Organization repository on GitHub
A scalable semantic database system for efficient and cost-effective semantic query processing.
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.Homepage
Jev directory
CommunityJev Repos & SDKs
JEVDB
A semantic database built on the DuckDB ecosystem that runs classification, semantic joins and scoring over text as ordinary SQL. It batches decisions on a Jev model and returns probabilities, labels and scores directly, without generated explanations.
- Stars
- 14
- Language
- C++
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- PDAIS
- Last verified
- Oct 2026
Used inJev for Data & Analytics
- Languages
- Python
- Capabilities
- Open source
Highlights
- Runs semantic filters, semantic joins, classification and scoring over text inside ordinary SQL.
- By default batches decisions on a Jev model in a single stage, returning probabilities and labels.
- Without key pruning it is called JEVDB-Flash; optional key conditions remove impossible pairs.
- An optional cascade sends uncertain decisions to a second-stage model; an OpenAI-compatible backend is available without a Jev account.
- GitHub metadata: MIT license, C++ repo, created 2026-10-02, last pushed 2026-10-11.
Quickstart
bash
pip install jevdbWatch out
README and GitHub metadata reviewed 2026-10-17; the digest excerpt stops after the pip install line, so the full SQL API surface, benchmark numbers and pricing are not evidenced here.
Questions about this entry
Short answers drawn from the linked project or page.
JEVDB (Just Evaluation and Verification Database) is a scalable semantic database built on the DuckDB ecosystem that runs semantic filters, joins, classification and scoring over text as part of ordinary SQL.
By default it batches decisions on a Jev model in a single stage and returns probabilities, labels and scores directly, so ordinary semantic filters and joins need no generated explanation. Run without key pruning, that mode is called JEVDB-Flash.
The README's install section says: pip install jevdb, for Python users, then open a connection. The digest excerpt does not show connection setup, table DDL or query examples.
Yes, according to the README: an OpenAI-compatible LLM backend is available for users without a Jev account. The digest does not state which backends or keys are accepted.
Optional key conditions remove impossible pairs before decisions are made, and an optional cascade sends uncertain decisions to a second-stage model. The README excerpt does not document their configuration.
Semantic filters and joins return probabilities, labels and scores rather than generated explanations, by design. The digest shows no evaluation numbers, pricing or production limits for the database.
The PDAIS organisation publishes it under the MIT license, with a C++ repository created 2026-10-02 and pushed 2026-10-11, per the digest's GitHub metadata.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
Hacker News: A MySQL plugin that filters rows by asking Jev whether a column matches a sentence.
maayanlevy-hn2 pointsA MySQL plugin that filters rows by meaning (built on TypeSafe Jev)Read the thread on Hacker NewsX: jev(): Postgres WHERE clauses in plain language
More Jev resources like this
A System One layout optimizer for decision-model workloads: it reorders rows and fields so a prefix-caching backend reuses input computation, then returns per-record decisions in original order. Its bundled backend serves AutoTrust JEV-9B through vLLM.
Jev Repos & SDKs#community#github#python
Community
0814wdwd/solo_jevPython
0814wdwd/solo_jevPythonA Python library that turns Jev-style decision models into ordinary function calls: check returns a bool, classify picks one option, label picks every option that applies, and score rates on a scale, with probabilities behind every answer.
Jev Repos & SDKs#community#github#python
Community
jlowin/vibecheckPython
jlowin/vibecheckPythonA frozen decision server that serves Gemma 4 31B — quantized to FP8 at startup — in TypeSafe's /v1/systemone format, reading the next-token distribution instead of generating tokens. It needs one FP8 NVIDIA GPU with 80 GB and has no authentication.
Jev Repos & SDKs#community#github#python
Community
krishna-gogineni-765/deck31bPython
krishna-gogineni-765/deck31bPythonHTTP server for the Mica v0.5 4B Preview decision model: GGUF weights run through llama.cpp and answer noul, choice and score questions with calibrated probabilities over the TypeSafe /v1/systemone format.
Jev Repos & SDKs#community#github#python
Community
akivet/MicaPython
akivet/MicaPythonServing code for the Jeff 1.0 family of Jev-style decision models: a state, a typed question and its options go in, and one forward pass returns a probability for each option. Four open models from 4B to 31B parameters are served the same way.
Jev Repos & SDKs#community#github#python
Community
j-geuter/jeff-servePython
j-geuter/jeff-servePythonA Python batching proxy for Jev that returns Apache Arrow streams, with Python and JavaScript SDKs. It packs many independent states and questions into each TypeSafe API call or runs them concurrently, then emits the answers as an ordered Arrow IPC stream with the schema first.
Jev Repos & SDKs#community#github#python
Community
columnar-tech/jevaroPython
columnar-tech/jevaroPythonFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.