Data catalogue
Find datasets, series, publications and extracts across the marketplace.
- Warehouse rows
- 6.17B
- Structured DB
- 1,711.35 GB
- Live data store
- 189.73 GB
- Data tables
- 1,03,091
- Publications & data products
- 1,749
About these figures
BigQuery reports 6,167,191,751 physical rows across 89 native base tables in 9 catalogue warehouses, measured on . Structured DB measures logical bytes across the same tables. The headline excludes 22 verified staging and backup tables with 365,935,268 rows and 57.49 GB of logical storage. Separate publisher editions can contain overlapping observations.
The earlier 40-MCP inventory reported 1,115,017,091 records across warehouses, files and upstream sources, including 811,051,329 upstream survey records from MoSPI NADA.
Live data store measures 189.73 GB of live catalogue objects across 39 Cloud Storage buckets, measured on .
UNCTAD ingestion files account for 153.97 GB of additional live storage. Retained soft-deleted objects account for 109.84 GB. Raw publisher archives and their corresponding BigQuery tables are measured in their respective storage layers.
Data tables counts 1,03,091 publisher tables held across the marketplace MCPs, measured in each MCP's own store on 2026-11-10: one table, sheet, dataflow, report section or API dataset in one edition counts once, the way data.gov.in counts resources. Raw copies, backups and archive duplicates are not counted twice. They belong to 1,749 publications and data products — six Economic Survey reports are one publication — which hold 10,664 editions, 8,62,701 series and 19,717 documents. India Intelligence and Survey chapter packs are built from these MCPs and are not added. Geo-Spatial can also reach 2,36,742 data.gov.in resources live; they are not held and not counted.
The search index includes 18,941 datasets (tables, survey studies and map layers) and 493 individually indexed series. Separate live and archived access routes can have their own entries. These figures apply across the catalogue, regardless of filters.
Reference & capabilities
128 results
MONEYCONTROL
MONEYCONTROL ["moneycontrol.com"]
MOODYS
MOODYS ["moodys.com"]
MOPNG
MOPNG ["mopng.gov.in", "ppac.gov.in"]
MORTH
MORTH ["morth.nic.in", "parivahan.gov.in"]
MOSDE
MOSDE ["msde.gov.in"]
MOSPI
MOSPI ["mospi.gov.in", "esankhyiki.mospi.gov.in"]
multi query search
Decompose a hard query into diverse variants, search each, and fuse the results with Reciprocal Rank Fusion (RRF). Better recall than a single search when a question has multiple facets or the phrasing is ambiguous. Variants are LLM-generated (paraphrases + sub-questions); results are deduped and re-ranked across all variants. Args: query: The (possibly complex) question. authorities: Optional sco
NASDAQ
NASDAQ ["nasdaq.com"]
NASSCOM
NASSCOM ["nasscom.in"]
news
news "news"
NHTSA
NHTSA ["nhtsa.gov"]
NITI
NITI ["niti.gov.in"]
NSDL
NSDL ["nsdl.co.in"]
NSE
NSE ["nseindia.com", "nseindiaipo.com"]
NYSE
NYSE ["nyse.com"]
OECD
OECD ["oecd.org", "stats.oecd.org"]
pdf discover
List every PDF link on an HTML landing page (a URL from a Milvus hit). Use when a hit points at a HUB page (not a direct PDF) and the answer lives in an attached PDF. Workflow: pdf_discover → pick by anchor text → pdf_fetch_structured. Args: url: The HTML landing page URL. link_text_filter: Optional case-insensitive substring filter. max_links: Cap on links returned (default 40). Returns: {url, do
pdf fetch
Download a PDF (a URL from a Milvus hit) and extract its text with pypdf. SMART mode (recommended): pass `query` and NO `pages` — it navigates to the right pages instead of dumping the whole file, using (1) the Milvus chunks for THIS pdf nearest the query and (2) the PDF's TOC/outline titles matching the query, then extracts only those pages (±1 neighbour). Token-efficient. EXPLICIT mode: pass `pa
pdf fetch structured
Direct PDF download + pypdf extraction → focused LLM pass → structured JSON. Same shape as `fetch_structured` but via the PDF path. Use when a hit references a PDF (by `url`) and you want its values typed rather than raw.
pdf grep
Grep a PDF (a URL from a Milvus hit) for a pattern — like the `pdfgrep` CLI. Returns only the matching snippets WITH PAGE NUMBERS, not the whole document — token-efficient locate-before-read. Workflow: `pdf_grep` to find which pages mention X → `pdf_fetch(pages=[…])` or `pdf_fetch_structured` to read those pages precisely. (Raw PDF bytes are cached, so the follow-up fetch doesn't re-download.) Arg
Inventory snapshot 16 Nov 2026. Publisher dates and individual source checks can differ.