typedef
@typedef.ai
We are here to eat bamba and revolutionize the world of query engines. The Spark is gone, let's rethink data processing with a pinch of AI
Note: auto-routing is being explored; today you keep full control.
check the repo for more: github.com/typedef-ai/f...
check the repo for more: github.com/typedef-ai/f...
GitHub - typedef-ai/fenic: Build reliable AI and agentic applications with DataFrames
Build reliable AI and agentic applications with DataFrames - typedef-ai/fenic
github.com
October 21, 2025 at 11:07 PM
Note: auto-routing is being explored; today you keep full control.
check the repo for more: github.com/typedef-ai/f...
check the repo for more: github.com/typedef-ai/f...
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
Use defaults for simple ops; override model_alias for complex ones
Balance cost/latency/quality without extra orchestration
October 21, 2025 at 11:07 PM
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
Use defaults for simple ops; override model_alias for complex ones
Balance cost/latency/quality without extra orchestration
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.
With Fenic, you register multiple models once and select them per call.
October 21, 2025 at 11:07 PM
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.
With Fenic, you register multiple models once and select them per call.
fenic's Multiple Model Configuration & Selection lets you pick the right model for each step, cheap where you can, powerful where you must.
Think of it as a per-operator model dial across your pipeline.
Think of it as a per-operator model dial across your pipeline.
October 21, 2025 at 11:07 PM
fenic's Multiple Model Configuration & Selection lets you pick the right model for each step, cheap where you can, powerful where you must.
Think of it as a per-operator model dial across your pipeline.
Think of it as a per-operator model dial across your pipeline.
Thanks to @danielvanstrien.bsky.social and @lhoestq.hf.co for the collaboration and feedback that made this possible and to David Youngworth you built and maintains the integration!
October 21, 2025 at 6:57 PM
Thanks to @danielvanstrien.bsky.social and @lhoestq.hf.co for the collaboration and feedback that made this possible and to David Youngworth you built and maintains the integration!
A few things you can do with this new integration.
1. Rehydrate the same agent context anywhere (local → prod)
2. Versioned, auditable datasets for experiments & benchmarks
1. Rehydrate the same agent context anywhere (local → prod)
2. Versioned, auditable datasets for experiments & benchmarks
fenic
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
October 21, 2025 at 6:57 PM
A few things you can do with this new integration.
1. Rehydrate the same agent context anywhere (local → prod)
2. Versioned, auditable datasets for experiments & benchmarks
1. Rehydrate the same agent context anywhere (local → prod)
2. Versioned, auditable datasets for experiments & benchmarks
Fenic ❤️ Hugging Face Datasets!
You can now turn any fenic snapshot into a shareable, versioned dataset on @hf.co perfect for reproducible agent contexts and data sandboxes.
Docs: huggingface.co/docs/hub/dat...
You can now turn any fenic snapshot into a shareable, versioned dataset on @hf.co perfect for reproducible agent contexts and data sandboxes.
Docs: huggingface.co/docs/hub/dat...
fenic
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
October 21, 2025 at 6:57 PM
Fenic ❤️ Hugging Face Datasets!
You can now turn any fenic snapshot into a shareable, versioned dataset on @hf.co perfect for reproducible agent contexts and data sandboxes.
Docs: huggingface.co/docs/hub/dat...
You can now turn any fenic snapshot into a shareable, versioned dataset on @hf.co perfect for reproducible agent contexts and data sandboxes.
Docs: huggingface.co/docs/hub/dat...
"AI confidence is high — but production results still lag."
Our cofounder, Yoni Michael, shares why in CIO.
Read it here 👉 www.cio.com/article/4069...
#CIO #AIinEnterprise #Typedef
Our cofounder, Yoni Michael, shares why in CIO.
Read it here 👉 www.cio.com/article/4069...
#CIO #AIinEnterprise #Typedef
CIOs’ AI confidence yet to match results
While a large percentage of IT and business leaders believe their AI efforts will meet or exceed expectations, only a small number have successfully deployed projects thus far.
www.cio.com
October 20, 2025 at 11:07 PM
"AI confidence is high — but production results still lag."
Our cofounder, Yoni Michael, shares why in CIO.
Read it here 👉 www.cio.com/article/4069...
#CIO #AIinEnterprise #Typedef
Our cofounder, Yoni Michael, shares why in CIO.
Read it here 👉 www.cio.com/article/4069...
#CIO #AIinEnterprise #Typedef
Common patterns: multi-step enrichment, RAG prep, nightly jobs with partial recomputes.
for more check the Github repo: github.com/typedef-ai/f...
for more check the Github repo: github.com/typedef-ai/f...
September 24, 2025 at 1:38 AM
Common patterns: multi-step enrichment, RAG prep, nightly jobs with partial recomputes.
for more check the Github repo: github.com/typedef-ai/f...
for more check the Github repo: github.com/typedef-ai/f...
