Recap of important links: Blog: https://
blog.langchain.dev/benchmarking-q
uestion-answering-over-csv-data/
… YouTube: https://
youtube.com/watch?v=jGnf4O
hptbA
… Code & data used: https://
github.com/langchain-ai/l
angchain-benchmarks
… We had a lot of fun doing this and learned a lot – we're going to do it for more tasks! Up next: SQL
AI
-
LangChain Benchmarking Question-Answering CSV Data Tasks
By
–
-
Improving AI Agents for CSV Question-Answering Applications
By
–
This started ~2 weeks ago, when I tweeted that we wanted to improve our chains/agents for doing question/answering over CSV data Why? Most QA applications focus on text data, but lots of real world data is in CSVs
-
Building AI Evaluation Datasets from Real User Questions
By
–
The first issue to solve was that we didn't have a dataset to evaluate Rather than try to make up some questions, we put out an example application and logged what questions people asked They also kindly provided feedback, so we could easily identify errors!
-
LangChain Benchmarking Question Answering CSV Data
By
–
Blog: https://
blog.langchain.dev/benchmarking-q
uestion-answering-over-csv-data/
… YouTube: https://
youtube.com/watch?v=jGnf4O
hptbA
… Code & data used: https://
github.com/langchain-ai/l
angchain-benchmarks
… Now for a quick thread: -
Benchmarking Question Answering Over CSV Data
By
–
Benchmarking Question/Answering Over CSV Data Deep dive on improving an application that does question answering over CSV data: 3000 word blog post
30min video
Open sourced eval data
Open sourced code for gathering feedback
Open sourced final agent code -
SKT’s Investment in Anthropic: Fine-Tuning Approach
By
–
To read more about our approach to fine-tuning and SKT’s investment in Anthropic, you can visit our blog:
-
SK Telecom becomes strategic investor and partner in Anthropic
By
–
We are pleased to announce that @SKtelecom (“SKT”), the largest mobile operator in Korea, has become a commercial partner as well as a strategic investor in Anthropic.
-
SKT and Anthropic Partner on Customized Telecom AI Model
By
–
SKT and Anthropic will work together to develop a model that will be customized to best meet the needs of telcos. Using fine-tuning, Anthropic will leverage SKT’s domain experience in order to optimize the model for a wide range of applications.
-
Gen-2 Video AI Extended to 18 Seconds on Browser and iOS
By
–
Extend Gen-2 outputs up to 18s. Now available in browser and coming soon to iOS. pic.twitter.com/lTjxTnVPdr
— Runway (@runwayml) 15 août 2023Extend Gen-2 outputs up to 18s. Now available in browser and coming soon to iOS.
-
SAS Explore Las Vegas: AI and Analytics Conference September
By
–
Booked your flights yet? The countdown is on! Meet us at SAS Explore in Las Vegas to dive into the latest in #AI and analytics http://
2.sas.com/6019Pc1gP | Sept. 11-14 #ExploreSAS