Those are part of LangChain Expression Language, their own way of setting up chain's easily with their components. More on that here python.langchain.com/v0.1/docs/expression_language/get_started/
@nsshing20 сағат бұрын
"very scientific diagram" lol
@lucfaceКүн бұрын
Dude I love your agent vids. Of all the stuff out here they have been the most helpful because your breakdowns are complete and articulated well. Thanks, man. PLEASE do more! Ha. I would love some case study ones or different sort of mash up ones that go outside the norm and use idk different kinds of tools and models and trigger all sorts of weird actions. I think these things are legit the first step to robot brains so if that sparks any creativity…. Also brother what did you use to make that 3D graph? And do you have any opinions on graphrag? (not to confuse since the name is similar but subject is not related)
@AdamLucekКүн бұрын
Thanks! I do all my quick diagramming just with app.diagrams.net/ cuz its free and easy. Haven't looked too much into GraphRAG yet!
@Leonid.Shamis2 күн бұрын
Thank you Adam! You have a unique style of presenting those concepts, making them very clear, understandable, and complete. I think LangGraph offers one of the best ways to set up those multi-agent workflows compared with other frameworks (AutoGen, CrewAI, AgentScope, Phidata, Langroid, etc.). The only missing piece is the low-code GUI/IDE option to reliably build such workflows for LangGraph - existing low-code tools (like Flowise, Langflow, etc.) do not yet have good support for LangGraph. Maybe this could be another video idea for you? :)
@AdamLucek2 күн бұрын
I agree! The biggest benefit of LangGraph is that you can be super custom and specific with what you build, but it's also the biggest downside of it. Very high barrier to entry, requires development/python understanding that isn't readily available to everyone with good GenAI/Agent ideas. A clean low-code/no-code gui would certainly be a good middle ground!
@hexbenjamin2 күн бұрын
EXCITED
@ShivNC2 күн бұрын
Hell yeah Adam you’re killing it (although I have no clue what you’re talking about)
@AdamLucek2 күн бұрын
Thanks Shiv 😆
@kaushilkundalia21974 күн бұрын
Loved this video. Great stuff.
@saitejagangapuram74127 күн бұрын
dude, you next video should be comparing the multi agent collbaration framework or patterns
@AdamLucek3 күн бұрын
Multi agent collab video coming soon!
@iainhmunro8 күн бұрын
Does it do Tibetan ?
@Jupurgepen8 күн бұрын
Thanks! You deserve more views.
@Watdooyoumeen9 күн бұрын
Can you integrate your routing node to perplexica the clone of perplexity?
@sveineksdfghjkljhgfd9 күн бұрын
do anybody else get "No good DuckDuckGo Search Result was found" from from DuckDuckGo_Search? i have tried with different versions of ddg..i'm running it from the terminal and not Jupyter Notebook. *edit: Brilliant videos btw!
@JohnSmith-qh4vf11 күн бұрын
on kaggle pls
@genXstream18 күн бұрын
Which would you say is more crucial to analyzing the "correctness" of the language agent tree search result: "blah blah blah" or "yada yada yada"?
@AdamLucek17 күн бұрын
Im more partial to yada yada yada, but I can see the benefits of blah blah blah. Really comes down to your use case and desired blah to yada ratio
@matthewturnerphd18 күн бұрын
Thanks for this video! Several smaller details you emphasized were things I had missed in other tutorials, and really helped me.
@madhudson122 күн бұрын
absolutely fantastic. I've been trying to do something similar today and experienced much of the 'going rogue' - with incorrect special tokens, until I followed your example.
@AdamLucek22 күн бұрын
Glad I could help!
@JoshuaMillerDev22 күн бұрын
I wonder if anyone has went through the thought exercise of how an AI model could benefit from having anyone "fold at home" in order to build it. In other words... instead of the owner (OpenAI, Llama, whatever..) dedicating servers to build a LLM, could it not be distributed such that video cards in PC's around the world contribute idle cycles towards the training? Seems like a good way to have an open sourced model to get off the ground, or build using more tokens. Could even have a reward system (minor) allowing X privileged API access per contribution node or whatever.
@psousa5022 күн бұрын
Hi Adam, thank you very much for your video, it's very helpful. I have one doubt, I thought that Langchain would take care of those special tokens for us when we are using the ChatOllama class, am I wrong?
@AdamLucek22 күн бұрын
From my tests with ChatOllama they did not cover that automatically, so you still need the special tokens to prompt it correctly as of now!