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
Protect pricey semantic ops (classify/extract) from re-execution
Reuse cached results across multiple downstream analyses
Recover from mid-pipeline failures without starting over
September 24, 2025 at 1:38 AM
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
Protect pricey semantic ops (classify/extract) from re-execution
Reuse cached results across multiple downstream analyses
Recover from mid-pipeline failures without starting over
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.
Without caching, teams re-pay tokens and time on retries: flaky APIs, disk hiccups, long recomputes.
September 24, 2025 at 1:38 AM
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.
Without caching, teams re-pay tokens and time on retries: flaky APIs, disk hiccups, long recomputes.
fenic's Local Data Caching & Persistence keeps expensive AI steps from rerunning and your pipelines resilient.
September 24, 2025 at 1:38 AM
fenic's Local Data Caching & Persistence keeps expensive AI steps from rerunning and your pipelines resilient.
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
Use defaults for simple ops; override model_alias for complex ones
Balance cost/latency/quality without extra orchestration
September 22, 2025 at 11:07 PM
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
Use defaults for simple ops; override model_alias for complex ones
Balance cost/latency/quality without extra orchestration
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.
With Fenic, you register multiple models once and select them per call.
September 22, 2025 at 11:07 PM
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.
With Fenic, you register multiple models once and select them per call.
fenic's Multiple Model Configuration & Selection lets you pick the right model for each step, cheap where you can, powerful where you must.
Think of it as a per-operator model dial across your pipeline.
Think of it as a per-operator model dial across your pipeline.
September 22, 2025 at 11:07 PM
fenic's Multiple Model Configuration & Selection lets you pick the right model for each step, cheap where you can, powerful where you must.
Think of it as a per-operator model dial across your pipeline.
Think of it as a per-operator model dial across your pipeline.
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/
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/
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.
thedataexchange.media
September 21, 2025 at 12:05 AM
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/
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/
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-...
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-...
Bridging the AI Gap: How Yoni Iny's Typedef is Revolutionizing Data Processing
Yoni Michael, tech veteran and Typedef co-founder, transforms AI-powered data analytics with an innovative serverless platform for LLM workflows.
www.aiworldtoday.net
September 20, 2025 at 9:36 PM
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-...
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-...
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/...
For AI to Scale, Infrastructure Has to Change-Typedef Gets It
Typedef, a new AI infrastructure startup that officially launched on June 18, 2025, raised $5.5 million in seed funding, led by Pear VC.
aimmediahouse.com
September 20, 2025 at 8:42 PM
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/...
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...
Typedef project Fenic: A ‘dataframe’ for LLMs
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,…
www.techzine.eu
September 20, 2025 at 3:57 PM
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...
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...
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...
AI Fatigue Is Real, But It's Fixable | The AI Journal
Enterprises have embraced generative AI with high expectations – new business insights, automated agents, real-time decision-making. What many got instead are
aijourn.com
September 20, 2025 at 2:44 AM
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...
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...
Common patterns: review mining, invoice parsing, lead enrichment, spec extraction.
for more, check the GitHub repo: github.com/typedef-ai/f...
for more, check the GitHub repo: github.com/typedef-ai/f...
September 20, 2025 at 1:38 AM
Common patterns: review mining, invoice parsing, lead enrichment, spec extraction.
for more, check the GitHub repo: github.com/typedef-ai/f...
for more, check the GitHub repo: github.com/typedef-ai/f...
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
Auto-prompting via function calling / structured outputs (OpenAI, Anthropic)
Use unnest() and explode() to work with the data—no manual JSON wrangling
September 20, 2025 at 1:38 AM
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
Auto-prompting via function calling / structured outputs (OpenAI, Anthropic)
Use unnest() and explode() to work with the data—no manual JSON wrangling
Most teams hand-roll JSON parsing, brittle regex, and post-hoc validators. That’s slow and error-prone.
With fenic, you keep it declarative.
With fenic, you keep it declarative.
September 20, 2025 at 1:38 AM
Most teams hand-roll JSON parsing, brittle regex, and post-hoc validators. That’s slow and error-prone.
With fenic, you keep it declarative.
With fenic, you keep it declarative.
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.
Think of it as schema-first parsing: you define a Pydantic model; Fenic enforces it and returns structured columns.
September 20, 2025 at 1:38 AM
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.
Think of it as schema-first parsing: you define a Pydantic model; Fenic enforces it and returns structured columns.
Common patterns: doc mining, content ingestion, RAG prep, taxonomy extraction.
for more, including examples and documentation, check: github.com/typedef-ai/f...
for more, including examples and documentation, check: github.com/typedef-ai/f...
September 18, 2025 at 1:38 AM
Common patterns: doc mining, content ingestion, RAG prep, taxonomy extraction.
for more, including examples and documentation, check: github.com/typedef-ai/f...
for more, including examples and documentation, check: github.com/typedef-ai/f...