New LangChain XML Agents

  Рет қаралды 7,221

James Briggs

James Briggs

Күн бұрын

Пікірлер: 11
@XavierNV
@XavierNV 9 ай бұрын
Great video as always, have been following you for a while now and always appreciate the knowledge you share for free! You have helped me go from a beginner in LLMs to embedding advanced agents into my applications, cannot thank you enough!
@jamesbriggs
@jamesbriggs 9 ай бұрын
Thanks I appreciate the comment, I'm happy it's helped!
@jawdridi
@jawdridi 9 ай бұрын
Hey, will you be doing tutorials about the new Self-reflective RAG? :)
@gfxmrsaltman
@gfxmrsaltman 9 ай бұрын
Hey James, really appreaciate your videos. I am currently working on a Project that is supposed to be a RAG Chatbot with multiple Website(s)-Data. The "problem" I am facing is that I need the assistant/bot to be able to make a "knowledge" switch, depending on the context of the conversation. Do you have any idea, how I could implement that? The additional data is stored in Chroma Vectorstore(s). I could also think of using the chunk metadata for that purpose but I wanted to know what you would do/recommend in this kind of situation. Cheers
@priyanshugarg6175
@priyanshugarg6175 8 ай бұрын
New to GenAI. I wanted to know whether LangChain is used in production ?
@jamesbriggs
@jamesbriggs 8 ай бұрын
Yeah I’ve seen it used, it typically won’t be the *only* thing and there’s often a lot of tweaking required, but it’s used in prod
@dikshyakasaju7541
@dikshyakasaju7541 9 ай бұрын
I tried it with other models too but it didn't work as the documentation suggested this: Use with regular LLMs, not with chat models. Is it because Anthropic models are good at reasoning/writing XML?
@jamesbriggs
@jamesbriggs 9 ай бұрын
yeah they've been trained to do function calling / tool usage via XML tags - I find that comment in the docs odd, as they recommend using with Anthropic models, but Anthropic models at all chat LLMs afaik (maybe Claude 1 is not?) - but in any case, it works well!
@benoAI
@benoAI 9 ай бұрын
Can we use XML Agents together with chain of thought prompting (ReAct)? If anyone has tried this out, please share your notebook -- much appreciated!
@jamesbriggs
@jamesbriggs 9 ай бұрын
I don't know about using over many iterations, but for single tool usage this has worked as a replacement of ReAct for me
@Lampshadx
@Lampshadx 9 ай бұрын
you can just edit the prompt that you pass in create_xml_agent to use a ReAct style prompt. That's what I have been doing, otherwise, it often use the tool when it doesnt need to
LangGraph 101: it's better than LangChain
32:26
James Briggs
Рет қаралды 83 М.
Local LangGraph Agents with Llama 3.1 + Ollama
47:55
James Briggs
Рет қаралды 10 М.
МЕНЯ УКУСИЛ ПАУК #shorts
00:23
Паша Осадчий
Рет қаралды 1,4 МЛН
Happy birthday to you by Secret Vlog
00:12
Secret Vlog
Рет қаралды 6 МЛН
Triple kill😹
00:18
GG Animation
Рет қаралды 18 МЛН
How Much Tape To Stop A Lamborghini?
00:15
MrBeast
Рет қаралды 130 МЛН
LangChain vs. LlamaIndex - What Framework to use for RAG?
16:51
Coding Crash Courses
Рет қаралды 18 М.
NEW Claude 3.5 UPDATE: Amazing SEO content (Full tutorial)
14:35
Nex Gen AI
Рет қаралды 2,1 М.
Prompt Templates for GPT 3.5 and other LLMs - LangChain #2
22:57
James Briggs
Рет қаралды 56 М.
LangChain Agents Deep Dive with GPT 3.5 - LangChain #7
32:17
James Briggs
Рет қаралды 57 М.
LangGraph Deep Dive: Build Better Agents
46:13
James Briggs
Рет қаралды 28 М.
ADVANCED Python AI Agent Tutorial - Using RAG
40:59
Tech With Tim
Рет қаралды 151 М.
Streaming for LangChain Agents + FastAPI
27:42
James Briggs
Рет қаралды 32 М.
From RAG to Knowledge Assistants
27:29
LlamaIndex
Рет қаралды 23 М.
Reflection Agents
21:11
LangChain
Рет қаралды 25 М.
МЕНЯ УКУСИЛ ПАУК #shorts
00:23
Паша Осадчий
Рет қаралды 1,4 МЛН