@psousa5018 күн бұрын
@@AdamLucek I'm not sure about that. From the Ollama docs we can see that there is a raw parameter that we can use when we do want to provide those special tokens. Langchain ChatOllama class use the Ollama endpoint (localhost:11434) and it doesn't not specify this parameter, so I think we should not use those tokens when sending a prompt
@vv1nter__23 күн бұрын
And it can be used to communicate in discord?
@user-rl9yz3rg7r23 күн бұрын
Thank you for the wonderful lecture and example of source code. The example source code worked nicely in the local environment, and the test code inserted conveniently in the middle helped me understand the example a lot
@ringpolitiet23 күн бұрын
Very well done, subbed. A perfect complexity project to get into LangGraph.
@TestMyHomeChannel23 күн бұрын
You are an awesome teacher. I am already running almost the same setup, with agents created automatically by another PraisonAI but didn’t fully follow what was going on and many times not working and I didn’t know why. I loved the way you broke down and explained everything. Looking forward to see more videos from you. Best wishes
@OliNorwell23 күн бұрын
Very good video, I'm impressed, you got yourself a new sub. I'm not a massive fan of LangChain but your video style is very easy to follow so I'm looking forward to watching your others too. Great work.
@JEffigy23 күн бұрын
Hey can you please share the miro board link? Or drop it into a high res pdf? AWESOME work btw 👍👍👍
@AdamLucek23 күн бұрын
Here you go! drive.google.com/file/d/1ESnrIy4c5LPOhNHRnn87Cv7DU_i0-_J9/view?usp=sharing
@JoshuaMillerDev23 күн бұрын
I like seeing these. Something to consider is having the web search differentiate between sponsored and non sponsored results. I have not seen anyone tackle that yet. It seems to me that search results and LLM outputs would be more accurate when steering away from sponsored data.
@AdamLucek23 күн бұрын
Good idea!
@JoshuaMillerDev23 күн бұрын
Just FYI, doing what I mentioned could be problematic in a long long run as folks use search less and LLMs more. At some point there is a potential conflict where search engines get nothing from billions + of AI crawling. Not much of a worry, but a good thought exercise.
@WladBlank23 күн бұрын
Interesting concept. I try to force my llms to produce valid json and this would be easier.
24 күн бұрын
Excellent video thank you!
@alejandroGTES24 күн бұрын
Awesome project! Is it possible to use another service as translation rather than Chatgpt that doesn't require a subscription?
@AdamLucek24 күн бұрын
Certainly possible. Translation service could be anything as the sentence string is all thats being passed back and forth. I just used OpenAI for a quick solution, but any service could be substituted in that step.
@alejandroGTES24 күн бұрын
@@AdamLucek Oh nice, I would love to see and updated version with a free alternative.
@amanmeghrajani124 күн бұрын
loving your content, thank you for sharing this. learning a lot! would you be interested in making a video to show how to deploy these models and have access to them from inputs like whatsapp chat, email? would be super helpful
@GeorgAubele24 күн бұрын
Thanks for the really interesting and well done clip. I get an error at the end, when testing the whole thing: It says, it has a ratelimit exception in the duckduckgo_search module: 202 Ratelimit.
@AdamLucek24 күн бұрын
Seems like something is broken in the connection between DuckDuckGo and LangChain's integration... getting this error too. You can use Tavily for the time being, replacing the duckduckgo lines, although you may need a Tavily API key. from langchain_community.tools.tavily_search import TavilySearchResults web_search_tool = TavilySearchResults(include_raw_content=True, search_depth='advanced', max_results=5) Will look into other ways to get around this.
@AdamLucek24 күн бұрын
Found a fix! Somethings up with the recent version of the python API. Running `pip install -U duckduckgo_search==5.3.0b4` and then restarting your environment fixed it for me :)
@GeorgAubele23 күн бұрын
@@AdamLucek Thanks, will try it
@GeorgAubele19 күн бұрын
@@AdamLucek Thanks! That did the trick! Even a new verion 5.3.1 does have that bug ... :/
@jimlynch939024 күн бұрын
I really enjoyed this video. I've seen lots of "how to" vids WRT programming using local LLMs but this is by far the best one I've viewed. I often get lost and have to re read some of the steps however you moved along at exactly the right pace for me and explained pretty much all of the questions I was dreaming up during the view. Thank you! Ollama does have function calling but this method seems to be more logical and easier to understand.
