HackerTrans
TopNewTrendsCommentsPastAskShowJobs

dmpetrov

no profile record

Submissions

Anthropic's in-house data analytics with Claude

claude.com
4 points·by dmpetrov·mese scorso·1 comments

Code as Agent Harness

code-as-harness.github.io
3 points·by dmpetrov·2 mesi fa·0 comments

Issue tracking for AI-assisted software work

github.com
3 points·by dmpetrov·2 mesi fa·0 comments

How to Build a Data Agent in 2026

twitter.com
2 points·by dmpetrov·4 mesi fa·0 comments

Entire - hooks into your Git workflow to capture AI agent sessions

github.com
2 points·by dmpetrov·5 mesi fa·0 comments

Monty: A minimal, secure Python interpreter written in Rust for use by AI

github.com
323 points·by dmpetrov·5 mesi fa·164 comments

Overcoming data inconsistency with a universal semantic layer

infoworld.com
1 points·by dmpetrov·2 anni fa·0 comments

comments

dmpetrov
·mese scorso·discuss
[flagged]
dmpetrov
·2 mesi fa·discuss
[flagged]
dmpetrov
·5 mesi fa·discuss
I like the idea a lot but it's still unclear from the docs what the hard security boundary is once you start calling LLMs - can it avoid "breaking out" into the host env in practice?
dmpetrov
·2 anni fa·discuss
Good point - it does sound a bit like marketing bs. We’ll rephrase it.
dmpetrov
·2 anni fa·discuss
Please share your feedback!
dmpetrov
·2 anni fa·discuss
Good question! I’m not so familiar with it.

It looks like Daft is closer to Lance with it’s own data format and engine. But I’d appreciate more insights from users or the creators.
dmpetrov
·2 anni fa·discuss
Lance is just a data format. Lance DB might be more comparable to DataChain.

DataChain focuses on data transformation and versioning, whereas LanceDB appears to be more about retrieving and serving data. Both designed for multimodal use cases.

From technical side: Lance has it's own data format and DB engine while DataChain utilizes existing DB engines (SQLite in open-source and ClickHouse/BigQuery in SaaS).

In SaaS, DataChain has analytics features including data lineage tracking and visualization for PDFs, videos, and annotated images (e.g., bounding boxes, poses). I'm curious to understand the unique value of LanceDB's SaaS — insight would be helpful!

You could think of it as OLTP (Lance) versus OLAP (DataChain) for multimodal data, though this analogy may not be perfect.
dmpetrov
·2 anni fa·discuss
It's not a format :)

It's simpliy about linking metadata from a json to a corresponding image or video file, like pairing data003.png & data003.json to a single, virtual record. Some format use this approach: open-image or laion datasets.
dmpetrov
·2 anni fa·discuss
Absolutely, that's a common scenario!

Just connect from your Python code (like the lambda in the example) to DB and extract the necessary data.
dmpetrov
·2 anni fa·discuss
I guess, it involves splitting a file into smaller document snippets, getting page numbers and such, and calculating embeddings for each snippet—that’s the usual approach. Specific signals vary by use case.

Hopefully, @jerednel can add more details.
dmpetrov
·2 anni fa·discuss
Exactly! DataChain does lazy compute. It will read metadata/json while applying filtering and only download a sample of data files (jpg) based on the filter.

This way, you might end up downloading just 1% of your data, as defined by the metadata filter.
dmpetrov
·2 anni fa·discuss
DataChain has no assumptions about metadata format. However, some formats are supported out of the box: WebDataset, json-pair, openimage, etc.

Extract metadata as usual, then return the result as JSON or a Pydantic object. DataChian will automatically serialize it to internal dataset structure (SQLite), which can be exported to CSV/Parquet.

In case of PDF/HTML, you will likely produce multiple documents per file which is also supported - just `yield return my_result` multiple times from map().

Check out video: https://www.youtube.com/watch?v=yjzcPCSYKEo Blog post: https://datachain.ai/blog/datachain-unstructured-pdf-process...
dmpetrov
·2 anni fa·discuss
Yes, it's not meant to replace data engineering tools like Prefect or Temporal. Instead, it serves as a transformation engine and ad-hoc analytics for images/video/text data. It's pretty much DBT use case for text and images in S3/GCS, though every analogy has its limits.

Try it out - looking forward to your feedback!
dmpetrov
·2 anni fa·discuss
Yay! Excited to see DataChain on the front page :)

Maintainer and author here. Happy to answer any questions.

We built DataChain because our DVC couldn't fully handle data transformations and versioning directly in S3/GCS/Azure without data copying.

Analogy with "DBT for unstractured data" applies very well to DataChain since it transforms data (using Python, not SQL) inside in storages (S3, not DB). Happy to talk more!
dmpetrov
·2 anni fa·discuss
Can this work statistically? For a giving number of attempts, you can ger a required number of successes to make sure it's a statistically meaningful result.

In theory, this approach could help address the non-determinism of LLMs.
dmpetrov
·2 anni fa·discuss
Thank you!

Just shoot an email to support and mention HN. I’ll read and reply.
dmpetrov
·2 anni fa·discuss
Right, DVC caches data for consistency and reproducibility.

If caching is not needed and streaming required, we've created a sister tool DataChain. It's even supports WebDataset and can stream from tar archives and filter images by metadata.

WebDataset example: https://github.com/iterative/datachain/blob/main/examples/mu...
dmpetrov
·2 anni fa·discuss
Yes. And if you track transformations of the binaries or ml training
dmpetrov
·2 anni fa·discuss
In this cases, you need DVC if:

1. File are too large for Git and Git LFS.

2. You prefer using S3/GCS/Azure as a storage.

3. You need to track transformations/piplines on the file - clean up text file, train mode, etc.

Otherwise, vanilla Git may be sufficient.
dmpetrov
·2 anni fa·discuss
hi there! Maintainer and author here. Excited to see DVC on the front page!

Happy to answer any questions about DVC and our sister project DataChain https://github.com/iterative/datachain that does data versioning with a bit different assumptions: no file copy and built-in data transformations.