review feedback

harjotgill · harjotgill · commit 6a91e80fc130 · 2024-03-16T20:15:29.000-07:00
diff --git a/blog/ai-code-reviews-reclaims-2023-10-05/blog.md b/blog/ai-code-reviews-reclaims-2023-10-05/blog.md
@@ -161,9 +161,9 @@ elsewhere.
 
 This isn't just about shipping faster—although who doesn't want to do that? It's
 also about optimizing your team's time so they can focus on what they do best:
-create amazing software. If an AI code review tool can handle the initial pass,
-highlighting potential issues with the code, the developer can resolve initial
-feedback faster and your human experts can spend their time solving more
+create remarkable software. If an AI code review tool can handle the initial
+pass, highlighting potential issues with the code, the developer can resolve
+initial feedback faster and your human experts can spend their time solving more
 complex, higher-level problems.
 
 In the next section, we'll understand how AI-powered code reviewers offer a more
diff --git a/blog/boosting-engineering-efficiency-2023-11-13/blog.md b/blog/boosting-engineering-efficiency-2023-11-13/blog.md
@@ -28,11 +28,6 @@ reliable friend who never sleeps (because they're code) and knows all the coding
 rules. This article explores how these intelligent bots fill the gaps in our
 fast-paced, sometimes slow, new world.
 
-```mdx-code-block
-import Tabs from '@theme/Tabs';
-import TabItem from '@theme/TabItem';
-```
-
 <!--truncate-->
 
 ## Direct Correlation: Remote Engineering Challenges & AI Solutions
diff --git a/blog/coderabbit-deep-dive-2023-08-26/blog.md b/blog/coderabbit-deep-dive-2023-08-26/blog.md
@@ -92,7 +92,7 @@ reviewer to ensure code quality. It goes beyond existing linters and static code
 analysis tools in uncovering issues and suggesting improvements by providing a
 human-like understanding of the objective of the code.
 
-With CodeRabbit, developers get context aware feedback within minutes, which
+With CodeRabbit, developers get context-aware feedback within minutes, which
 enables them to make improvements based on best practices and get their code
 ready to be merged faster. CodeRabbit also helps reviewers by providing them
 with confidence and speed to approve the code faster. Reviewers can use
@@ -135,7 +135,7 @@ context of the pull request and changes across multiple files. Below is a
 glimpse into the challenges we faced and the solutions we came up with:
 
 **Context window size:** The LLM models have limited context windows, for
-instance,`gpt-3.5-turbo` has a context window of 4K or 16K tokens and `gpt-4`
+instance, `gpt-3.5-turbo` has a context window of 4K or 16K tokens and `gpt-4`
 has a context window of 8K tokens. This is often insufficient to pack larger
 change sets. To circumvent this, we provide various summaries while reviewing
 changes to each file and by smartly prioritizing context that is packed in each
@@ -155,15 +155,14 @@ the noise.
 
 **Costs:** While advanced models like `gpt-4` are great in performing complex
 tasks, they are several orders of magnitude more expensive than models like
-`gpt-3.5-turbo`. We had to design a multi-model approach that uses simpler
-models for summarizations, while complex models are used for tasks such as
-reviewing code. In addition, simpler models act as a triage filter that
-identifies the changes that need to be thoroughly reviewed by more complex
-models.
+`gpt-3.5-turbo`. We had to design a multimodel approach that uses simpler models
+for summarizations, while complex models are used for tasks such as reviewing
+code. In addition, simpler models act as a triage filter that identifies the
+changes that need to be thoroughly reviewed by more complex models.
 
 **Inaccuracies:** LLMs are not perfect and often return inaccurate results, and
 they sometimes even ignore instructions and completely fabricate a response.
-Rather than keep fighting the LLMs we wrote layers of sanity checks to fix or
+Rather than keep fighting the LLMs, we wrote layers of sanity checks to fix or
 hide the inaccuracies from the user.
 
