Spell checking automation + fix typos (microsoft#977)

dluc · web-flow · commit fd1e0146184e · 2023-05-12T20:04:16.000Z
Spell checking automation: * Add typos checker to PR flow using https://github.com/marketplace/actions/typos-action * Fix existing typos * Add config file, with exclusions and exceptions: `.github/_typos.toml` The checker can be run locally, e.g. * Install: `brew install typos-cli` * Install: `conda install typos` Run: `typos -c .github/_typos.toml`
diff --git a/.github/_typos.toml b/.github/_typos.toml
@@ -0,0 +1,21 @@
+# Typos configuration file
+#
+# Info:    https://github.com/marketplace/actions/typos-action
+# Install: brew install typos-cli
+# Install: conda install typos
+# Run:     typos -c .github/_typos.toml
+
+[files]
+extend-exclude = [
+    "_typos.toml",
+    "package-lock.json",
+    "*.bicep",
+    "encoder.json",
+    "vocab.bpe",
+    "GPT3TokenizerTests.cs",
+    "CodeTokenizerTests.cs",
+    "test_code_tokenizer.py",
+]
+
+[default.extend-words]
+ACI = "ACI" # Azure Container Instance
diff --git a/.github/workflows/typos.yaml b/.github/workflows/typos.yaml
@@ -0,0 +1,29 @@
+# Check pull requests for typos.
+#
+# Configuration: .github/_typos.toml
+#
+# Info:          https://github.com/marketplace/actions/typos-action
+# Local install: brew install typos-cli
+# Local install: conda install typos
+# Local run:     typos -c .github/_typos.toml
+
+name: Spell Check
+
+on:
+  workflow_dispatch:
+  pull_request:
+    branches: [ "main", "feature*" ]
+
+jobs:
+  run:
+    name: Spell Check with Typos
+    runs-on: ubuntu-latest
+    steps:
+    - name: Check out code
+      uses: actions/checkout@v3
+
+    - name: Use custom config file
+      uses: crate-ci/typos@master
+      with:
+        config: .github/_typos.toml
+        write_changes: false
diff --git a/dotnet/src/Connectors/Connectors.AI.OpenAI/Tokenizers/GPT3Tokenizer.cs b/dotnet/src/Connectors/Connectors.AI.OpenAI/Tokenizers/GPT3Tokenizer.cs
@@ -92,7 +92,7 @@ public static List<int> Encode(string text)
                 }
             }
 
-            // Ensure we have a sufficient Span<char> buffer to accomodate maxUtf8Length chars.
+            // Ensure we have a sufficient Span<char> buffer to accommodate maxUtf8Length chars.
             // The byte-to-char mapping scheme employed is 1:1, so we'll end up needing 1 char
             // for every 1 UTF8 byte. If we can reasonably stack-allocate the space, we do, otherwise
             // we temporarily rent a pooled array.
diff --git a/dotnet/src/IntegrationTests/README.md b/dotnet/src/IntegrationTests/README.md
@@ -6,7 +6,7 @@
    and deploy an instance of Azure OpenAI, deploy a model like "text-davinci-003" find your Endpoint and API key.
 2. **OpenAI**: go to [OpenAI](https://openai.com/api/) to register and procure your API key.
 3. **HuggingFace API key**: see https://huggingface.co/docs/huggingface_hub/guides/inference for details.
-4. **Azure Bing Web Search API**: go to [Bing Web Seach API](https://www.microsoft.com/en-us/bing/apis/bing-web-search-api)
+4. **Azure Bing Web Search API**: go to [Bing Web Search API](https://www.microsoft.com/en-us/bing/apis/bing-web-search-api)
    and select `Try Now` to get started.
 
 ## Setup
diff --git a/dotnet/src/SemanticKernel.Abstractions/SemanticKernel.Abstractions.csproj b/dotnet/src/SemanticKernel.Abstractions/SemanticKernel.Abstractions.csproj
@@ -16,7 +16,7 @@
   </PropertyGroup>
 
   <ItemGroup>
-    <!--Setting version overrides to miniumum supported version, to maximize compatability.-->
+    <!--Setting version overrides to minimum supported version, to maximize compatibility.-->
     <PackageReference Include="Microsoft.Bcl.HashCode" VersionOverride="[1.1.0, )" />
     <PackageReference Include="Microsoft.Extensions.Logging" VersionOverride="[6.0.0, )" />
     <PackageReference Include="System.Linq.Async" VersionOverride="[6.0.1, )" />
diff --git a/python/semantic_kernel/text/text_chunker.py b/python/semantic_kernel/text/text_chunker.py
@@ -224,7 +224,7 @@ def _split_list(
     text: List[str], max_tokens: int, separators: List[str], trim: bool
 ) -> List[str]:
     """
-    Split list of sring into lines.
+    Split list of string into lines.
     """
     if not text:
         return []
diff --git a/python/tests/unit/text/test_text_chunker.py b/python/tests/unit/text/test_text_chunker.py
@@ -319,9 +319,9 @@ def test_split_paragraph_spaces():
     assert expected == split
 
 
-def test_split_paragraph_hypens():
+def test_split_paragraph_hyphens():
     """
-    a plaintext example that splits on hypens
+    a plaintext example that splits on hyphens
     """
     text = [
         "This is a test of the emergency broadcast system-This is only a test",
diff --git a/samples/apps/book-creator-webapp-react/src/components/TaskButton.tsx b/samples/apps/book-creator-webapp-react/src/components/TaskButton.tsx
@@ -34,7 +34,7 @@ const TaskButton: FC<IData> = ({
     uri,
     skills,
 }) => {
-    const maxSteps = 10; //this is the maximum number of iterations planner will take while attemping to solve
+    const maxSteps = 10; //this is the maximum number of iterations planner will take while attempting to solve
     const sk = useSemanticKernel(uri);
     const taskRunner = useTaskRunner(sk, keyConfig, maxSteps);
     const [isBusy, setIsBusy] = useState<boolean>(false);
diff --git a/samples/apps/copilot-chat-app/README.md b/samples/apps/copilot-chat-app/README.md
@@ -114,7 +114,7 @@ The WebApp can display this error when the application is configured for an acti
 
 ## 2. Issues using text completion models, such as `text-davinci-003`
 CopilotChat supports chat completion models, such as `gpt-3.5-*` and `gpt-4-*`.
-See [OpenAI's model compatiblity](https://platform.openai.com/docs/models/model-endpoint-compatibility) for
+See [OpenAI's model compatibility](https://platform.openai.com/docs/models/model-endpoint-compatibility) for
 the complete list of current models supporting chat completions.
 
 ## 3. Localhost SSL certificate errors
diff --git a/samples/apps/copilot-chat-app/webapi/Skills/OpenApiSkills/JiraSkill/openapi.json b/samples/apps/copilot-chat-app/webapi/Skills/OpenApiSkills/JiraSkill/openapi.json
@@ -391,7 +391,7 @@
                 },
                 "name": {
                   "type": "string",
-                  "x-ms-summary": "Name fo the issue resolution"
+                  "x-ms-summary": "Name of the issue resolution"
                 }
               },
               "x-ms-summary": "Resolution",
diff --git a/samples/apps/copilot-chat-app/webapi/appsettings.json b/samples/apps/copilot-chat-app/webapi/appsettings.json
@@ -1,12 +1,12 @@
 //
 // # CopilotChat Application Settings
-// 
+//
 // # Quickstart
 //  - Update the "Completion" and "Embedding" sections below to use your AI services.
-// 
+//
 // # Secrets
 // Consider populating secrets, such as "Key" and "ConnectionString" properties, from dotnet's user-secrets when running locally.
-// https://learn.microsoft.com/en-us/aspnet/core/security/app-secrets?view=aspnetcore-7.0&tabs=windows#secret-manager       
+// https://learn.microsoft.com/en-us/aspnet/core/security/app-secrets?view=aspnetcore-7.0&tabs=windows#secret-manager
 // Values in user secrets and (optionally) Key Vault take precedence over those in this file.
 //
 {
@@ -28,7 +28,7 @@
   //  - Set "DeploymentOrModelId" to the name of the deployment to use (e.g., "gpt-35-turbo", "gpt-4", etc.)
   //  - Set "Endpoint" to the endpoint of your Azure OpenAI instance (e.g., "https://contoso.openai.azure.com")
   //  - Set "Key" using dotnet's user secrets (see above) (i.e. dotnet user-secrets set "Completion:Key" "MY_AZURE_OPENAI_KEY")
-  // 
+  //
   // To use OpenAI as the AI completion service:
   //  - Set "AIService" to "OpenAI"
   //  - Set "DeploymentOrModelId" to the name of the deployment to use (e.g., "gpt-3.5-turbo", "gpt-4", etc.)
@@ -51,7 +51,7 @@
   //  - Set "DeploymentOrModelId" to the name of the deployment to use (e.g., "text-embedding-ada-002")
   //  - Set "Endpoint" to the endpoint of your Azure OpenAI instance (e.g., "https://contoso.openai.azure.com")
   //  - Set "Key" using dotnet's user secrets (see above) (i.e. dotnet user-secrets set "Embedding:Key" "MY_AZURE_OPENAI_KEY")
-  // 
+  //
   // To use OpenAI as the AI embedding service:
   //  - Set "AIService" to "OpenAI"
   //  - Set "DeploymentOrModelId" to the name of the deployment to use (e.g., "text-embedding-ada-002" )
@@ -69,7 +69,7 @@
   // Optional Azure Speech service configuration for providing Azure Speech access tokens.
   // - Set the Region to the region of your Azure Speech resource (e.g., "westus").
   // - Set the Key using dotnet's user secrets (see above) (i.e. dotnet user-secrets set "AzureSpeech:Key" "MY_AZURE_SPEECH_KEY")
-  // 
+  //
   "AzureSpeech": {
     "Region": ""
     // "Key": ""
@@ -112,7 +112,7 @@
   // Memories stores are used for storing new memories and retrieving semantically similar memories.
   // - Supported Types are "volatile", "qdrant", or "azurecognitivesearch".
   // - When using Qdrant or Azure Cognitive Search, see ./README.md for deployment instructions.
-  // - The "Semantic Search" feature must be enabled on Azure Cognitive Search. 
+  // - The "Semantic Search" feature must be enabled on Azure Cognitive Search.
   // - The Embedding configuration above will not be used when Azure Cognitive Search is selected.
   //
   "MemoriesStore": {
@@ -146,7 +146,7 @@
   },
 
