Merge pull request #1 from dlqqq/local-providers-dlqqq

Fix build and add user documentation

docs/source/users/index.md

@@ -219,7 +219,7 @@ The chat backend remembers the last two exchanges in your conversation and passe
     alt='Screen shot of an example follow up question sent to Jupyternaut, who responds with the improved code and explanation.'
     class="screenshot" />
 
-### Using the chat interface with SageMaker endpoints
+### SageMaker endpoints usage
 
 Jupyter AI supports language models hosted on SageMaker endpoints that use JSON
 schemas. The first step is to authenticate with AWS via the `boto3` SDK and have
@@ -255,6 +255,37 @@ response.  In this example, the endpoint returns an object with the schema
 `{"generated_texts":["<output>"]}`, hence the response path is
 `generated_texts.[0]`.
 
+### GPT4All usage (early-stage)
+
+Currently, we offer experimental support for GPT4All. To get started, first
+decide which models you will use. We currently offer three models from GPT4All:
+
+| Model name                   | Model size | Model bin URL                                              |
+|------------------------------|------------|------------------------------------------------------------|
+| `ggml-gpt4all-l13b-snoozy`   | 7.6 GB     | `http://gpt4all.io/models/ggml-gpt4all-l13b-snoozy.bin`    |
+| `ggml-gpt4all-j-v1.2-jazzy`  | 3.8 GB     | `https://gpt4all.io/models/ggml-gpt4all-j-v1.2-jazzy.bin`  |
+| `ggml-gpt4all-j-v1.3-groovy` | 3.8 GB     | `https://gpt4all.io/models/ggml-gpt4all-j-v1.3-groovy.bin` |
+
+
+Note that each model comes with its own license, and that users are themselves
+responsible for verifying that their usage complies with the license. You can
+find licensing details on the [GPT4All official site](https://gpt4all.io/index.html).
+
+For each model you use, you will have to run the command
+
+```
+curl -LO --output-dir ~/.cache/gpt4all "<model-bin-url>"
+```
+
+, where `<model-bin-url>` should be substituted with the corresponding URL
+hosting the model binary (within the double quotes). After restarting the
+server, the GPT4All models installed in the previous step should be available to
+use in the chat interface.
+
+GPT4All support is still an early-stage feature, so some bugs may be encountered
+during usage. Our team is still actively improving support for locally-hosted
+models.
+
 ### Asking about something in your notebook
 
 Jupyter AI's chat interface can include a portion of your notebook in your prompt.

packages/jupyter-ai-magics/jupyter_ai_magics/providers.py

@@ -225,7 +225,10 @@ def __init__(self, **kwargs):
     model_id_key = "model"
     pypi_package_deps = ["gpt4all"]
     auth_strategy = None
-    fields = [IntegerField(key="n_threads", label="Threads")]
+    fields = [IntegerField(key="n_threads", label="CPU thread count (optional)")]
+
+    async def _acall(self, *args, **kwargs) -> Coroutine[Any, Any, str]:
+        return await self._call_in_executor(*args, **kwargs)
 
 
 HUGGINGFACE_HUB_VALID_TASKS = (

packages/jupyter-ai-magics/pyproject.toml

@@ -24,7 +24,7 @@ dependencies = [
     "ipython",
     "pydantic",
     "importlib_metadata~=5.2.0",
-    "langchain==0.0.220",
+    "langchain==0.0.223",
     "typing_extensions==4.5.0",
     "click~=8.0",
     "jsonpath-ng~=1.5.3",

packages/jupyter-ai/pyproject.toml

@@ -28,7 +28,7 @@ dependencies = [
     "openai~=0.26",
     "aiosqlite~=0.18",
     "importlib_metadata~=5.2.0",
-    "langchain==0.0.220",
+    "langchain==0.0.223",
     "tiktoken", # required for OpenAIEmbeddings
     "jupyter_ai_magics",
     "dask[distributed]",

packages/jupyter-ai/src/components/settings/model-fields.tsx

@@ -18,6 +18,10 @@ export function ModelField(props: ModelFieldProps): JSX.Element {
   function handleChange(
     e: React.ChangeEvent<HTMLInputElement | HTMLTextAreaElement>
   ) {
+    if (!('format' in props.field)) {
+      return;
+    }
+
     // Perform validation based on the field format
     switch (props.field.format) {
       case 'json':