{"id":43,"library":"llama-parse","title":"LlamaParse","description":"GenAI-native cloud document parser by LlamaIndex for RAG-optimized output. Parses PDFs, PPTX, DOCX, XLSX, HTML and more into markdown, text, or structured JSON with accurate table extraction and multimodal support. Cloud API service — requires an API key from cloud.llamaindex.ai. NOT a local/offline tool. CRITICAL: The llama-parse package (and its successor llama-cloud-services) are DEPRECATED as of early 2026. The replacement is 'llama-cloud' (pip install llama-cloud), which targets LlamaParse API v2. The old packages are maintained until May 1, 2026 only.","status":"deprecated","version":"0.6.94","language":"python","source_language":"en","source_url":"https://github.com/run-llama/llama_cloud_services","tags":["llamaparse","llama-parse","llama-cloud","document-parsing","pdf-parsing","rag","llamaindex","cloud-api","ocr","table-extraction"],"install":[{"cmd":"pip install llama-cloud","lang":"bash","label":"NEW — recommended for all new projects (API v2)"},{"cmd":"pip install llama-parse","lang":"bash","label":"DEPRECATED — maintained until May 1, 2026 only (API v1)"},{"cmd":"pip install llama-cloud-services","lang":"bash","label":"DEPRECATED — intermediate package, also replaced by llama-cloud"}],"dependencies":[{"reason":"Required. API key from https://cloud.llamaindex.ai/api-key. All requests fail without it. Can be set as env var or passed directly to the parser constructor.","package":"LLAMA_CLOUD_API_KEY","optional":false},{"reason":"Required in Jupyter/notebook environments only. LlamaParse uses async internally; nest_asyncio patches the event loop to allow sync usage in notebooks.","package":"nest_asyncio","optional":true}],"imports":[{"wrong":"from llama_cloud import LlamaParse","symbol":"LlamaParse","correct":"from llama_cloud import Client"}],"quickstart":{"code":"# NEW API (llama-cloud, v2) — recommended\n# pip install llama-cloud\nimport os\nfrom llama_cloud.services.parse import LlamaParse\n\nparser = LlamaParse(\n    api_key=os.environ[\"LLAMA_CLOUD_API_KEY\"],\n    tier=\"cost_effective\",  # fast | cost_effective | agentic | agentic_plus\n    result_type=\"markdown\",\n)\n\ndocuments = parser.load_data(\"./my_file.pdf\")\nprint(documents[0].text[:500])\n\n# ---\n# OLD API (llama-parse, v1) — deprecated, works until May 2026\n# pip install llama-parse\nimport nest_asyncio\nnest_asyncio.apply()  # required in notebooks\n\nfrom llama_parse import LlamaParse\n\nparser = LlamaParse(\n    api_key=os.environ[\"LLAMA_CLOUD_API_KEY\"],\n    result_type=\"markdown\",\n    num_workers=4,\n    verbose=True,\n)\n\ndocuments = parser.load_data(\"./my_file.pdf\")\ndocuments_batch = parser.load_data([\"./file1.pdf\", \"./file2.pdf\"])\ndocuments_async = await parser.aload_data(\"./my_file.pdf\")","lang":"python","description":"Cloud API — requires internet and valid API key. Free tier available. For notebooks, call nest_asyncio.apply() before using sync methods or use aload_data() for async."},"warnings":[{"fix":"Migrate to: pip install llama-cloud. New import: from llama_cloud.services.parse import LlamaParse. Review the v1→v2 migration guide at developers.llamaindex.ai.","message":"llama-parse and llama-cloud-services are DEPRECATED. Both packages will receive no new features and are maintained only until May 1, 2026. New LlamaParse API v2 features are only available in the 'llama-cloud' package.","severity":"breaking","affected_versions":"all llama-parse versions, all llama-cloud-services versions"},{"fix":"Add 1 to all target_pages values when migrating from v1 to v2.","message":"LlamaParse API v2 changed target_pages from 0-based indexing to 1-based indexing. Code using target_pages='0,1,2' (v1) must be updated to target_pages='1,2,3' (v2). Silent wrong results if not updated.","severity":"breaking","affected_versions":"all code migrating from v1 to v2"},{"fix":"Explicitly set images_to_save in v2 if you need images extracted. Do not assume v1 image defaults carry over.","message":"v2 API removed save_images and take_screenshot boolean flags. Replaced by images_to_save parameter. In v1, save_images defaulted to True; in v2, images are NOT saved by default.","severity":"breaking","affected_versions":"all code migrating from v1 to v2"},{"fix":"Rewrite parsing_instruction