iiinova — where your digital self keeps evolving

Common patterns: multi-step enrichment, RAG prep, nightly jobs with partial recomputes. for more check the Github repo: github.com/typedef-ai/f...

000

With fenic, it’s explicit and simple: call .cache() where it matters. Protect pricey semantic ops (classify/extract) from re-execution Reuse cached results across multiple downstream analyses Recover from mid-pipeline failures without starting over

100

Think of it as checkpointing for LLM workloads: cache after costly ops, restart from there if something fails. Without caching, teams re-pay tokens and time on retries: flaky APIs, disk hiccups, long recomputes.

100

typedef @typedef.ai · 23/09/2025

fenic's Local Data Caching & Persistence keeps expensive AI steps from rerunning and your pipelines resilient.

100

Mix providers (OpenAI, Anthropic) with simple aliases Use defaults for simple ops; override model_alias for complex ones Balance cost/latency/quality without extra orchestration

000

typedef @typedef.ai · 23/09/2025

Teams often wire a single model and pay in either cost or quality. With Fenic, you register multiple models once and select them per call.

100

typedef @typedef.ai · 23/09/2025

100

typedef @typedef.ai · 21/09/2025

Why do most AI projects stall? Because going from prototype → production is HARD. On Data Exchange, we share how Typedef makes inference-first pipelines actually work at scale. 👉 thedataexchange.media/typedef-fenic/

thedataexchange.media

The Fenic Approach to Production-Ready Data Processing

Kostas Pardalis on Inference-First Data Frames, Markdown as Structure, Semantic Query Operations, and Production AI Debugging.

000

Bridging the AI Gap: How Yoni Iny's Typedef is Revolutionizing Data Processing

We’re honored to be featured in AI World Today! 🚀 Our co-founder Yoni Michael shares how Typedef is closing the gap between AI prototypes and production, making inference a first-class data operation. 👉 Read the full interview: www.aiworldtoday.net/p/interview-...

aiworldtoday.net

Yoni Michael, tech veteran and Typedef co-founder, transforms AI-powered data analytics with an innovative serverless platform for LLM workflows.

000

For AI to Scale, Infrastructure Has to Change-Typedef Gets It

We’re building the AI-native, inference-first infrastructure that powers scalable, production-ready LLM pipelines—no infrastructure headaches, just reliable results. Read more in AIM about how we’re overcoming pilot paralysis: aimmediahouse.com/ai-startups/...

aimmediahouse.com

Typedef, a new AI infrastructure startup that officially launched on June 18, 2025, raised $5.5 million in seed funding, led by Pear VC.

000

Typedef project Fenic: A ‘dataframe’ for LLMs

Fenic brings the reliability of DataFrame pipelines to AI workloads—semantic joins, markdown parsing, transcripts, and more—now strengthened with the 0.3.0 update. Dive into the latest improvements. → www.techzine.eu/blogs/data-m...

techzine.eu

Typedef provides purpose-built AI data infrastructure services for cloud workloads that need to handle LLM-powered pipelines, unstructured data Typedef is Helping AI and Data Teams Build Faster,…

000

AI Fatigue Is Real, But It's Fixable | The AI Journal

AI fatigue is everywhere. But it’s not inevitable. In AI Journal, Typedef co-founder Yoni Michael shares how teams can escape “pilot paralysis” and move AI from prototype to production with confidence. 👉 Read the article: aijourn.com/ai-fatigue-i...

aijourn.com

Enterprises have embraced generative AI with high expectations – new business insights, automated agents, real-time decision-making. What many got instead are

000

Common patterns: review mining, invoice parsing, lead enrichment, spec extraction. for more, check the GitHub repo: github.com/typedef-ai/f...

000

Define a Pydantic schema; get type-checked structs (ints, bools, lists, Optionals) Auto-prompting via function calling / structured outputs (OpenAI, Anthropic) Use unnest() and explode() to work with the data—no manual JSON wrangling

100

Most teams hand-roll JSON parsing, brittle regex, and post-hoc validators. That’s slow and error-prone. With fenic, you keep it declarative.

100

fenic's Structured Output Extraction turns LLM text into validated tables, directly in your DataFrame. Think of it as schema-first parsing: you define a Pydantic model; Fenic enforces it and returns structured columns.

100

Common patterns: doc mining, content ingestion, RAG prep, taxonomy extraction. for more, including examples and documentation, check: github.com/typedef-ai/f...