   //
-  // Planner can determine which skill functions, if any, need to be used to fullfill a user's request.
+  // Planner can determine which skill functions, if any, need to be used to fulfill a user's request.
   // https://learn.microsoft.com/en-us/semantic-kernel/concepts-sk/planner
   // - Set Enabled to false to disable the planner which can save a round-trip to the AI service but will disable plug-in support.
   //
diff --git a/samples/apps/copilot-chat-app/webapp/src/components/open-api-plugins/PluginConnector.tsx b/samples/apps/copilot-chat-app/webapp/src/components/open-api-plugins/PluginConnector.tsx
@@ -74,7 +74,7 @@ export const PluginConnector: React.FC<PluginConnectorProps> = ({
     const [username, setUsername] = useState('');
     const [password, setPassword] = useState('');
     const [accessToken, setAccessToken] = useState('');
-    const [apiPropertiesInput, setApiRequirmentsInput] = useState(apiProperties);
+    const [apiPropertiesInput, setApiRequirementsInput] = useState(apiProperties);
 
     const [open, setOpen] = useState(false);
     const [errorMessage, setErrorMessage] = useState<string | undefined>();
@@ -237,7 +237,7 @@ export const PluginConnector: React.FC<PluginConnectorProps> = ({
                                                     type="text"
                                                     id={'plugin-additional-info' + property}
                                                     onChange={(_e, input) => {
-                                                        setApiRequirmentsInput({
+                                                        setApiRequirementsInput({
                                                             ...apiPropertiesInput,
                                                             [property]: {
                                                                 ...propertyDetails,
diff --git a/samples/dotnet/kernel-syntax-examples/Example13_ConversationSummarySkill.cs b/samples/dotnet/kernel-syntax-examples/Example13_ConversationSummarySkill.cs
@@ -38,7 +38,7 @@ internal static class Example13_ConversationSummarySkill
 Jane: What about you?
 John: That's cool. Let me see if mine will write a poem, too.
 John: Here's a poem my chatbot wrote:
-John: The signularity of the universe is a mystery.
+John: The singularity of the universe is a mystery.
 John: The universe is a mystery.
 John: The universe is a mystery.
 John: The universe is a mystery.
diff --git a/samples/dotnet/kernel-syntax-examples/Skills/JiraSkill/openapi.json b/samples/dotnet/kernel-syntax-examples/Skills/JiraSkill/openapi.json
@@ -462,7 +462,7 @@
                 },
                 "name": {
                   "type": "string",
-                  "x-ms-summary": "Name fo the issue resolution"
+                  "x-ms-summary": "Name of the issue resolution"
                 }
               },
               "x-ms-summary": "Resolution",
diff --git a/samples/notebooks/dotnet/05-using-the-planner.ipynb b/samples/notebooks/dotnet/05-using-the-planner.ipynb
@@ -135,7 +135,7 @@
    "source": [
     "As you can see in the above plan, the Planner has taken the user's ask and converted it into an XML-based plan detailing how the AI would go about solving this task.\n",
     "\n",
-    "It makes use of the skills that the Kernel has available to it and determines which functions to call in order to fullfill the user's ask.\n",
+    "It makes use of the skills that the Kernel has available to it and determines which functions to call in order to fulfill the user's ask.\n",
     "\n",
     "The output of each step of the plan gets set as `setContextVariable` which makes it available as `input` to the next skill."
    ]
diff --git a/samples/notebooks/dotnet/07-DALL-E-2.ipynb b/samples/notebooks/dotnet/07-DALL-E-2.ipynb
@@ -7,7 +7,7 @@
    "source": [
     "# Generating images with AI\n",
     "\n",
-    "This notebook demonstrates how to use OpenAI DALL-E 2 to generate images, in combination with ther LLM features like text and embedding generation.\n",
+    "This notebook demonstrates how to use OpenAI DALL-E 2 to generate images, in combination with other LLM features like text and embedding generation.\n",
     "\n",
     "Here, we use Text Generation to generate a random image description and DALL-E 2 to create an image from that description, showing the image inline.\n",
     "\n",
diff --git a/samples/notebooks/dotnet/08-chatGPT-with-DALL-E-2.ipynb b/samples/notebooks/dotnet/08-chatGPT-with-DALL-E-2.ipynb
@@ -24,7 +24,7 @@
     "2. User messages store the data received from the user of your app.\n",
     "3. Assistant messages store the replies generated by the LLM model. \n",
     "\n",
-    "Your app is reponsible for adding information to the chat history and maintaining this object. The Chat Completion API is stateless, and returns only new messages, that your app can use, e.g. to execute commands, generate images, or simply continue the conversation."
+    "Your app is responsible for adding information to the chat history and maintaining this object. The Chat Completion API is stateless, and returns only new messages, that your app can use, e.g. to execute commands, generate images, or simply continue the conversation."
    ]
   },
   {
diff --git a/samples/notebooks/python/05-using-the-planner.ipynb b/samples/notebooks/python/05-using-the-planner.ipynb
@@ -55,7 +55,7 @@
    "metadata": {},
    "source": [
     "### Setting Up the Planner\n",
-    "Here we will be using a BasicPlanner that will create a sequential plan to be evaluated in order. The ouput of a function becomes the inputs of the next function. "
+    "Here we will be using a BasicPlanner that will create a sequential plan to be evaluated in order. The output of a function becomes the inputs of the next function. "
    ]
   },
   {
diff --git a/samples/notebooks/python/07-hugging-face-for-skills.ipynb b/samples/notebooks/python/07-hugging-face-for-skills.ipynb
@@ -45,7 +45,7 @@
    "source": [
     "First, we will create a kernel and add both text completion and embedding services. \n",
     "\n",
-    "For text completion, we are chosing gp2. This is a text-generation model. (Note: text-generation will repeat the input in the output, text2text-generation will not.)\n",
+    "For text completion, we are choosing GPT2. This is a text-generation model. (Note: text-generation will repeat the input in the output, text2text-generation will not.)\n",
     "For embeddings, we are using sentence-transformers/all-MiniLM-L6-v2. Vectors generated for this model are of length 384 (compared to a length of 1536 from OpenAI ADA).\n",
     "\n",
     "The following step may take a few minutes when run for the first time as the models will be downloaded to your local machine."
@@ -79,7 +79,7 @@
    "source": [
     "### Add Memories and Define a skill to use them\n",
     "\n",
-    "Most models available on huggingface.co are not as powerful as OpenAI GPT-3+. Your skills will likely need to be simpler to accomodate this."
+    "Most models available on huggingface.co are not as powerful as OpenAI GPT-3+. Your skills will likely need to be simpler to accommodate this."
    ]
   },
   {

Original file line number	Diff line number	Diff line change
`@@ -92,7 +92,7 @@ public static List<int> Encode(string text)`
`92`	`92`	`}`
`93`	`93`	`}`
`94`	`94`
`95`		`- // Ensure we have a sufficient Span<char> buffer to accomodate maxUtf8Length chars.`
	`95`	`+ // Ensure we have a sufficient Span<char> buffer to accommodate maxUtf8Length chars.`
`96`	`96`	`// The byte-to-char mapping scheme employed is 1:1, so we'll end up needing 1 char`
`97`	`97`	`// for every 1 UTF8 byte. If we can reasonably stack-allocate the space, we do, otherwise`
`98`	`98`	`// we temporarily rent a pooled array.`
Original file line number	Diff line number	Diff line change
`@@ -391,7 +391,7 @@`
`391`	`391`	`},`
`392`	`392`	`"name": {`
`393`	`393`	`"type": "string",`
`394`		`- "x-ms-summary": "Name fo the issue resolution"`
	`394`	`+ "x-ms-summary": "Name of the issue resolution"`
`395`	`395`	`}`
`396`	`396`	`},`
`397`	`397`	`"x-ms-summary": "Resolution",`