DeepRob: Deep Learning for Robot Perception – University of Michigan, 2023 An ongoing class on neural network based approaches for robot perception. The class covers advanced topics in computer vision & emerging topics in deep robotic perception. Videos:
https://
youtube.com/playlist?list=
PLf_SmXJixhnXoMs0Qvxe500BrjfbIOwSg
…
AGENTS
-
DeepRob: Deep Learning for Robot Perception University of Michigan
By
–
-
LangChain Introduces Tracing Feature for Chain Debugging
By
–
We’re excited to announce a new feature in LangChain: Tracing! By enabling tracing in LangChain, you’ll be able to more effectively inspect and debug your complex chain/agent runs. Blog: https://
blog.langchain.dev/tracing/
Docs: https://
langchain.readthedocs.io/en/latest/trac
ing.html
… -
Optimize ability to ego ratio with coworkers
By
–
With co-workers, optimize the ability to ego ratio.
-
Browser Controller Generating Selenium Code via AI
By
–
Browser controller that generates Selenium—similar to @natfriedman's natbot or @AdeptAILabs https://t.co/WCmuFKB55f
— Alexandr Wang (@alexandr_wang) 30 janvier 2023Browser controller that generates Selenium—similar to @natfriedman
's natbot or @AdeptAILabs -
LangChain Search Classes Enhanced with Detailed Metadata Results
By
–
More detailed search results @EnricoShippole added a method to the search classes to return more detailed search info: title, snippet, link WebGPT? Google Search: https://
langchain.readthedocs.io/en/latest/modu
les/utils/examples/google_search.html#metadata-results
… Bing Search: https://
langchain.readthedocs.io/en/latest/modu
les/utils/examples/bing_search.html#metadata-results
… -
Tool Decorator Simplifies Agent Function Creation
By
–
Decorator for creating tools Thanks to @jxnlco you can now create a Tool from a function with a simple decorator. Easier than ever to have agents start interacting with arbitrary functions! Documentation: https://
langchain.readthedocs.io/en/latest/modu
les/agents/examples/custom_tools.html#using-the-tool-decorator
… -
SQL Database Agent Optimization via Prompt Engineering
By
–
yes new ones! see the thread for an example of an agent optimized (via the prompt) for interacting with a sql db
-
Serialized AI Agents: Should Tools Be Included Together?
By
–
will depend on what tools you use with it! these serialized agents do NOT include the specific tools (yet), they're just the agent logic and rely on users to pass intools do you think it would be more useful to have agents + tools serialized together?
