refactor: llamacloud configs #707

thucpn · 2025-07-14T12:13:41Z

Summary by CodeRabbit

New Features
- Added support for a new, structured LlamaCloud integration configuration, allowing users to specify output directories and toggle the index selector in the chat UI.
- Introduced new example templates and server initialization files for streamlined LlamaCloud integration.
Bug Fixes
- Improved runtime detection of LlamaCloud usage by switching from environment variable checks to URL query parameters.
Documentation
- Updated documentation to clarify and expand instructions for enabling and configuring LlamaCloud integration, replacing deprecated options with the new configuration object.
Refactor
- Refactored internal configuration handling to use the new LlamaCloud config object, replacing previous boolean flags and environment-based logic.

changeset-bot · 2025-07-14T12:13:45Z

🦋 Changeset detected

Latest commit: e2163de

The changes in this PR will be included in the next version bump.

This PR includes changesets to release 4 packages

Name	Type
create-llama	Patch
@llamaindex/server	Minor
llamaindex-server-examples	Patch
@create-llama/llama-index-server	Patch

Not sure what this means? Click here to learn what changesets are.

Click here if you're a maintainer who wants to add another changeset to this PR

coderabbitai · 2025-07-14T12:13:47Z

Walkthrough

This update refactors and extends LlamaCloud integration across server, templates, and documentation. It introduces a structured llamaCloud config object, modifies server initialization, request handling, and file path logic, updates function signatures to propagate output directory settings, and revises documentation to clarify and separate LlamaCloud configuration from general options.

Changes

Files/Groups	Change Summary
`.changeset/gorgeous-squids-run.md`	Adds a changeset documenting a refactor of LlamaCloud configs for patch/minor version updates.
`packages/create-llama/helpers/python.ts`, `typescript.ts`	Refactors copying logic for TypeScript server templates, conditionally handling LlamaCloud files and directories.
`packages/create-llama/templates/components/ts-proxy/llamacloud/index.ts`, `.../nextjs/src/llamacloud/index.ts`	Adds new modules to initialize and start LlamaIndexServer with LlamaCloud configuration.
`packages/create-llama/templates/components/use-cases/python/*/README-template.md`	Updates documentation to remove `llamaCloudIndexSelector` and add a "LlamaCloud Integration" section.
`packages/server/CLAUDE.md`, `README.md`	Updates documentation to replace `llamaCloudIndexSelector` with a structured `llamaCloud` config object.
`packages/server/next/app/api/files/[...slug]/route.ts`	Changes LlamaCloud usage detection from environment variable to URL query parameter.
`packages/server/src/handlers/chat.ts`, `utils/events.ts`, `utils/workflow.ts`	Updates function signatures and logic to accept and propagate `llamaCloudOutputDir`.
`packages/server/src/server.ts`	Integrates `llamaCloud` config into server initialization, validation, config generation, and request handling.
`packages/server/src/types.ts`	Removes `llamaCloudIndexSelector` from `UIConfig`; adds `LlamaCloudConfig` type and updates server options.

Sequence Diagram(s)

sequenceDiagram
    participant User
    participant Server
    participant LlamaIndexServer
    participant LlamaCloud

    User->>Server: Sends request (e.g., chat, file API)
    Server->>LlamaIndexServer: Initializes with llamaCloud config
    alt File API with llamaCloud enabled
        Server->>Server: Injects useLlamaCloud=true query param
        Server->>LlamaCloud: Retrieves file using outputDir config
        LlamaCloud-->>Server: Returns file data
    end
    alt Chat request
        Server->>LlamaIndexServer: handleChat(..., llamaCloudOutputDir)
        LlamaIndexServer->>LlamaCloud: Uses outputDir for source events
    end
    Server-->>User: Responds with data

Possibly related PRs

feat: support file server for python llamadeploy #703: Adds file server support for Python llamadeploy and LlamaCloud file retrieval using environment variables; related as both PRs modify LlamaCloud file serving, but this PR introduces explicit config and new request handling.

Suggested reviewers

marcusschiesser

Poem

In the cloud where llamas dwell,
Configs refactored, all is well.
Output paths now clear and bright,
Docs and types set just right.
With every hop, this rabbit sees—
LlamaCloud runs with greater ease!
🐇✨

✨ Finishing Touches

📝 Generate Docstrings

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

Review comments: Directly reply to a review comment made by CodeRabbit. Example:
- I pushed a fix in commit <commit_id>, please review it.
- Explain this complex logic.
- Open a follow-up GitHub issue for this discussion.
Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
- @coderabbitai explain this code block.
- @coderabbitai modularize this function.
PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
- @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
- @coderabbitai read src/utils.ts and explain its main purpose.
- @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
- @coderabbitai help me debug CodeRabbit configuration file.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

@coderabbitai pause to pause the reviews on a PR.
@coderabbitai resume to resume the paused reviews.
@coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
@coderabbitai full review to do a full review from scratch and review all the files again.
@coderabbitai summary to regenerate the summary of the PR.
@coderabbitai generate docstrings to generate docstrings for this PR.
@coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
@coderabbitai resolve resolve all the CodeRabbit review comments.
@coderabbitai configuration to show the current CodeRabbit configuration for the repository.
@coderabbitai help to get help.

