Do I need to install every extra to start extracting?

No. Core extraction and the agent loop need only the base install. Add provider extras, RAG, serve, hub, or media packs only for the paths you use; the tables map each provider string to its extra and env var.

How is this different from calling JSON mode directly?

It cascades provider-native JSON mode, tool-call extraction, and prompted repair with per-attempt cost, token, and capability accounting, plus stepwise per-field coercion and a 50-field registry.

What do agents actually get without an API key?

Keyless search, fetch, and readers for YouTube, GitHub, HN, arXiv, and feeds, with failover across backends and a local cache with content-aware lifetimes. Keys only raise limits and quality.

How do I watch spend across models and tools?

Every call records tokens and cost, Desk shows live per-provider and per-project spend from the tray, and hub adds scoped keys, spend caps, and per-call metering with an OpenAI-compatible serve layer.

How do I install a provider in Prompture?

pip install prompture gets the core; provider SDKs are opt-in extras such as prompture[openai], [anthropic], [google] or [groq], each with its own env var, while Ollama needs no extra.

How do I run a decision model through Prompture?

It exposes a decision-model interface for typed noul, choice and score answers behind one API, with the options being hosted TypeSafe Jev, self-hosted Kev, or in-process Laya.

What does prompture doctor tell me?

It reports what works on this machine, including providers, tools, media, MCP servers and binaries, which backend is active, and the exact fix for anything that is not.

CommunityJev Integrations & Adapters

Prompture

Python library for schema-enforced JSON extraction into Pydantic models, with provider-native JSON mode fallback, auto-repair, token and cost tracking, plus agents, RAG, and eval helpers.

See highlights

Open github.com

Stars: 14
Language: Python
License: MIT
Published by: Community
Author: jhd3197
Last verified: Oct 2026

jhd3197/Prompture

User repository on GitHub

View on GitHub

Prompture is an API-first library for requesting structured JSON output from LLMs (or any structure), validating it against a schema, and running comparative tests between models.

Forks: 3
Last pushed: Updated Oct 2026

Repo stats from the GitHub API, cached Oct 2026.Homepage

About this project

Prompture Structured JSON extraction from any LLM. Schema-enforced, Pydantic-native, multi-provider. Prompture is a Python library that turns LLM responses into validated, structured data. Define a schema or Pydantic model, point it at any provider, and get typed output back — with token tracking, cost calculation, and automatic JSON repair built in.

Quoted from the project's README. Read the full README.

Tagscommunity jevbest catalog-import

Works forJev for Classification Jev for Ranking

Used inJev for Software & DevTools

Languages: Python

Highlights

One provider/model string across many providers; provider SDKs install as opt-in extras.
Stepwise per-field extraction with type coercion, field registry, and multi-model fallback accounting.
Keyless web search, fetch, readers, and transcription with failover, local cache, and safety caps.
Decision-model interface for typed noul, choice, and score answers via hosted Jev, self-hosted Kev, or in-process Laya.

Watch out

The core package is orchestration only; provider SDKs are opt-in extras. Model calls, transcription, and some packs need keys you hold, while web search and reading start keyless. Doctor reports what works and the exact fix. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

More Jev resources like this

loki

Agent runtime with a terminal UI and a messaging gateway that keeps memory, self-built skills, session search, scheduling, and subagents across Telegram, Discord, Slack, WhatsApp, Signal, and CLI.

Jev Integrations & Adapters#community#jevbest#catalog-import

Community

wundercorp/lokiPython

vgi-typesafe

DuckDB table functions over a VGI worker that expose Jev Choice, Noul, Score, and multi-question ask for LATERAL joins with confidence-based routing.

Jev Integrations & Adapters#community#jevbest#catalog-import

Community

Query-farm/vgi-typesafePython

hunch

Python library that maps Jev's Choice, Score and Noul onto verbs like classify, score, check, where, extract, verify and rank, keeping data shape in and out, batching one request per distinct row and caching answers.

Jev Integrations & Adapters#community#jevbest#catalog-import

Community

steven-shoemaker/hunchPython

milvus-model

The model-integration layer for the Milvus vector database, shipping adapters for embedding and reranker models from hosted providers, Jev among them, plus local backends.

Jev Integrations & Adapters#community#jevbest

Community

milvus-io/milvus-modelPython

jev-tree

Typed Python planner runtime that turns batched Jev action distributions into executable probability trees and graphs for finite decision tasks.

Jev Integrations & Adapters#community#jevbest#catalog-import

Community

Chuf-H/jev-treePython

laya-jev-GraphRAG

GraphRAG layer that runs a 4-phase ingest-to-answer pipeline over Neo4j, Memgraph, AGE or Kuzu using Laya or Jev decisions instead of per-hop LLM calls.

Jev Integrations & Adapters#community#jevbest#catalog-import

Community

bodepudimuneendra-netizen/laya-jev-GraphRAGPython

Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai