Data retrieval is a fundamental challenge in AI systems, and the approaches for solving it are still evolving. Vector search was an early answer to the retrieval problem, but the rise of agentic systems has raised the stakes considerably. Agents issue queries at machine speed, decompose complex questions into parallel searches, and require retrieval infrastructure that can keep pace without becoming prohibitively expensive.



<a href="https://www.trychroma.com/">Chroma</a> is a company building open source infrastructure for AI applications, best known for its widely used database of the same name.  The company also published the influential Context Rot paper, which documented how model performance degrades as context window utilization increases, and recently released Context One, a 20 billion parameter retrieval sub-agent trained to do agentic search at frontier model quality but at an order of magnitude lower cost and higher speed.



<a href="https://x.com/HammadTime">Hammad Bashir</a> is the CTO of Chroma, with a background spanning machine learning, computer vision, and data systems. In this episode, Hammad joins Gregor Vand to discuss the origins of ChromaDB, our current understanding of context rot, why a purpose-built small model can match frontier models on search tasks, the philosophy behind Chroma’s open source approach, and where the company sees AI data infrastructure heading. Sponsorship inquiries: <a href="mailto:sponsor@softwareengineeringdaily.com">sponsor@softwareengineeringdaily.com</a>




The post <a href="https://softwareengineeringdaily.com/podcasts/chroma-and-agentic-retrieval/">Chroma and Agentic Retrieval</a> appeared first on <a href="https://softwareengineeringdaily.com">Software Engineering Daily</a>.

Data retrieval is a fundamental challenge in AI systems, and the approaches for solving it are still evolving. Vector search was an early answer to the retrieval problem, but the rise of agentic systems has raised the stakes considerably. Agents issue queries at machine speed, decompose complex questions into parallel searches, and require retrieval infrastructure that can keep pace without becoming prohibitively expensive. Chroma is a company building open source infrastructure for AI applications, best known for its widely used database of the same name. The company also published the influential Context Rot paper, which documented how model performance degrades as context window utilization increases, and recently released Context One, a 20 billion parameter retrieval sub-agent trained to do agentic search at frontier model quality but at an order of magnitude lower cost and higher speed. Hammad Bashir is the CTO of Chroma, with a background spanning machine learning, computer vision, and data systems. In this episode, Hammad joins Gregor Vand to discuss the origins of ChromaDB, our current understanding of context rot, why a purpose-built small model can match frontier models on search tasks, the philosophy behind Chroma’s open source approach, and where the company sees AI data infrastructure heading. Sponsorship inquiries: sponsor@softwareengineeringdaily.com The post Chroma and Agentic Retrieval appeared first on Software Engineering Daily.

Data retrieval is a fundamental challenge in AI systems, and the approaches for solving it are still evolving. Vector search was an early answer to the retrieval problem, but the rise of agentic systems has raised the stakes considerably. Agents issue queries at machine speed, decompose complex questions into parallel searches, and require retrieval infrastructure that can keep pace without becoming prohibitively expensive.



<a href="https://www.trychroma.com/" rel="noopener noreferrer">Chroma</a> is a company building open source infrastructure for AI applications, best known for its widely used database of the same name. &nbsp;The company also published the influential Context Rot paper, which documented how model performance degrades as context window utilization increases, and recently released Context One, a 20 billion parameter retrieval sub-agent trained to do agentic search at frontier model quality but at an order of magnitude lower cost and higher speed.



<a href="https://x.com/HammadTime" rel="noopener noreferrer">Hammad Bashir</a> is the CTO of Chroma, with a background spanning machine learning, computer vision, and data systems. In this episode, Hammad joins Gregor Vand to discuss the origins of ChromaDB, our current understanding of context rot, why a purpose-built small model can match frontier models on search tasks, the philosophy behind Chroma’s open source approach, and where the company sees AI data infrastructure heading. Sponsorship inquiries: <a href="mailto:sponsor@softwareengineeringdaily.com" rel="noopener noreferrer">sponsor@softwareengineeringdaily.com</a>




The post <a href="https://softwareengineeringdaily.com/podcasts/chroma-and-agentic-retrieval/" rel="noopener noreferrer">Chroma and Agentic Retrieval</a> appeared first on <a href="https://softwareengineeringdaily.com" rel="noopener noreferrer">Software Engineering Daily</a>.

Chroma and Agentic Retrieval

Many real-world processes produce data as a continuous stream rather than as isolated records. Sensor readings, financial markets, and application telemetry all generate data this way. This kind of time-series data has a distinctive shape. It’s written far more often than it is updated, it accumulates continuously, and it is usually queried across ranges of time. Time-series databases are built specifically for this kind of workload.



<a href="https://www.tigerdata.com/timescaledb">TimescaleDB</a> is an open source database from <a href="https://www.tigerdata.com/">Tiger Data</a> that adds time-series capabilities to PostgreSQL. It’s implemented as a Postgres extension, so it introduces new functionality while preserving standard Postgres behavior and SQL. This lets a single Postgres-based system handle both transactional and analytical workloads without splitting data across multiple tools.



<a href="https://www.linkedin.com/in/bpurcell/" data-type="link" data-id="https://www.linkedin.com/in/bpurcell/">Brandon Purcell</a> is the Director of Product Management at Tiger Data. In this episode, Brandon joins Kevin Ball to discuss why time-series data breaks conventional databases, how hypertables and Hypercore scale Postgres, zero-copy database forking for agent-based workflows, and much more. Full Disclosure: This episode is sponsored by Tiger Data Sponsorship inquiries: <a href="mailto:sponsor@softwareengineeringdaily.com">sponsor@softwareengineeringdaily.com</a>
The post <a href="https://softwareengineeringdaily.com/podcasts/scaling-time-series-workloads-on-postgres/">Scaling Time-Series Workloads on Postgres</a> appeared first on <a href="https://softwareengineeringdaily.com">Software Engineering Daily</a>.

Many real-world processes produce data as a continuous stream rather than as isolated records. Sensor readings, financial markets, and application telemetry all generate data this way. This kind of time-series data has a distinctive shape. It’s written far more often than it is updated, it accumulates continuously, and it is usually queried across ranges of time. Time-series databases are built specifically for this kind of workload. TimescaleDB is an open source database from Tiger Data that adds time-series capabilities to PostgreSQL. It’s implemented as a Postgres extension, so it introduces new functionality while preserving standard Postgres behavior and SQL. This lets a single Postgres-based system handle both transactional and analytical workloads without splitting data across multiple tools. Brandon Purcell is the Director of Product Management at Tiger Data. In this episode, Brandon joins Kevin Ball to discuss why time-series data breaks conventional databases, how hypertables and Hypercore scale Postgres, zero-copy database forking for agent-based workflows, and much more. Full Disclosure: This episode is sponsored by Tiger Data Sponsorship inquiries: sponsor@softwareengineeringdaily.com The post Scaling Time-Series Workloads on Postgres appeared first on Software Engineering Daily.

Many real-world processes produce data as a continuous stream rather than as isolated records. Sensor readings, financial markets, and application telemetry all generate data this way. This kind of time-series data has a distinctive shape. It’s written far more often than it is updated, it accumulates continuously, and it is usually queried across ranges of time. Time-series databases are built specifically for this kind of workload.



<a href="https://www.tigerdata.com/timescaledb" rel="noopener noreferrer">TimescaleDB</a> is an open source database from <a href="https://www.tigerdata.com/" rel="noopener noreferrer">Tiger Data</a> that adds time-series capabilities to PostgreSQL. It’s implemented as a Postgres extension, so it introduces new functionality while preserving standard Postgres behavior and SQL. This lets a single Postgres-based system handle both transactional and analytical workloads without splitting data across multiple tools.



<a href="https://www.linkedin.com/in/bpurcell/" rel="noopener noreferrer">Brandon Purcell</a> is the Director of Product Management at Tiger Data. In this episode, Brandon joins Kevin Ball to discuss why time-series data breaks conventional databases, how hypertables and Hypercore scale Postgres, zero-copy database forking for agent-based workflows, and much more. Full Disclosure: This episode is sponsored by Tiger Data Sponsorship inquiries: <a href="mailto:sponsor@softwareengineeringdaily.com" rel="noopener noreferrer">sponsor@softwareengineeringdaily.com</a>
The post <a href="https://softwareengineeringdaily.com/podcasts/scaling-time-series-workloads-on-postgres/" rel="noopener noreferrer">Scaling Time-Series Workloads on Postgres</a> appeared first on <a href="https://softwareengineeringdaily.com" rel="noopener noreferrer">Software Engineering Daily</a>.

Scaling Time-Series Workloads on Postgres

“The world is increasingly disconnected, if you think about dealing with things like mobile devices that flap in and out of connectedness.” 
 
Continue reading…

“The world is increasingly disconnected, if you think about dealing with things like mobile devices that flap in and out of connectedness.” Continue reading…

“The world is increasingly disconnected, if you think about dealing with things like mobile devices that flap in and out of connectedness.” 
 
Continue reading…

Distributed NoSQL Databases with Jon Meredith

“I found Spark and I was really excited because I’m a functional programming nerd, and it was written in Scala.” 
 
Continue reading…

“I found Spark and I was really excited because I’m a functional programming nerd, and it was written in Scala.” Continue reading…

“I found Spark and I was really excited because I’m a functional programming nerd, and it was written in Scala.” 
 
Continue reading…

Spark in Practice with Holden Karau

"It’s a great world to be a developer in. If you’re a developer today, you have so many tools and so many options." 
 
Continue reading…

"It’s a great world to be a developer in. If you’re a developer today, you have so many tools and so many options." Continue reading…

"It’s a great world to be a developer in. If you’re a developer today, you have so many tools and so many options." 
 
Continue reading…

Apache Drill with Tomer Shiran

“I really think that data science is like design in the sense that it’s a way of thinking.” 
 
Continue reading…

“I really think that data science is like design in the sense that it’s a way of thinking.” Continue reading…

“I really think that data science is like design in the sense that it’s a way of thinking.” 
 
Continue reading…

Data Science with Srini Kadamati

“The more you’re comfortable with this idea that everything is going to fail, the more you realize that it's a natural process of distributed systems, and it helps you write and architect better code.” 
 
Continue reading…

“The more you’re comfortable with this idea that everything is going to fail, the more you realize that it's a natural process of distributed systems, and it helps you write and architect better code.” Continue reading…

“The more you’re comfortable with this idea that everything is going to fail, the more you realize that it's a natural process of distributed systems, and it helps you write and architect better code.” 
 
Continue reading…

Architecting Distributed Databases with Fangjin Yang

“Every vendor will advertise that their system is better – that’s nice, I understand you need to sell your thing, but what am I gaining as a user and what am I sacrificing as a user by choosing your product?” 
 
Continue reading…

“Every vendor will advertise that their system is better – that’s nice, I understand you need to sell your thing, but what am I gaining as a user and what am I sacrificing as a user by choosing your product?” Continue reading…

“Every vendor will advertise that their system is better – that’s nice, I understand you need to sell your thing, but what am I gaining as a user and what am I sacrificing as a user by choosing your product?” 
 
Continue reading…

Distributed Systems with Alvaro Videla

“Systems are giving up correctness for latency, and I’m arguing that stream processing systems have to be designed to allow the user to pick the tradeoffs that the application needs." 
 
Continue reading…

“Systems are giving up correctness for latency, and I’m arguing that stream processing systems have to be designed to allow the user to pick the tradeoffs that the application needs." Continue reading…

“Systems are giving up correctness for latency, and I’m arguing that stream processing systems have to be designed to allow the user to pick the tradeoffs that the application needs." 
 
Continue reading…

Demystifying Stream Processing with Neha Narkhede

“We still need to see in the long run how much of community and industry adoption is there. Because at the end of the day, these are the single two most important things which define and determine the success of any platform.” 
 
Continue reading…

“We still need to see in the long run how much of community and industry adoption is there. Because at the end of the day, these are the single two most important things which define and determine the success of any platform.” Continue reading…

“We still need to see in the long run how much of community and industry adoption is there. Because at the end of the day, these are the single two most important things which define and determine the success of any platform.” 
 
Continue reading…

Stream Processing with Satish Mittal

“We want people to be able to pick up whatever tool it is and really push themselves to get something done with it in a short amount of time, because that’s ultimately what they need to do as a data engineer in the industry.” 
 
Continue reading…

“We want people to be able to pick up whatever tool it is and really push themselves to get something done with it in a short amount of time, because that’s ultimately what they need to do as a data engineer in the industry.” Continue reading…

“We want people to be able to pick up whatever tool it is and really push themselves to get something done with it in a short amount of time, because that’s ultimately what they need to do as a data engineer in the industry.” 
 
Continue reading…

Data Engineering with David Drummond and Austin Ouyang

“It’s a great time to be an engineer.” 
 
Information retrieval and search engineering are becoming more intertwined with machine learning and natural language processing, leading to a wealth of work to be done in the field. 
 
Continue reading…

“It’s a great time to be an engineer.” Information retrieval and search engineering are becoming more intertwined with machine learning and natural language processing, leading to a wealth of work to be done in the field. Continue reading…

“It’s a great time to be an engineer.” 
 
Information retrieval and search engineering are becoming more intertwined with machine learning and natural language processing, leading to a wealth of work to be done in the field. 
 
Continue reading…

Share Software Engineering Daily

Sign up to save your podcasts

Software Engineering Daily

Software Engineering Daily episodes

About Software Engineering Daily

More shows like Software Engineering Daily

TechLab by Bol