content as system_prompt and/or user_prompt in v2 configuration.","message":"parsing_instruction parameter (v1) is deprecated. Replaced by system_prompt + user_prompt combination in v2. Old parsing_instruction values are silently ignored in v2.","severity":"breaking","affected_versions":"all code migrating from v1 to v2"},{"fix":"For on-prem or data-sensitive use cases, contact LlamaIndex for enterprise/VPC options. There is no self-hosted OSS equivalent.","message":"LlamaParse is a cloud API — it is not a local parser. All documents are sent to LlamaIndex servers. Not suitable for sensitive/private documents without a VPC or on-prem enterprise agreement.","severity":"gotcha","affected_versions":"all"},{"fix":"Add import nest_asyncio; nest_asyncio.apply() at the top of any notebook or async-host environment. New llama-cloud SDK has improved sync/async handling.","message":"nest_asyncio.apply() is required in Jupyter notebooks and environments that already have a running event loop (e.g., FastAPI startup). Without it, calling sync methods like load_data() raises 'This event loop is already running'.","severity":"gotcha","affected_versions":"all (old llama-parse API)"},{"fix":"Always install: pip install llama-cloud (new) or pip install llama-parse (old/deprecated). Never llama-parser.","message":"llama-parser (note: singular, no 'e') is a completely different, unmaintained package on PyPI released in 2024. pip install llama-parser installs the wrong package. The correct package names are llama-parse (deprecated) or llama-cloud (current).","severity":"gotcha","affected_versions":"all"},{"fix":"Use only the four valid tier strings. 'fast' is text-only spatial extraction. 'agentic_plus' is highest fidelity for complex layouts.","message":"Parsing tiers in v2 are: fast, cost_effective, agentic, agentic_plus. Using any other string (e.g. old v1 mode names) returns: 'Unsupported tier: must be one of: fast, cost_effective, agentic, agentic_plus'.","severity":"gotcha","affected_versions":"v2 API (llama-cloud package)"},{"fix":"Wrap asynchronous calls (e.g., `parser.aload_data()`) in an `async def` function and execute it using `asyncio.run(your_async_function())`. For interactive environments like Jupyter, consider using `nest_asyncio.apply()` at the top of your script/notebook to handle potential event loop conflicts if running `asyncio.run()` multiple times.","message":"The 'await' keyword can only be used inside an 'async def' function. Attempting to use 'await' directly in the global scope or a non-async function will result in a 'SyntaxError: 'await' outside function'.","severity":"breaking","affected_versions":"all llama-cloud versions when using 'aload_data' in the global scope or a non-async function"}],"env_vars":null,"search_vec":"'1':91 '2026':67,92 'accur':30 'api':37,41,82,111 'cloud':5,36,60,73,78,100,110 'cloud-api':109 'cloud.llamaindex.ai':44 'critic':49 'deprec':63 'document':6,102 'document-pars':101 'docx':18 'earli':66 'extract':32,115 'genai':3 'genai-n':2 'html':20 'instal':75 'json':28 'key':42 'llama':52,59,72,77,96,99 'llama-cloud':71,76,98 'llama-cloud-servic':58 'llama-pars':51,95 'llamaindex':9,108 'llamapars':1,81,94 'local/offline':47 'maintain':88 'markdown':24 'may':90 'multimod':34 'nativ':4 'ocr':112 'old':85 'optim':13 'output':14 'packag':54,86 'pars':15,53,97,103,106 'parser':7 'pdf':105 'pdf-pars':104 'pdfs':16 'pip':74 'pptx':17 'rag':12,107 'rag-optim':11 'replac':69 'requir':39 'servic':38,61 'structur':27 'successor':57 'support':35 'tabl':31,114 'table-extract':113 'target':80 'text':25 'tool':48 'v2':83 'xlsx':19","created_at":"2026-03-16T04:39:09.011572+00:00","updated_at":"2026-04-16T16:19:10.292217+00:00","problems":null,"ecosystem":"pypi","meta_description":null,"install_score":0,"quickstart_score":0,"quickstart_tag":"stale","pypi_latest":"0.6.94","cli_name":"","cli_version":null,"type":"library","homepage":"https://cloud.llamaindex.ai","github":null,"docs":null,"changelog":null,"pypi":"https://pypi.org/project/llama-parse/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"categories":["llm-agents","data","serialization"],"base_url":null,"auth_type":null,"provenance":{"verified_status":"passing","verified_at":"2026-07-03","last_verified":"2026-07-03","next_check":"2026-08-02","install_tag":"stale"}}