Sensible

The easiest way to get structured data out of documents

[Sensible @sensiblehq]

🚀 Introducing Sensible Instruct!

Transform documents into structured data with LLMs, including GPT-4.

Use natural language to extract data from any document.

🤖 AI-powered document extraction
🗣️ Natural language queries
⚡️ Extract data in seconds
📄 Works with any doc

[Sensible @sensiblehq]

More here: https://t.co/rS5m4QqIaL

[Sensible @sensiblehq]

Today we’re excited to launch Human Review, a powerful new feature that allows you to easily review and correct flagged extractions right in the Sensible app.

With Human Review, you can:
✅ Auto flag extractions that need a closer look
✅ Easily review and edit extracted fields
✅ Approve or reject extractions

Want to learn more? Link in the next post.

[Sensible @sensiblehq]

https://t.co/xlAulNbd3h

[Sensible @sensiblehq]

Are embeddings still the best for RAG?

We’ve recently explored some new approaches to retrieval-augmented generation (RAG) that rely solely on completions without using embeddings.

Learn how this completions-only method compares to embedding-based approaches, and why we believe it may be the future for certain RAG use cases as language models continue to improve.

[Danil @danilk]

I've been incredibly impressed by the customer support experience @sensiblehq, customer-obsessed would be an understatement of the year. Great work @kevesun @minglu !

[Sensible @sensiblehq]

📆 @craft_ventures is hosting an AI agent hackathon June 4-5th. The prize: $10k for the finalist, $5k for two runners up.

Applications close May 10th. Mention in your application that you heard about the hackathon through Sensible.

https://t.co/hXTTZrMbTr

[Sensible @sensiblehq]

More info here: https://t.co/bJyvswCgnI

[Sensible @sensiblehq]

We've just launched a powerful new feature to streamline document extraction: recommended queries.

After ingesting your document, Sensible uses LLMs to identify key data points within the document and automatically generates optimized queries to extract structured data.

[Sensible @sensiblehq]

@naum_naum_naum Both are great OSS options. If you're interested in a hosted API, maybe https://t.co/qhwGRWtYS5 can help.

[Sensible @sensiblehq]

📄 Ever wondered how the PDF became ubiquitous and conquered the digital world? Read the untold story of the PDF's rise, its impact on tech and business, and why it's still vital in 2023.

https://t.co/nXFbpLS3Xx

[Corey Haines @coreyhainesco]

Gotta shoutout @zstvns for making the most badass PDF I’ve ever seen 💪

[Sensible @sensiblehq]

📄 Ever wondered how the PDF became ubiquitous and conquered the digital world? Read the untold story of the PDF's rise, its impact on tech and business, and why it's still vital in 2023.

https://t.co/nXFbpLS3Xx

[Sensible @sensiblehq]

Sensible’s new user management capabilities make it easy to coordinate your team’s account directly within the Sensible app.

- Team management: Invite new users to your team account, or remove existing members, directly within the app without needing to reach out to customer success.

- User permissions: User management introduces two user designations – admins and members – to manage accessibility within team accounts. Admins can invite new members, set other admins, remove members, create and manage API keys, update billing, and change the subscription plan. Members can view other users on the team account, update their own account details, and view monthly plan usage.

- Subscription management: View or upgrade your subscription plan and billing information, and track plan usage for the current billing period.

- API keys: Easily create new API keys, or track where current API keys are being used.

[Sensible @sensiblehq]

We’re excited to launch Sensible’s in-app dashboard.

Now, you can track all your document extraction metrics in one place, in real-time.

https://t.co/IBgll5gbz6

[Sensible @sensiblehq]

1/ At @Sensiblehq, we've been leveraging LLMs to transform unstructured documents into structured data at scale.

Here's everything you need to know about document question-answering, including: 👇

✅ chunking
✅ layout preservation
✅ cost optimization
✅ confidence scores

[Sensible @sensiblehq]

How can you measure LLM extraction accuracy when traditional ML confidence scores don’t work?

Sensible’s confidence signals help to identify common sources of extraction uncertainty, and enhance your LLM prompting to achieve better results.

https://t.co/m1CzupBUeG

[Sensible @sensiblehq]

How can you measure LLM extraction accuracy when traditional ML confidence scores don’t work?

Sensible’s confidence signals help to identify common sources of extraction uncertainty, and enhance your LLM prompting to achieve better results.

https://t.co/m1CzupBUeG

[Sensible @sensiblehq]

@zachweinberg 👇
https://t.co/ZgWThkz7Xs

[Terrible Maps @TerribleMaps]

Maximum size of a PDF, version 7: 381 km × 381 km.

https://t.co/Sxz37HMYD1

[Sensible @sensiblehq]

End/ If you liked this thread, please like and retweet the first post here: 👇
https://t.co/q9IMAKGYpC

[Sensible @sensiblehq]

1/ At @Sensiblehq, we've been leveraging LLMs to transform unstructured documents into structured data at scale.

Here's everything you need to know about document question-answering, including: 👇

✅ chunking
✅ layout preservation
✅ cost optimization
✅ confidence scores

[Sensible @sensiblehq]

1/ At @Sensiblehq, we've been leveraging LLMs to transform unstructured documents into structured data at scale.

Here's everything you need to know about document question-answering, including: 👇

✅ chunking
✅ layout preservation
✅ cost optimization
✅ confidence scores

[Sensible @sensiblehq]

9/ For an in-depth, check out the full post: https://t.co/zl3ToeLodV