010

Type safety: Embedding/Markdown/JSON columns prevent incompatible ops Built-ins that matter: normalize, similarity, jq queries for JSON and many more Less glue: query structured + unstructured togethe,; mix dataframes + SQL + AI in one plan

100

Most teams treat AI artifacts as loose strings/arrays: schema drift, brittle casting, ad-hoc JSON parsing, and inconsistent similarity math. In fenic, these are first-class.

fenic's First-Class AI Data Types make embeddings, markdown, and JSON real, typed columns, with the right operations built in. Think of it as strong types for meaning and structure: safer pipelines, richer queries.

100

for examples and more information, check: github.com/typedef-ai/f...

000

Most teams fight drift: regex stacks, ad-hoc prompts, inconsistent tags. With fenic you can: Define classes once; get schema-clean, consistent labels Zero-shot or few-shot with real examples (not just descriptions) Batching, caching, retries built-in all testable in the same plan.

100

Think of it as CASE/WHEN for unstructured text: you define the classes and fenic constrains outputs to exactly those labels.

100

fenic's Semantic Classification turns free-text into clean enums right inside your DataFrame.

100

Common patterns: job↔candidate matching, RAG candidate retrieval, fuzzy dedupe/linking. for examples, demos and more information: github.com/typedef-ai/f...

000

With fenic, it’s one call in your pipeline. Get top-K matches with similarity scores Batch ANN under the hood; models & rate limits live in your Session Compose with selects/filters/LIMIT to control cost and spend

100

Think of it as a k-NN join for meaning: for each row in A, fetch the top-K most similar rows in B (cosine), with scores. Most teams roll their own: separate embedding jobs, vector index wiring, threshold tuning, brittle Python loops.

100

fenic's Semantic Similarity Join (Vector Join) finds nearest neighbors across tables using embeddings, right inside your DataFrame.

typedef @typedef.ai · 09/09/2025

HuggingFace connector: hf://… URIs; also directory loaders to turn folders into DataFrames. Built-in metrics: track latency, tokens, and cost per pipeline locally. DX & stability: clearer errors (e.g., union()), handy null()/empty(), safer S3 auth, smarter retries.

100

typedef @typedef.ai · 09/09/2025

MCP server out-of-the-box: plug Fenic tools into Claude Code, Gemini CLI, Cursor & friends. Latest model support: GPT-5 + Claude Opus 4.1 with fail-fast provider key validation.

100

typedef @typedef.ai · 09/09/2025

fenic 0.4.0 is live: declarative tools for agents, a production-ready MCP server, and direct reads from HuggingFace plus big DX & reliability gains. Highlights: Declarative tools: define function-calling tools as data (type-safe, reviewable, reusable).

151

typedef @typedef.ai · 08/09/2025

You get reliable, table-ready outputs instead of free‑form text.

000

typedef @typedef.ai · 08/09/2025

pass a Pydantic model to semantic.extract or semantic.map and fenic will prompt the model, parse the output, and return typed/struct columns (first‑class support for OpenAI/Anthropic structured responses).

100

typedef @typedef.ai · 08/09/2025

fenic ensures LLM outputs conform to schemas using Pydantic models.

typedef @typedef.ai · 06/09/2025

You can clean/filter/LIMIT before invoking expensive AI calls to reduce cost and provide a better context to the model.

000

typedef @typedef.ai · 06/09/2025

Create from pandas, select/filter/group_by/join, use a Session (like SparkSession) and mix SQL + LLM operations,.

100

typedef @typedef.ai · 06/09/2025

fenic offers standard DataFrame operations with a familiar Spark/Pandas-like API.

100

typedef @typedef.ai · 05/09/2025

Because UDFs are plannable, you can still filter/limit/group with standard DataFrame ops to reduce AI cost, keep pipelines auditable, and only push to the model the enriched, relevant data it needs.

010

typedef @typedef.ai · 05/09/2025

Use them when native column ops aren’t enough, e.g. complex normalization, domain enrichment (spaCy, custom tokenizers, external feature libs), or bespoke pre/post-processing before embeddings/LLM calls.

100

typedef @typedef.ai · 05/09/2025

fenic UDFs allow you to inject arbitrary Python (including external libraries) directly into the fenic execution plan while preserving lazy planning, metrics and reproducibility.