Add research-paper-analyzer kit#163
Open
Suhas-123-cell wants to merge 10 commits into
Open
Conversation
Adds kit metadata (lamatic.config.js), agent identity (agent.md), README with setup guide, safety constitution, and .gitignore. Uses plain JavaScript — no TypeScript — matching contributor's stack. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Defines the 4-node Lamatic flow (API Trigger → Extract From File → LLM Node → API Response) with full node/edge config and the structured prompt that produces title, authors, year, problem statement, methodology, findings, limitations, plain-English summary, and follow-up questions. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- orchestrate.js: maps flow ID from env to Lamatic workflow - lib/lamatic-client.js: initialises Lamatic SDK, validates env vars - actions/orchestrate.js: server action that calls executeFlow() and returns structured analysis or a typed error - package.json, jsconfig.json, next.config.mjs, tailwind + postcss configs: plain JS/JSX project setup (no TypeScript) - .env.example: documents required env vars Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
page.jsx (JSX, no TypeScript): - URL input form with loading state - Displays title, authors, year in a header bar - Plain English Summary always expanded (highlighted) - Problem statement, methodology, findings, limitations, follow-up questions all collapsible independently - Copy-to-JSON and New-paper reset buttons - Error state with icon layout.jsx + globals.css: Next.js App Router shell with Tailwind Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Next.js server actions, lamatic-client.js, next.config, tailwind/postcss configs, and App Router structure are all removed. The new backend will be FastAPI (Python) matching the contributor's stack, with a plain React + Vite frontend. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- main.py: POST /analyze accepts pdf_url, calls Lamatic flow via httpx, returns structured JSON; GET /health for readiness check - CORS configured for localhost:5173 (Vite) and localhost:3000 - Pydantic request model validates input - Typed error handling: 401, 404, 504 timeout, network errors - requirements.txt: fastapi, uvicorn, httpx, python-dotenv, pydantic - .env.example: documents all 4 required env vars Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- src/App.jsx: fetches POST /analyze from FastAPI backend; shows title/authors/year bar, Plain English Summary (always open), and collapsible sections for problem statement, methodology, key findings, limitations, follow-up questions - Copy-to-JSON and New-paper reset buttons - Error handling with icon display - vite.config.js: proxies /analyze and /health to localhost:8000 so no CORS issues in dev - VITE_BACKEND_URL env var for production deploys - Tailwind CSS for styling Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Adds architecture diagram: React → FastAPI → Lamatic → LLM - Separate startup instructions for backend (uvicorn) and frontend (vite) - Documents POST /analyze request/response schema - Updates tech stack section: FastAPI, Python, Vite (no Next.js) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Lamatic exposes a single GraphQL endpoint per project, not REST. Updated main.py to send the ExecuteWorkflow query with workflowId and payload variables. Also handles GraphQL-level errors from data.errors and checks execute_result.status == "success". Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Contributor
|
Important Review skippedAuto reviews are limited based on label configuration. 🏷️ Required labels (at least one) (1)
Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: Repository UI (base), Organization UI (inherited) Review profile: ASSERTIVE Plan: Pro Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
✨ Finishing Touches🧪 Generate unit tests (beta)
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. Comment |
There was a problem hiding this comment.
Pull request overview
Note
Copilot was unable to run its full agentic suite in this review.
Adds a new “Research Paper Analyzer” kit that extracts text from a PDF URL and returns a structured academic analysis via a Lamatic flow, with a bundled FastAPI backend and React/Vite frontend.
Changes:
- Introduces Lamatic flow + prompts/constitution for extracting and analyzing academic PDFs into structured JSON
- Adds a FastAPI service that calls Lamatic GraphQL to execute the flow
- Adds a React + Vite + Tailwind frontend UI to submit a PDF URL and render/copy results
Reviewed changes
Copilot reviewed 21 out of 21 changed files in this pull request and generated 6 comments.
Show a summary per file
| File | Description |
|---|---|
| kits/research-paper-analyzer/flows/research-paper-analyzer.js | Defines the Lamatic flow nodes, prompt wiring, and output schema for the analyzer |
| kits/research-paper-analyzer/prompts/analyze-paper.md | Adds the user prompt that requests a strict JSON breakdown of the paper |
| kits/research-paper-analyzer/constitutions/default.md | Adds safety/accuracy guardrails and an error behavior for non-paper input |
| kits/research-paper-analyzer/apps/backend/main.py | Implements a FastAPI proxy that executes the Lamatic workflow via GraphQL |
| kits/research-paper-analyzer/apps/frontend/src/App.jsx | Implements the UI + request handling and renders the structured analysis |
| kits/research-paper-analyzer/apps/frontend/package.json | Adds frontend dependencies/devDependencies for Vite/React/Tailwind |
| kits/research-paper-analyzer/README.md | Documents setup, architecture, and usage for the new kit |
| kits/research-paper-analyzer/agent.md | Documents agent identity, capabilities, and intended output schema |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
+84
to
+95
| year: { type: ["number", "null"] }, | ||
| problem_statement: { type: "string" }, | ||
| methodology: { type: "string" }, | ||
| key_findings: { type: "array", items: { type: "string" } }, | ||
| limitations: { type: "array", items: { type: "string" } }, | ||
| plain_english_summary: { type: "string" }, | ||
| follow_up_questions: { type: "array", items: { type: "string" } }, | ||
| }, | ||
| required: [ | ||
| "title", "authors", "year", "problem_statement", "methodology", | ||
| "key_findings", "limitations", "plain_english_summary", "follow_up_questions", | ||
| ], |
| ## Accuracy | ||
| - Only draw conclusions directly supported by the paper's content | ||
| - Clearly flag when a section is missing, ambiguous, or truncated | ||
| - If the input is not an academic paper, return: `{"error": "Not an academic paper"}` |
Comment on lines
+27
to
+32
| app.add_middleware( | ||
| CORSMiddleware, | ||
| allow_origins=["http://localhost:5173", "http://localhost:3000"], | ||
| allow_methods=["POST", "GET"], | ||
| allow_headers=["*"], | ||
| ) |
Comment on lines
+15
to
+18
| const BACKEND_URL = import.meta.env.VITE_BACKEND_URL || ""; | ||
|
|
||
| async function callAnalyze(pdfUrl) { | ||
| const res = await fetch(`${BACKEND_URL}/analyze`, { |
Comment on lines
+33
to
+35
| - **Extract From File** — file URL: `{{trigger.pdf_url}}` | ||
| - **LLM Node** — use prompt from `prompts/analyze-paper.md`, structured JSON output | ||
| - **API Response** — output: `{{LLMNode.output}}` |
| - Format all output as structured JSON matching the defined schema | ||
|
|
||
| ## Output Schema | ||
|
|
Adds a Pydantic field_validator on AnalyzeRequest.pdf_url that: - Rejects any non-HTTPS scheme (file://, http://, gopher://, etc.) - Rejects raw IP addresses in private/reserved ranges: 10.0.0.0/8, 172.16.0.0/12, 192.168.0.0/16, 127.0.0.0/8, 169.254.0.0/16 (cloud IMDS), 0.0.0.0/8, ::1/128, fc00::/7 Without this, an attacker could supply an internal URL and have Lamatic's servers fetch it, leaking cloud metadata or internal service responses back in the API response. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
kits/research-paper-analyzer— an AI kit that takes any academic PDF URL and returns a structured breakdownfollow-up questions