 **Data privacy:** The biggest concern from our users is whether their code is
diff --git a/blog/how-we-built-cost-effective-generative-ai-application-2023-12-23/blog.md b/blog/how-we-built-cost-effective-generative-ai-application-2023-12-23/blog.md
@@ -19,7 +19,7 @@ CodeRabbit reviews several thousand pull requests (PRs) daily. We have
 innovative client-side request prioritization technique to navigate OpenAI rate
 limits. In this blog post, we will explore how we manage to deliver continuous,
 in-depth code analysis cost-effectively, while also providing a robust, free
-plan to open source projects.
+plan to open-source projects.
 
 <!--truncate-->
 
@@ -37,10 +37,10 @@ functionalities. CodeRabbit offers the following tiers of service:
   of code changes in a PR.
 
 Our vision is to offer an affordable, AI-driven code review service to
-developers and organizations of all sizes while supporting the open source
-community. We are particularly mindful of open source projects, understanding
+developers and organizations of all sizes while supporting the open-source
+community. We are particularly mindful of open-source projects, understanding
 the challenges in reviewing community contributions. Our goal is to reduce the
-burden of code reviews for open source maintainers by improving submission
+burden of code reviews for open-source maintainers by improving submission
 quality before the review process begins.
 
 CodeRabbit's review process is automatically triggered when a PR is opened in
@@ -64,7 +64,7 @@ gpt-4 models.
 
 Our primary cost driver is using OpenAI's API to generate code review comments.
 We will share our cost optimization strategies in the following sections.
-Without these optimizations, our free offering to open source projects would not
+Without these optimizations, our free offering to open-source projects would not
 be feasible.
 
 Let's take a look at the strategies that helped us optimize the cost and improve
@@ -94,14 +94,14 @@ changes, we save almost 50% on costs.
 
 ## 2. Rate-limiting: Enforcing Fair Usage
 
-Upon launching our free service for open source projects, we noticed individual
+Upon launching our free service for open-source projects, we noticed individual
 developers using it as a coding co-pilot by making hundreds of incremental
 commits for continuous feedback. CodeRabbit, designed for thorough code reviews
 unlike tools such as GitHub Copilot, incurs high costs when used in this manner.
 Therefore, we implemented hourly rate-limits on the number of files and commits
 reviewed per user, to control excessive usage without compromising user
 experience. These limits vary across different product tiers. For example, we
-set more aggressive limits for open source users compared to trial and paid
+set more aggressive limits for open-source users compared to trial and paid
 users.
 
 To implement these rate-limits, we evaluated various options for Serverless
@@ -114,23 +114,23 @@ In FluxNinja Aperture, policies are decoupled from application logic through
 labels, enabling new policy additions without altering application code. We
 apply labels in FluxNinja Aperture, wrap the review workload with its SDK, and
 write policies that enforce limits on those labels. For example, we enforce a 3
-reviews per hour limit (1 review every 20 minutes) for open source users,
+reviews per hour limit (1 review every 20 minutes) for open-source users,
 allowing a burst of 2 back-to-back reviews, as shown in the screenshots below.
 
 Integration with FluxNinja Aperture SDK
 
-![Rate limiting commits per hour for open source users](generative-ai-request-flow-cost-saving.png "Rate limiting commits per hour for open source users")
-Rate limiting commits per hour for open source users
+![Rate-limiting commits per hour for open-source users](generative-ai-request-flow-cost-saving.png)
+_Rate-limiting commits per hour for open-source users_
 
-![Wait time feedback to the user in a comment](rate-limit-message-screenshot.png "Wait time feedback to the user in a comment")
-Wait time feedback to the user in a comment
+![Wait time feedback to the user in a comment](rate-limit-message-screenshot.png)
+_Wait time feedback to the user in a comment_
 
 Given the high cost and capacity constraints of state-of-the-art models such as
 gpt-4, rate-limiting is an essential requirement for any AI application. By
 implementing fair-usage rate limits, we are saving almost 20% on our costs.
 
