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, 78 insertions, 0 deletions

diff --git a/server/continuedev/libs/llm/replicate.py b/server/continuedev/libs/llm/replicate.py
new file mode 100644
index 00000000..3423193b
--- /dev/null
+++ b/server/continuedev/libs/llm/replicate.py
@@ -0,0 +1,78 @@
+import concurrent.futures
+from typing import List
+
+import replicate
+from pydantic import Field
+
+from ...core.main import ChatMessage
+from .base import LLM
+from .prompts.edit import simplified_edit_prompt
+
+
+class ReplicateLLM(LLM):
+    """
+    Replicate is a great option for newly released language models or models that you've deployed through their platform. Sign up for an account [here](https://replicate.ai/), copy your API key, and then select any model from the [Replicate Streaming List](https://replicate.com/collections/streaming-language-models). Change `~/.continue/config.py` to look like this:
+
+    ```python title="~/.continue/config.py"
+    from continuedev.core.models import Models
+    from continuedev.libs.llm.replicate import ReplicateLLM
+
+    config = ContinueConfig(
+        ...
+        models=Models(
+            default=ReplicateLLM(
+                model="replicate/codellama-13b-instruct:da5676342de1a5a335b848383af297f592b816b950a43d251a0a9edd0113604b",
+                api_key="my-replicate-api-key")
+        )
+    )
+    ```
+
+    If you don't specify the `model` parameter, it will default to `replicate/llama-2-70b-chat:58d078176e02c219e11eb4da5a02a7830a283b14cf8f94537af893ccff5ee781`.
+    """
+
+    api_key: str = Field(..., description="Replicate API key")
+
+    model: str = "replicate/llama-2-70b-chat:58d078176e02c219e11eb4da5a02a7830a283b14cf8f94537af893ccff5ee781"
+
+    _client: replicate.Client = None
+
+    prompt_templates = {
+        "edit": simplified_edit_prompt,
+    }
+
+    async def start(self, **kwargs):
+        await super().start(**kwargs)
+        self._client = replicate.Client(api_token=self.api_key)
+
+    async def _complete(self, prompt: str, options):
+        def helper():
+            output = self._client.run(
+                self.model, input={"message": prompt, "prompt": prompt}
+            )
+            completion = ""
+            for item in output:
+                completion += item
+
+            return completion
+
+        with concurrent.futures.ThreadPoolExecutor() as executor:
+            future = executor.submit(helper)
+            completion = future.result()
+
+        return completion
+
+    async def _stream_complete(self, prompt, options):
+        for item in self._client.run(
+            self.model, input={"message": prompt, "prompt": prompt}
+        ):
+            yield item
+
+    async def _stream_chat(self, messages: List[ChatMessage], options):
+        for item in self._client.run(
+            self.model,
+            input={
+                "message": messages[-1]["content"],
+                "prompt": messages[-1]["content"],
+            },
+        ):
+            yield {"content": item, "role": "assistant"}