@GlobalAiServices25 күн бұрын
What's the point, SORA is not released yet. Just a waste of time!
@ringpolitiet23 күн бұрын
Why are you here?
@szpiegzkrainydeszczowcow847625 күн бұрын
Great job. Subscribing. Any chance you would make some video on long term memory in vector db? greetings
@dr.mikeybee25 күн бұрын
Nice work
@bharaths560325 күн бұрын
Kalakitta nanba!
@MEvansMusic25 күн бұрын
what is used for scoring?
@nilamara762025 күн бұрын
Really impressive that combination of these 3. But to have a perfect loop how to deal with an input audio (voice) in real time before start speaking to respond ? And another question the generating audio at last could be an emulation of your microphone ?
@AdamLucek25 күн бұрын
As this is currently setup, the streaming STT from AssemblyAI will transcribe, and then output a final "sentence" after some variable breakpoint of no speech. It is with this output that I process the rest of it into speech. As this is more an MVP, more could be done within that intermediary step (checks for speech, pauses, etc) that could change how and when the translated speech is played back, or even done as a separate process, not sequentially like this is happening!
@camilocampos590025 күн бұрын
awesome dude, I've been working with llama3 and langgraph to see if you can use tools with llama3 but you did it, you are great, cheers.
@AdamLucek25 күн бұрын
Glad I could help!
@rajesharora2725 күн бұрын
Awesome stuff!
@lavamonkeymc25 күн бұрын
Question: If I have a data preprocessing agent that has access to around 20 preprocessing tools, what is the best way to go about executing them on a pandas data frame? Do I have the data frame in the State and then pass that input in the function? Does the agent need to have access to that data frame or can we abstract that?
@AdamLucek25 күн бұрын
I imagine it could be abstracted out. A lot of the processing you can do with a langgraph setup similar to these doesn't necessarily need an LLM touch at the computation/function step- could use the LLM for logic based routing to the right node function that is already defined to affect a pre set dataframe
@xollob25 күн бұрын
Hi Adam, great work. I've been struggling trying to evaluate the different agent frameworks, autogen, crewai VRSEN and on and on. langchain etc. seems to be more logical as we can see what's happening and is more predictable. Would it be possible to get the Miro you built for this presentation? Greetings from France.
@AdamLucek23 күн бұрын
Here you go! drive.google.com/file/d/1ESnrIy4c5LPOhNHRnn87Cv7DU_i0-_J9/view?usp=sharing
@xollob17 күн бұрын
@@AdamLucek Thank you so much Adam.
@ricardoaltamiranomarquez75326 күн бұрын
¿Puedes compartir con nosotros tu presentación de Miro?, Great Job
@AdamLucek23 күн бұрын
Here you go! drive.google.com/file/d/1ESnrIy4c5LPOhNHRnn87Cv7DU_i0-_J9/view?usp=sharing
@ricardoaltamiranomarquez75323 күн бұрын
@@AdamLucek thank you very much, you are very good
@sanesanyo26 күн бұрын
Great work, thanks for this🙏. There is another agentic approach which is called self discovery. Would be cool if you cover that as well 😊.
@prafulmaka771028 күн бұрын
Good explanation!
@GriffinBrown-tq9jz28 күн бұрын
Well done! Thank you, sir
@tyler-morrison28 күн бұрын
This breakdown is insanely helpful 👏 I’ve been working as a Web Engineer for > 10 yrs and recently started learning about AI/ML. I began my career as a self-taught dev in the good ol’ jQuery days, but my lack of CS fundamentals is starting to come back an bite me. These architectural diagrams are incredibly useful for breaking down high-level concepts.
@AdamLucek27 күн бұрын
Glad you found this helpful! Everything I record and share is all self-taught as well, I've got no formal CS background- I just think the topic is interesting and worth sharing!
@tk015025 күн бұрын
Would you share your slides? So helpful!
@caokang495729 күн бұрын
Thank you for sharing! Great summary.
@PRColacino29 күн бұрын
Great video! Could you share the code?
@AdamLucek27 күн бұрын
Thanks! The code comes from LangChain's series on LangGraph, linked in the description. Here's a direct link to their repo github.com/langchain-ai/langgraph/tree/main/examples
@pinkmatter848829 күн бұрын
Your channel has been very valuable today to get me situated on how to get the hang of LLM use. I can now start thinking about project ideas to get some practice. Thank you very much !
@cmthimmaiahАй бұрын
Very nicely done, thank you for such a good preseentation.