-![Rate limit metrics for open source users](rate-limits-metrics-screenshot.png "image_tRate limit metrics for open source usersooltip")
-Rate limit metrics for open source users
+![Rate limit metrics for open source users](rate-limits-metrics-screenshot.png)
+_Rate limit metrics for open-source users_
 
 ## 3. Caching: Avoid Re-generating Similar Review Comments
 
diff --git a/blog/openai-rate-limits-2023-10-23/blog.md b/blog/openai-rate-limits-2023-10-23/blog.md
@@ -115,7 +115,7 @@ the nature of requests.
 
 We were introduced to the [FluxNinja Aperture](https://www.fluxninja.com/) load
 management platform by one of our advisors.
-[Aperture](https://github.com/fluxninja/aperture) is an open source load
+[Aperture](https://github.com/fluxninja/aperture) is an open-source load
 management platform that offers advanced rate-limiting, request prioritization,
 and quota management features. Essentially, Aperture serves as a global token
 bucket, facilitating client-side rate limits and business-attribute-based
@@ -150,13 +150,13 @@ context to Aperture, we also attach the following labels to each request:
   tier. For example, the reasoning could that the user is a `paid_user`,
   `trial_user` or a `open_source_user`. Requests to OpenAI are prioritized based
   on these labels.
-- `priority`: Requests are ranked according a priority number provided in this
-  label. For instance, requests from `paid_user` are given precedence over those
-  from `trial_user` and `open_source_user`. The base priority is incremented for
-  each file reviewed, enabling pull requests that are further along in the
-  review process to complete more quickly than newly submitted ones.
-  Additionally, chat messages are assigned a much higher priority compared to
-  review tasks.
+- `priority`: Requests are ranked according to a priority number provided in
+  this label. For instance, requests from `paid_user` are given precedence over
+  those from `trial_user` and `open_source_user`. The base priority is
+  incremented for each file reviewed, enabling pull requests that are further
+  along in the review process to complete more quickly than newly submitted
+  ones. Additionally, chat messages are assigned a much higher priority compared
+  to review tasks.
 
 ![Request Flow](request-flow.svg)
 
@@ -227,22 +227,22 @@ context to Aperture, we also attach the following labels to each request:
 
 Aperture offers a foundational "blueprint" for
 [managing quotas](https://docs.fluxninja.com/reference/blueprints/quota-scheduling/base),
-comprising of two main components:
+comprising two main components:
 
 - Rate limiter: OpenAI employs a token bucket algorithm to impose rate limits,
   and that is directly compatible with Aperture's rate limiter. For example, in
   the tokens per minute policy for `gpt-4`, we have allocated a burst capacity
   of `40000 tokens`, and a refill rate of `40000 tokens per minute`. The bucket
   begins to refill the moment the tokens are withdrawn, aligning with OpenAI's
-  rate limiting mechanism. This ensures our outbound request and token rate
+  rate-limiting mechanism. This ensures our outbound request and token rate
   remains synchronized with OpenAI's enforced limits.
 - Scheduler: Aperture has a
   [weighted fair queuing](https://docs.fluxninja.com/concepts/scheduler/)
   scheduler that prioritizes the requests based on multiple factors such as the
   number of tokens, priority levels and workload labels.
 
-By fine-tuning these two components in Aperture, we are able to go as fast as we
-can, with optimal user experience, while ensuring that we don't exceed the rate
+By fine-tuning these two components in Aperture, we can go as fast as we can,
+with optimal user experience, while ensuring that we don't exceed the rate
 limits.
 
 <details>
diff --git a/docs/about/support.md b/docs/about/support.md
@@ -29,8 +29,8 @@ which they are purchased and cannot be used under another organization.
 ### Can CodeRabbit review my existing PRs after integrating it?
 
 CodeRabbit would by default only review new PRs or existing PRs which have a new
-commit after the app is installed. You can, however, use `@coderabbitai review`
-command on the PR to trigger a review of existing PRs.
+commit after the app is installed. You can, however, use the
+`@coderabbitai review` command on the PR to trigger a review of existing PRs.
 
