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, 86 insertions, 0 deletions

diff --git a/server/continuedev/libs/llm/llamacpp.py b/server/continuedev/libs/llm/llamacpp.py
new file mode 100644
index 00000000..bc856a52
--- /dev/null
+++ b/server/continuedev/libs/llm/llamacpp.py
@@ -0,0 +1,86 @@
+import json
+from typing import Any, Callable, Dict
+
+from pydantic import Field
+
+from .base import LLM
+from .prompts.chat import llama2_template_messages
+from .prompts.edit import simplified_edit_prompt
+
+
+class LlamaCpp(LLM):
+    """
+    Run the llama.cpp server binary to start the API server. If running on a remote server, be sure to set host to 0.0.0.0:
+
+    ```shell
+    .\server.exe -c 4096 --host 0.0.0.0 -t 16 --mlock -m models\meta\llama\codellama-7b-instruct.Q8_0.gguf
+    ```
+
+    After it's up and running, change `~/.continue/config.py` to look like this:
+
+    ```python title="~/.continue/config.py"
+    from continuedev.libs.llm.llamacpp import LlamaCpp
+
+    config = ContinueConfig(
+        ...
+        models=Models(
+            default=LlamaCpp(
+                max_context_length=4096,
+                server_url="http://localhost:8080")
+        )
+    )
+    ```
+    """
+
+    model: str = "llamacpp"
+    server_url: str = Field("http://localhost:8080", description="URL of the server")
+
+    llama_cpp_args: Dict[str, Any] = Field(
+        {"stop": ["[INST]"]},
+        description="A list of additional arguments to pass to llama.cpp. See [here](https://github.com/ggerganov/llama.cpp/tree/master/examples/server#api-endpoints) for the complete catalog of options.",
+    )
+
+    template_messages: Callable = llama2_template_messages
+    prompt_templates = {
+        "edit": simplified_edit_prompt,
+    }
+
+    class Config:
+        arbitrary_types_allowed = True
+
+    def collect_args(self, options) -> Any:
+        args = super().collect_args(options)
+        if "max_tokens" in args:
+            args["n_predict"] = args["max_tokens"]
+            del args["max_tokens"]
+        if "frequency_penalty" in args:
+            del args["frequency_penalty"]
+        if "presence_penalty" in args:
+            del args["presence_penalty"]
+
+        for k, v in self.llama_cpp_args.items():
+            if k not in args:
+                args[k] = v
+
+        return args
+
+    async def _stream_complete(self, prompt, options):
+        args = self.collect_args(options)
+        headers = {"Content-Type": "application/json"}
+
+        async def server_generator():
+            async with self.create_client_session() as client_session:
+                async with client_session.post(
+                    f"{self.server_url}/completion",
+                    json={"prompt": prompt, "stream": True, **args},
+                    headers=headers,
+                    proxy=self.proxy,
+                ) as resp:
+                    async for line in resp.content:
+                        content = line.decode("utf-8")
+                        if content.strip() == "":
+                            continue
+                        yield json.loads(content[6:])["content"]
+
+        async for chunk in server_generator():
+            yield chunk