Added help text fields for embedding providers in the AI Setting page (#1288)

* Update `/learn.py` to log missing vector store

* Added help text for embeddings providers that use a registry

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Adds HF and OpenAI help for embeddings providers

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Author: srdas

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

@@ -1,4 +1,4 @@
-from typing import ClassVar, List
+from typing import ClassVar, List, Optional
 
 from jupyter_ai_magics.providers import (
     AuthStrategy,
@@ -31,6 +31,10 @@ class BaseEmbeddingsProvider(BaseModel):
     """List of supported models by their IDs. For registry providers, this will
     be just ["*"]."""
 
+    help: ClassVar[Optional[str]] = None
+    """Text to display in lieu of a model list for a registry provider that does
+    not provide a list of models."""
+
     model_id_key: ClassVar[str] = ...
     """Kwarg expected by the upstream LangChain provider."""
 
@@ -70,6 +74,10 @@ class HfHubEmbeddingsProvider(BaseEmbeddingsProvider, HuggingFaceHubEmbeddings):
     name = "Hugging Face Hub"
     models = ["*"]
     model_id_key = "repo_id"
+    help = (
+        "See [https://huggingface.co/docs/chat-ui/en/configuration/embeddings](https://huggingface.co/docs/chat-ui/en/configuration/embeddings) for reference. "
+        "Pass an embedding model's name; for example, `sentence-transformers/all-MiniLM-L6-v2`."
+    )
     # ipywidgets needed to suppress tqdm warning
     # https://stackoverflow.com/questions/67998191
     # tqdm is a dependency of huggingface_hub

packages/jupyter-ai-magics/jupyter_ai_magics/partner_providers/ollama.py

@@ -24,6 +24,10 @@ class OllamaEmbeddingsProvider(BaseEmbeddingsProvider, OllamaEmbeddings):
     name = "Ollama"
     # source: https://ollama.com/library
     model_id_key = "model"
+    help = (
+        "See [https://ollama.com/search?c=embedding](https://ollama.com/search?c=embedding) for a list of models. "
+        "Pass an embedding model's name; for example, `mxbai-embed-large`."
+    )
     models = ["*"]
     registry = True
     fields = [

packages/jupyter-ai-magics/jupyter_ai_magics/partner_providers/openai.py

@@ -93,7 +93,7 @@ class ChatOpenAICustomProvider(BaseProvider, ChatOpenAI):
         ),
         TextField(key="openai_proxy", label="Proxy (optional)", format="text"),
     ]
-    help = "Supports non-OpenAI model that use the OpenAI API interface. Replace the OpenAI API key with the API key for the chosen provider."
+    help = "Supports non-OpenAI models that use the OpenAI API interface. Replace the OpenAI API key with the API key for the chosen provider."
     registry = True
 
 
@@ -143,6 +143,7 @@ class OpenAIEmbeddingsCustomProvider(BaseEmbeddingsProvider, OpenAIEmbeddings):
             key="openai_api_base", label="Base API URL (optional)", format="text"
         ),
     ]
+    help = "Supports non-OpenAI embedding models that use the OpenAI API interface. Replace the OpenAI API key with the API key for the chosen provider."
 
 
 class AzureOpenAIEmbeddingsProvider(BaseEmbeddingsProvider, AzureOpenAIEmbeddings):

packages/jupyter-ai/jupyter_ai/handlers.py

@@ -140,6 +140,7 @@ def get(self):
                     id=provider.id,
                     name=provider.name,
                     models=provider.models,
+                    help=provider.help,
                     auth_strategy=provider.auth_strategy,
                     registry=provider.registry,
                     fields=provider.fields,