 ### Who can add the repositories on CodeRabbit?
 
diff --git a/docs/guides/customize-coderabbit.md b/docs/guides/customize-coderabbit.md
@@ -8,8 +8,7 @@ description:
 ---
 
 CodeRabbit offers various customization options to tailor the reviews to your
-specific requirements. Customizations can be made using one of the below options
-:
+requirements. Customizations can be made using one of the below options :
 
 1. **Customization via CodeRabbit YAML File** _(Recommended)_
 2. **Customization via CodeRabbit UI**
@@ -19,7 +18,8 @@ Customization defined in the YAML file overrides the settings in the UI.
 ### 1. Customize CodeRabbit using a YAML File[](https://coderabbit.ai/docs/get-started/customize-coderabbit)
 
 You can add a `.coderabbit.yaml` configuration file to your repositories. Below
-is a sample YAML file that can be used as a starting point and change as needed:
+is a sample YAML file that can be used as a starting point and changed as
+needed:
 
 #### version 2: `Current`
 
@@ -217,14 +217,14 @@ Reviews can also be customized through the UI under repository settings:
 **Path-based instructions :** Provide additional review guidelines based on the
 file paths using glob patterns.
 
-For further guidance, please refer this
+For further guidance, please refer to this
 section [Prompt Customization](/guides/prompt-customization)
 
 **Language Selection:** Select the natural language in which you want the review
 feedback. CodeRabbit supports most of the widely used languages. The default
 language is English.
 
-**Disable High Level Summary:** This allows disabling high level summary added
+**Disable High Level Summary:** This allows disabling high-level summary added
 with the pull request description.
 
 ---
@@ -236,7 +236,7 @@ with the pull request description.
 **Disable Reviews:** Disables automatic code reviews for the repository. Reviews
 can be initiated on-demand using CodeRabbit commands.
 
-**Enable Draft Pull request Reviews:** Select whether CodeRabbit should review
+**Enable draft pull request reviews:** Select whether CodeRabbit should review
 the draft pull requests.
 
 **Configure reviews using pull request labels:** Select specific pull request
diff --git a/docs/introduction/introduction.md b/docs/introduction/introduction.md
@@ -3,19 +3,19 @@ id: introduction
 title: What is CodeRabbit?
 sidebar_label: Introduction
 description:
-  CodeRabbit is an innovative, AI-first code reviewer. It provides context aware
+  CodeRabbit is an innovative, AI-first code reviewer. It provides context-aware
   review feedback on a pull request within minutes, thereby significantly
   reducing the time and effort associated with manual code reviews.
 slug: "/"
 ---
 
-**CodeRabbit** is an innovative, AI-first code reviewer. It provides context
-aware review feedback on a pull request within minutes, thereby significantly
-reducing the time and effort associated with manual code reviews. Secondly, it
-brings a different perspective to the reviews and finds issues often missed by
-the human eye. Developers can chat with the bot within the code, which allows
-them to provide additional context, ask questions, or have the bot generate
-code. It learns from your suggestions and gets better overtime.
+**CodeRabbit** is an innovative, AI-first code reviewer. It provides
+context-aware review feedback on a pull request within minutes, thereby
+significantly reducing the time and effort associated with manual code reviews.
+Secondly, it brings a different perspective to the reviews and finds issues
+often missed by the human eye. Developers can chat with the bot within the code,
+which allows them to provide additional context, ask questions, or have the bot
+generate code. It learns from your suggestions and gets better overtime.
 
 **CodeRabbit** seamlessly integrates with GitHub and GitLab repositories,
 performing continuous, incremental reviews for each commit within a pull
@@ -42,7 +42,7 @@ process with other third parties.
 Does CodeRabbit store my Data? We store embeddings of your conversations, which
 are used to improve future reviews for your organization.
 
-Compliance and Data Privacy: Your data is kept confidential, isolated by
+Compliance and Data Privacy: Your data is kept confidential, isolated by the
 organization, and used only to improve your organization reviews. Data storage
 complies with SOC2 Type II, GDPR, and HIPAA standards.
 
