# run-llama/llama_cloud_services

Knowledge Agents and Management in the Cloud

Repository: https://github.com/run-llama/llama_cloud_services
Canonical: https://ross.abutalabs.com/products/llama_cloud_services
Homepage: https://cloud.llamaindex.ai
Language: TypeScript
License: MIT
License Family: permissive
Topics: document, parsing, pdf, pdf-document-processor, pptx, structured-data, document-parser, document-parsing, docx-to-markdown, pdf-to-excel, pdf-to-json, pdf-to-text, ppt-to-json, tables, ppt-to-markdown, pdf-to-markdown
Last push: 2026-05-18T19:09:10+00:00

## Health v2 (maintenance only)
Score: 71/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 83, release rhythm 58, longevity 67
- inputs: {"age_days": 945, "days_push": 107, "days_rel": 201, "gap_med": 1.0, "n_releases_24m": 153}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4262, forks 466 (observed 2026-08-28T04:08:40.636158+00:00)

## What it is
LlamaCloud Services provides cloud-hosted document parsing and knowledge agent tooling, including the LlamaParse document parser that converts PDFs, DOCX, and PPTX into markdown, JSON, and structured data. This repository and its packages are deprecated; users should migrate to the new llama-cloud packages.

## Use cases
- parse resumes from pdfs
- convert pdf to markdown
- extract tables from pdfs into excel or
- parse powerpoint slides to  or markdown
- prepare documents for rag pipelines
- extract structured data from docx files

## When to choose
- you need high-quality parsing of complex PDFs with tables and layout
- you are building a RAG pipeline over messy documents
- you want a managed cloud parsing service instead of self-hosting

## When to avoid
- you need active development or support - the repo is deprecated until May 2026
- you require fully offline or self-hosted parsing
- you want a free tool without cloud API costs

## Facets
- artifact type: service
- maturity: abandoned
- function: parser, ocr, pdf, rag, etl
- domain: pdf, files, artificial-intelligence
- platform: python, cloud
- tags: document-parsing, pdf-to-markdown, pdf-to-, llamaparse, deprecated, knowledge-agents, structured-data-extraction, retrieval-augmented-generation, data-engineering, nodejs

## Member repositories
- run-llama/llama_cloud_services (main) score 71

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:40.636158+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:22:04.964980+00:00, confidence not recorded.
  - readme: https://github.com/run-llama/llama_cloud_services (fetched 2026-08-28T04:08:40.636158+00:00, sha 66d5ff4f658b)
- Data as of 2026-08-30T08:39:29.467469+00:00.