options) -> Any:
+        args = super().collect_args(options)
+        args = {**args, "max_new_tokens": options.max_tokens}
+        args.pop("max_tokens", None)
+        return args
+
+    async def _stream_complete(self, prompt, options):
+        args = self.collect_args(options)
+
+        ws_url = f"{self.streaming_url.replace('http://', 'ws://').replace('https://', 'wss://')}"
+        payload = json.dumps({"prompt": prompt, "stream": True, **args})
+        async with websockets.connect(
+            f"{ws_url}/api/v1/stream", ping_interval=None
+        ) as websocket:
+            await websocket.send(payload)
+
+            while True:
+                incoming_data = await websocket.recv()
+                incoming_data = json.loads(incoming_data)
+
+                match incoming_data["event"]:
+                    case "text_stream":
+                        yield incoming_data["text"]
+                    case "stream_end":
+                        break
+
+    async def _stream_chat(self, messages: List[ChatMessage], options):
+        args = self.collect_args(options)
+
+        async def generator():
+            ws_url = f"{self.streaming_url.replace('http://', 'ws://').replace('https://', 'wss://')}"
+            history = list(map(lambda x: x["content"], messages))
+            payload = json.dumps(
+                {
+                    "user_input": messages[-1]["content"],
+                    "history": {"internal": [history], "visible": [history]},
+                    "stream": True,
+                    **args,
+                }
+            )
+            async with websockets.connect(
+                f"{ws_url}/api/v1/chat-stream", ping_interval=None
+            ) as websocket:
+                await websocket.send(payload)
+
+                prev = ""
+                while True:
+                    incoming_data = await websocket.recv()
+                    incoming_data = json.loads(incoming_data)
+
+                    match incoming_data["event"]:
+                        case "text_stream":
+                            visible = incoming_data["history"]["visible"][-1]
+                            if len(visible) > 0:
+                                yield {
+                                    "role": "assistant",
+                                    "content": visible[-1].replace(prev, ""),
+                                }
+                                prev = visible[-1]
+                        case "stream_end":
+                            break
+
+        async for chunk in generator():
+            yield chunk