💬 LMQL Developer Survey

お使いのブラウザで JavaScript が有効になっていないため、このファイルは開けません。有効にして再読み込みしてください。

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.

Google にログインすると作業内容を保存できます。詳細

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)

その他:

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)

その他:

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

その他:

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.

送信

フォームをクリア

Google フォームでパスワードを送信しないでください。

このコンテンツは Google が作成または承認したものではありません。 - 利用規約 - プライバシーポリシー

このフォームが不審だと思われる場合報告

フォーム