Other keywords and placeholders

Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
Add @coderabbitai anywhere in the PR title to generate the title automatically.

Documentation and Community

Visit our Documentation for detailed information on how to use CodeRabbit.
Join our Discord Community to get help, request features, and share feedback.
Follow us on X/Twitter for updates and announcements.

packages/server/src/utils/events.ts

coderabbitai

Actionable comments posted: 2

♻️ Duplicate comments (1)

packages/server/src/utils/events.ts (1)

44-52: Parameter-based configuration is a valid architectural choice.

While environment variables were suggested in the past review, the parameter-based approach has advantages:

Explicit dependencies make the code more testable

Avoids global state and improves modularity

Maintains backward compatibility with the default value

The implementation correctly propagates the configuration through the call stack.

🧹 Nitpick comments (6)

.changeset/gorgeous-squids-run.md (1)

2-6: Add a clearer, human-readable summary line.

refactor: llamacloud configs is a bit terse. The changeset file is used for release notes, so expanding this sentence (e.g. “Refactor LlamaCloud configuration from boolean flag to structured object”) will make the changelog far more helpful.
packages/create-llama/templates/components/use-cases/python/document_generator/README-template.md (1)
92-99: Document all public llamaCloud options for consistency.

The server docs list both outputDir and indexSelector on the llamaCloud object, but this README only mentions outputDir. Omitting indexSelector creates a mismatch that can confuse users.
 - The following are the available options:
 - - `outputDir`: The directory for LlamaCloud output
 +The following are the available options:
 +- `outputDir`: Directory where LlamaCloud stores downloaded files
 +- `indexSelector` (boolean, optional): Show the LlamaCloud index-selector dropdown in the chat UI
packages/create-llama/templates/types/llamaindexserver/nextjs/src/llamacloud/index.ts (1)
8-17: Handle the promise returned by .start() to avoid unhandled rejections.

LlamaIndexServer.start() is async and returns a promise.
Creating the server inline without awaiting / catching means any startup failure will be swallowed by Node’s unhandled-rejection handler (or crash the process in future Node versions with --unhandled-rejections=strict).
- new LlamaIndexServer({
+const server = new LlamaIndexServer({
   workflow: workflowFactory,
   uiConfig: {
     componentsDir: "components",
     devMode: true,
   },
   llamaCloud: {
     outputDir: "output/llamacloud",
   },
-}).start();
+});
+
+server.start().catch((err) => {
+  console.error("Failed to start LlamaIndexServer:", err);
+  process.exit(1);
+});
packages/server/CLAUDE.md (1)
133-135: Minor wording tweak for clarity.

Consider rephrasing to make the object hierarchy explicit:
- `llamaCloud`: An object to configure the LlamaCloud integration containing the following properties:
+ `llamaCloud`: Object configuring LlamaCloud integration. Properties:
Purely editorial—no functional impact.
packages/create-llama/templates/components/use-cases/python/agentic_rag/README-template.md (1)
98-105: Mirror the full llamaCloud option set.

Like the previous README, this section omits the indexSelector flag that exists in the main server docs.
-The following are the available options:
-- `outputDir`: The directory for LlamaCloud output
+The following are the available options:
+- `outputDir`: Directory where LlamaCloud stores downloaded files
+- `indexSelector` (boolean, optional): Show the LlamaCloud index-selector dropdown in the chat UI
packages/server/src/server.ts (1)
198-205: Consider a more explicit approach for LlamaCloud file handling.

The current implementation adds a query parameter to signal LlamaCloud usage. Consider passing the configuration more explicitly:
      if (
        pathname?.includes("/api/files") &&
        req.method === "GET" &&
        this.llamaCloud
      ) {
-        query.useLlamaCloud = "true";
+        query.llamaCloudOutputDir = this.llamaCloud.outputDir;
      }
This would make the configuration more explicit and avoid boolean string conversions.

📜 Review details

Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 63f5f6f and e2163de.

📒 Files selected for processing (17)

.changeset/gorgeous-squids-run.md (1 hunks)
packages/create-llama/helpers/python.ts (1 hunks)
packages/create-llama/helpers/typescript.ts (1 hunks)
packages/create-llama/templates/components/ts-proxy/llamacloud/index.ts (1 hunks)
packages/create-llama/templates/components/use-cases/python/agentic_rag/README-template.md (1 hunks)
packages/create-llama/templates/components/use-cases/python/code_generator/README-template.md (1 hunks)
packages/create-llama/templates/components/use-cases/python/deep_research/README-template.md (1 hunks)
packages/create-llama/templates/components/use-cases/python/document_generator/README-template.md (1 hunks)
packages/create-llama/templates/types/llamaindexserver/nextjs/src/llamacloud/index.ts (1 hunks)
packages/server/CLAUDE.md (1 hunks)
packages/server/README.md (1 hunks)
packages/server/next/app/api/files/[...slug]/route.ts (1 hunks)
packages/server/src/handlers/chat.ts (2 hunks)
packages/server/src/server.ts (7 hunks)
packages/server/src/types.ts (1 hunks)
packages/server/src/utils/events.ts (2 hunks)
packages/server/src/utils/workflow.ts (2 hunks)

🧰 Additional context used

📓 Path-based instructions (10)

packages/create-llama/templates/**/*

Instructions used from: