lab 5
Browse files- Introduction_to_LangGraph_for_Agents_Assignment_Version.ipynb +0 -0
- README.md +82 -11
- pyproject.toml +16 -0
- uv.lock +0 -0
Introduction_to_LangGraph_for_Agents_Assignment_Version.ipynb
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
README.md
CHANGED
|
@@ -1,11 +1,82 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
<p align = "center" draggable=”false” ><img src="https://github.com/AI-Maker-Space/LLM-Dev-101/assets/37101144/d1343317-fa2f-41e1-8af1-1dbb18399719"
|
| 2 |
+
width="200px"
|
| 3 |
+
height="auto"/>
|
| 4 |
+
</p>
|
| 5 |
+
|
| 6 |
+
## <h1 align="center" id="heading">Session 5: Our First Agent with LangGraph</h1>
|
| 7 |
+
|
| 8 |
+
| 🤓 Pre-work | 📰 Session Sheet | ⏺️ Recording | 🖼️ Slides | 👨💻 Repo | 📝 Homework | 📁 Feedback |
|
| 9 |
+
|:-----------------|:-----------------|:-----------------|:-----------------|:-----------------|:-----------------|:-----------------|
|
| 10 |
+
| [Session 5: Pre-Work](https://www.notion.so/Session-5-Agents-with-LangGraph-1c8cd547af3d81068e44d4e4b901a9a8?pvs=4#1c8cd547af3d81578bedd1d2b11ab888)| [Session 5: Agents with LangGraph](https://www.notion.so/Session-5-Agents-with-LangGraph-1c8cd547af3d81068e44d4e4b901a9a8) | [Recording](https://us02web.zoom.us/rec/play/YvHRbOKYx8QDcTMwli7QjH-npGauB8wkk2gcN7ax7TV_oxQZbPRPdyxUebtH91uVQ8lRgCbP6u0iicmP.Vvroz4VC2XA7DILn?accessLevel=meeting&canPlayFromShare=true&from=my_recording&continueMode=true&componentName=rec-play&originRequestUrl=https%3A%2F%2Fus02web.zoom.us%2Frec%2Fshare%2F-fJk79tgwkAw3gJS0V69OeDvOUJ0EUE0qgOFey9-1uJPnL6oNT6vLmVygOWHl-JV.mYe1JWztYuHqsYWx) (ck*A3y%t) | [Session 5: Agents](https://www.canva.com/design/DAGjaRyDT1Y/Sy7YaHwHOc19gomlhpq7hw/edit?utm_content=DAGjaRyDT1Y&utm_campaign=designshare&utm_medium=link2&utm_source=sharebutton)| You Are Here!| [Session 5 Assignment: Agents with LangGraph](https://forms.gle/bA9BN2bgNLMNB9HXA)| [AIE6 Feedback 4/15](https://forms.gle/Fgb5K4PDKokvtX787)
|
| 11 |
+
|
| 12 |
+
|
| 13 |
+
In today's assignment, we'll be creating an Agentic LangChain RAG Application.
|
| 14 |
+
|
| 15 |
+
- 🤝 Breakout Room #1:
|
| 16 |
+
1. Install required libraries
|
| 17 |
+
2. Set Environment Variables
|
| 18 |
+
3. Creating our Tool Belt
|
| 19 |
+
4. Creating Our State
|
| 20 |
+
5. Creating and Compiling A Graph!
|
| 21 |
+
|
| 22 |
+
- 🤝 Breakout Room #2:
|
| 23 |
+
- Part 1: LangSmith Evaluator:
|
| 24 |
+
1. Creating an Evaluation Dataset
|
| 25 |
+
2. Adding Evaluators
|
| 26 |
+
- Part 2:
|
| 27 |
+
3. Adding Helpfulness Check and "Loop" Limits
|
| 28 |
+
4. LangGraph for the "Patterns" of GenAI
|
| 29 |
+
|
| 30 |
+
### Advanced Build
|
| 31 |
+
|
| 32 |
+
You are tasked to create an agent with 3 tools that can research a specific domain of your choice.
|
| 33 |
+
|
| 34 |
+
You must deploy the resultant agent with a Chainlit (or Custom) frontend.
|
| 35 |
+
|
| 36 |
+
## Homework
|
| 37 |
+
How Does the Model Determine Which Tool to Use?
|
| 38 |
+
Similar to any other model “decision” by generating tokens! Using the tools description + query the llm will make a decision if the user query could benefit from tool use.
|
| 39 |
+
|
| 40 |
+
Is There a Limit to How Many Times We Can Cycle?
|
| 41 |
+
25
|
| 42 |
+
|
| 43 |
+
How Are Correct Answers Associated with Questions?
|
| 44 |
+
If the answer contains the must mention keywords for a given question based on the list.
|
| 45 |
+
|
| 46 |
+
## Ship 🚢
|
| 47 |
+
|
| 48 |
+
The completed notebook!
|
| 49 |
+
|
| 50 |
+
### Deliverables
|
| 51 |
+
|
| 52 |
+
- A short Loom of the notebook, and a 1min. walkthrough of the application in full
|
| 53 |
+
|
| 54 |
+
## Share 🚀
|
| 55 |
+
|
| 56 |
+
Make a social media post about your final application!
|
| 57 |
+
|
| 58 |
+
### Deliverables
|
| 59 |
+
|
| 60 |
+
- Make a post on any social media platform about what you built!
|
| 61 |
+
|
| 62 |
+
Here's a template to get you started:
|
| 63 |
+
|
| 64 |
+
```
|
| 65 |
+
🚀 Exciting News! 🚀
|
| 66 |
+
|
| 67 |
+
I am thrilled to announce that I have just built and shipped an Agentic Retrieval Augmented Generation Application with LangChain! 🎉🤖
|
| 68 |
+
|
| 69 |
+
🔍 Three Key Takeaways:
|
| 70 |
+
1️⃣
|
| 71 |
+
2️⃣
|
| 72 |
+
3️⃣
|
| 73 |
+
|
| 74 |
+
Let's continue pushing the boundaries of what's possible in the world of AI and question-answering. Here's to many more innovations! 🚀
|
| 75 |
+
Shout out to @AIMakerspace !
|
| 76 |
+
|
| 77 |
+
#LangChain #QuestionAnswering #RetrievalAugmented #Innovation #AI #TechMilestone
|
| 78 |
+
|
| 79 |
+
Feel free to reach out if you're curious or would like to collaborate on similar projects! 🤝🔥
|
| 80 |
+
```
|
| 81 |
+
|
| 82 |
+
> #### NOTE: PLEASE SHUTDOWN YOUR INSTANCES WHEN YOU HAVE COMPLETED THE ASSIGNMENT TO PREVENT UNESSECARY CHARGES.
|
pyproject.toml
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[project]
|
| 2 |
+
name = "05-our-first-agent-with-langgraph"
|
| 3 |
+
version = "0.1.0"
|
| 4 |
+
description = "Add your description here"
|
| 5 |
+
readme = "README.md"
|
| 6 |
+
requires-python = ">=3.13"
|
| 7 |
+
dependencies = [
|
| 8 |
+
"arxiv==2.1.3",
|
| 9 |
+
"duckduckgo-search==5.3.1b1",
|
| 10 |
+
"jupyter==1.1.1",
|
| 11 |
+
"langchain==0.3.15",
|
| 12 |
+
"langchain-community==0.3.15",
|
| 13 |
+
"langchain-openai==0.3.2",
|
| 14 |
+
"langgraph==0.2.67",
|
| 15 |
+
"pandas==2.2.3",
|
| 16 |
+
]
|
uv.lock
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|