💬 LMQL Developer Survey

JavaScript isn't enabled in your browser, so this file can't be opened. Enable and reload.

Welcome to the LMQL developer survey. The goal of this survey is for the LMQL team to learn more about LMQL's user base and everyone's specific use cases, needs and requests.

This survey will inform the development and direction of the next major version of LMQL.

What kind of LLM are you primarily using with LMQL? (Please fill in 'Other' to indicate requests for new backends)

OpenAI Chat Models

OpenAI Completion Models

Open Models (via llama.cpp or transformers)

Other:

What part of LMQL and LLM programming would you like to see more support for?

Faster Inference Speeds / Performance

Building Chat Applications

Function Calling / Tool Augmentation

RAG pipelines

Working with Embedding Models

Nested Prompting and Other Advanced Forms of Prompting

More powerful decoding algorithms (beam search, tree of thought, graph of thought)

Regex and Grammar-Guided Generation

JSON Schema Constraints

More Inference Backends

Inference Certificates / Reproducible LLM output

Distribution Clause / Scoring

Query Orchestration (e.g. chaining multiple LMQL queries)

Observability Features (like tracing multiple LMQL queries in an application)

Other:

In what kind of applications are you using or planning to use LMQL?

Conversational Chat (e.g. document Q&A)

Data Processing / Transformation

Structured Data Extraction

Autonomous Agents

Code Generation

RAG-augmented Generation

Other:

Are you aware of LMQL's support for different decoding algorithms? If so, which kind of decoders are you using?

I don't know a lot about it

argmax and sample

beam, beam_var

Do you have other forms of feedback or feature requests? Please let us know.

Submit

Clear form

Never submit passwords through Google Forms.

This content is neither created nor endorsed by Google. Report Abuse - Terms of Service - Privacy Policy

Forms