Convex vs LlamaIndex

Convex

LlamaIndex

Convex · 18 features

• Actions — Non-deterministic functions for external I/O (fetch, AI APIs, email). Cannot rea…
• Authentication — Convex Auth (built-in) or BYO provider (Clerk, Auth0, Kinde, WorkOS). ID tokens …
• Convex Agents — AI agent framework with durable memory, threads, tool use. Works with OpenAI / A…
• Convex Auth — First-party auth library: passwords, magic links, OAuth, phone — stored in your …
• Convex Components — Reusable backend modules (rate limiter, workflow, aggregate, action-retrier, etc…
• Cron Jobs — Recurring schedules defined in convex/crons.ts. UTC, cron-style patterns.
• Durable Workflows — Long-running multi-step workflows with retries and at-least-once guarantees.
• Exception Reporting — Auto-capture errors to Sentry, Axiom, Datadog.
• File Storage — Upload/download via storage API. Returns storage IDs referenced in documents.
• Full-Text Search — BM25 search index on table fields. withSearchIndex query helper.
• HTTP Actions — Expose public HTTP endpoints for webhooks, OAuth callbacks, third-party integrat…
• Log Streams — Stream function logs to Axiom, Datadog, Sentry. Pro+.
• Mutations — Transactional write functions. All reads + writes in one mutation are ACID; conf…
• Preview Deployments — Every Git branch gets its own isolated deployment. Integrates with Vercel/Netlif…
• Queries — Deterministic read-only TS functions. Automatically cached and re-run when under…
• Real-Time Subscriptions — useQuery auto-subscribes; server invalidates when data a query read changes. No …
• Scheduler — schedule.after / schedule.at — enqueue functions to run later. Durable, survives…
• Vector Search — Native vector index on tables. withIndex + filter fields. Up to 4096 dims.

LlamaIndex · 16 features

• Agents — Agent patterns: ReAct, function-calling, multi-agent workflows.
• Document Readers — 200+ readers for PDF, web, Google Drive, SharePoint, Notion, S3, Slack.
• Evaluations — Built-in eval framework: faithfulness, context precision/recall.
• LlamaCloud — Managed indexing + retrieval platform. File connectors, auto-chunking, retrieval…
• LlamaExtract — Schema-based structured extraction from unstructured docs.
• LlamaHub — Community marketplace of readers, tools, prompts.
• LlamaParse — Best-in-class PDF + complex document parser. Tables, math, layout preserved.
• Multimodal — Image + text models, image retrieval.
• Node Parsers — Document chunkers: token, sentence, semantic, hierarchical.
• Observability (OpenLLMetry) — OTel-based tracing baked in.
• Property Graph — Graph-based RAG (knowledge graphs from unstructured data).
• Query Engines — Retrieval + response synthesis combos — router, sub-question, tree, etc.
• RAG — End-to-end RAG patterns: ingest → index → retrieve → synthesize.
• Tools — 50+ pre-built tool integrations.
• Vector Store Integrations — 50+ vector DB integrations.
• Workflows — Event-driven agent workflows (AgentWorkflow).