Dear Tutor, well explained the concept clearly. Thank you. Could you please create a play list with proper ordering of videos, so that we can learn Langchain step-by-step?
Wow, this video provides a fascinating insight into Langchain agents and their capabilities! 🤖 I'm excited to learn more about how agents work under the hood of Link Chain and the endless possibilities they offer for businesses investing in technology, data, and analytics. Looking forward to diving deeper into building custom agents and unlocking their potential! 🚀🔍 #LangtuneAgents #AI #Innovation
What a inspiring Agent topic for me as a beginner. Maybe a question can you make a tutor with more then 1 agent that communicate with each other. Many thanks.
Hello Rabbit Metrics, I am asking here as this is your latest video, I have seen your videos regarding Langchain, I am curious how to optimize inference while using LLMs in Langchain using TensorRT or Onnx Runtime... As in Industries, It's very obvious, to save the time as well as computation cost... In TensorRT while using open source models, we have techniques like quantization and a few more more for that... So In Langchain is there any way to do this?
You might provide a Configuration Service that serves user/customer-specific configuration data to your provider services. Or provide the tokens in a (secured) user directory with custom attributes.
oh I think I get it. The "->" in python function definition denotes adding annotations for the function. The shopify_objects are defined in this annotation in string format, and I guess this info is fed to the LLM as a prompt. Is that about right? Extremely cool!
@@seannam1218 the text you see immediately after the function declaration with the 3 " is a docstring, and you can access through the property ".__doc__" i guess in the langchain source code, it accesses that description this way. yourFunction.__doc__
Thanks a lot, Rabbitmetrics! The video and the demo fulfill well their purpose of explaining LangCham Agents in a simple way!
This is exactly what i needed for my project. thanks a lot!!
Dear Tutor, well explained the concept clearly. Thank you. Could you please create a play list with proper ordering of videos, so that we can learn Langchain step-by-step?
Great, succinct and useful demo. Appreciate it!
Wow, this video provides a fascinating insight into Langchain agents and their capabilities! 🤖 I'm excited to learn more about how agents work under the hood of Link Chain and the endless possibilities they offer for businesses investing in technology, data, and analytics. Looking forward to diving deeper into building custom agents and unlocking their potential! 🚀🔍 #LangtuneAgents #AI #Innovation
Thank you for your video, I want to know if langgraph can replace crewai
What a inspiring Agent topic for me as a beginner. Maybe a question can you make a tutor with more then 1 agent that communicate with each other.
Many thanks.
Question: Due to the looping in Langchain's Agent, is there an excessive consumption of tokens?
Thats super neat !!
Hello , Is the performance and speed of agents superior to that of chains?
An informative video. Is there any way to summarise transcripts using a custom method via agents?
so agents are nothing but a function?
(feel free to correct me if I'm wrong)
Great Video, please improve the audio and soundtrack choice.
Hello Rabbit Metrics, I am asking here as this is your latest video, I have seen your videos regarding Langchain, I am curious how to optimize inference while using LLMs in Langchain using TensorRT or Onnx Runtime... As in Industries, It's very obvious, to save the time as well as computation cost... In TensorRT while using open source models, we have techniques like quantization and a few more more for that... So In Langchain is there any way to do this?
best
Er du tilfældigvis Dansker? 😅
Great tutorial, I am wondering how can we pass the Shopify access token dynamically to tools if we are building a saas?
You might provide a Configuration Service that serves user/customer-specific configuration data to your provider services. Or provide the tokens in a (secured) user directory with custom attributes.
to be frankly,there is no different from crud hard code😂i think we should dig more unique Scenario in business,or langchain is a nice vase
937 Hartmann Parkways
That noise to show the type in the animation kills my ears
this function is too simple... how about you build pandas_dataframe_agent from scratch using this approach?
im early
Hey, Early. Nice to meet you
Awesome tutorial! How did the agent know to pass the keyword "Customer" to the get_shopify_insight function without you explicitly telling it?
Thanks for watching! The agent infers what it needs to pass from the signature of the function get_shopify_insight
oh I think I get it. The "->" in python function definition denotes adding annotations for the function. The shopify_objects are defined in this annotation in string format, and I guess this info is fed to the LLM as a prompt. Is that about right? Extremely cool!
@@seannam1218 the text you see immediately after the function declaration with the 3 " is a docstring, and you can access through the property ".__doc__" i guess in the langchain source code, it accesses that description this way. yourFunction.__doc__