Hashgrid DNA (local)

hashgrid

The Python client for Hashgrid DNA, a search engine that learns from your grades. You store items, ask a question, get the items that fit it best, and grade them with an LLM, a smaller model or your users. Each grade improves the results for every question.

pip install hashgrid

Sign up

Each grid has its own API key (hg-…). DNA.signup makes a grid, no key needed, and returns its key:

from hashgrid import DNA
api_key = DNA.signup("mine")print(api_key)   # shown only now: store it, e.g. as $HASHGRID_API_KEY

DNA(api_key) opens the grid, and DNA() opens it from $HASHGRID_API_KEY. A grid made this way holds up to 1024 items, queries included (dna.info().max_items), and each address can sign up a few times a day. Need more? Write to [email protected].

The loop

from hashgrid import DNA
dna = DNA()
dna.put("cities/lisbon", "Lisbon, a hilly coastal capital")dna.put("cities/oslo", "Oslo, between fjords and forest")
query = dna.query("a capital by the sea")results = query.results(limit=2, prefix="cities/")results[0].key                      # "cities/lisbon"query.grade(results[0], 1.0)        # a good resultquery.grade(results[1], -0.5)       # a poor one

• Items live at keys, like 42 or tools/42. prefix narrows results and listings to keys that start with it. Results return keys and metadata, not content: map the keys back to your own data.
• Queries have an id. To ask the same question again, reopen it with dna.query(id=query.id), so its grades add up.
• Grades run from -1 (wrong) to 1 (right). You can grade any item, not only those a query returned. Only grades train DNA, and a grade shows in results within a few seconds.

Content

An item or a query is text (str), a record (a dict), an image (its bytes, or a Path to its file), or an embedding from the grid's model (a list of floats). DNA embeds the rest itself.

from pathlib import Path
dna.put("tools/search", {"name": "search", "description": "Search the web"})dna.put("photos/beach", Path("beach.jpg"))dna.put("raw", '{"a": 1}', type="text/plain")   # text that looks like JSON

DNA keeps only what it matches on: text and records up to 8 KB, images as a 512 px WebP. dna.get(key) reads one item back, as kept.

Everything else

Methods take a key or the Item / Result itself. AsyncDNA and AsyncQuery have the same methods, awaited. Errors are subclasses of DNAError: Unauthorized (401), Forbidden (403, the grid is full), NotFound (404), PreconditionFailed (412), TooLarge (413), UnsupportedType (415), Invalid (422) and TooManyRequests (429).

For agents, DNA has a hosted MCP server at https://dna.hashgrid.ai/mcp.

License

MIT