{"id":31727167,"url":"https://github.com/zeesshhh0/learning_langgraph","last_synced_at":"2026-04-11T20:40:25.109Z","repository":{"id":317817877,"uuid":"1068481595","full_name":"zeesshhh0/learning_langgraph","owner":"zeesshhh0","description":"This repository contains my code and notes as I learn about Agentic AI using LangGraph","archived":false,"fork":false,"pushed_at":"2025-10-03T07:13:34.000Z","size":82,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-10-03T09:13:52.846Z","etag":null,"topics":["agents","langgraph","langgraph-python","notes"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/zeesshhh0.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-10-02T13:00:35.000Z","updated_at":"2025-10-03T07:13:37.000Z","dependencies_parsed_at":"2025-10-03T09:13:58.136Z","dependency_job_id":"e653dd60-55c0-4da2-bf52-aade4bfc629c","html_url":"https://github.com/zeesshhh0/learning_langgraph","commit_stats":null,"previous_names":["zeesshhh0/learning_langgraph"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/zeesshhh0/learning_langgraph","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zeesshhh0%2Flearning_langgraph","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zeesshhh0%2Flearning_langgraph/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zeesshhh0%2Flearning_langgraph/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zeesshhh0%2Flearning_langgraph/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zeesshhh0","download_url":"https://codeload.github.com/zeesshhh0/learning_langgraph/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zeesshhh0%2Flearning_langgraph/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279000851,"owners_count":26082950,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-09T02:00:07.460Z","response_time":59,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agents","langgraph","langgraph-python","notes"],"created_at":"2025-10-09T06:18:49.887Z","updated_at":"2026-04-11T20:40:25.102Z","avatar_url":"https://github.com/zeesshhh0.png","language":"Jupyter Notebook","readme":"# LangGraph - My Learning Journey\n\nThis repository contains my code and notes as I learn about Agentic AI using LangGraph from the [Agentic AI using LangGraph](https://youtube.com/playlist?list=PLKnIA16_RmvYsvB8qkUQuJmJNuiCUJFPL) playlist by CampusX.\n\n## What I've Learned\n\nI will be checking off the topics as I complete them. You can find the code for each topic in the respective folders.\n\n- [x] Agentic AI Fundamentals\n- [x] LangChain vs. LangGraph\n- [x] Sequential Workflows\n- [x] Parallel Workflows\n- [x] Branching \u0026 Nested Workflows\n- [x] Iterative Workflows\n- [x] Memory (Short-term \u0026 Long-term)\n- [x] Chatbot Application\n---\n\n## Workflows and Projects\n\nThis repository showcases a variety of workflows built with LangGraph, demonstrating different patterns for building AI agents and applications.\n\n### Sequential Workflows\n\nThese workflows execute tasks in a specific order, with the output of one step feeding into the next.\n\n* **Simple LLM Workflow** (`sequential_workflow/simple_llm_workflow.ipynb`): A basic example of a sequential workflow that takes a question from the user, passes it to a large language model (LLM), and returns the answer.\n\n* **Blog Generator Workflow** (`sequential_workflow/blog_generator_workflow.ipynb`): This workflow automates the process of writing a blog post. It takes a title as input, generates a 3-point outline, and then uses both the title and the outline to create the full blog content.\n\n* **BMI Calculator Workflow** (`sequential_workflow/bmi_calculator_workflow.ipynb`): A non-LLM example of a sequential workflow. This simple application takes a user's height and weight, calculates their BMI, and then categorizes the result (e.g., underweight, normal weight, overweight).\n\n### Parallel Workflow\n\nThis workflow executes multiple tasks simultaneously to improve efficiency.\n\n* **UPSC Essay Review Workflow** (`parallel_workflow/upse_essay_review_workflow.ipynb`): This workflow is designed to provide comprehensive feedback on an essay. It evaluates the essay on three different criteria—**language**, **clarity**, and **depth**—in parallel. After all evaluations are complete, it generates a final summary of the feedback and calculates an average score.\n\n### Conditional Workflow\n\nThis workflow uses conditional logic to decide which tasks to execute based on the input.\n\n* **Review Response Workflow** (`conditional_workflow/review_response_workflow.ipynb`): This workflow automates customer review responses. It first analyzes the sentiment of a customer's review.\n    * If the review is **negative**, the workflow first runs a \"diagnosis\" to understand the problem and then generates an appropriate, empathetic reply.\n    * If the review is **positive**, it skips the diagnosis step and immediately generates a positive response.\n\n### Chatbot Application\n\nThis is a simple chatbot built with a Streamlit frontend and a LangGraph backend.\n\n* **`chatbot/chatbot_app.py`**: The user-facing application built with Streamlit that provides a simple chat interface.\n* **`chatbot/chatbot_app_backend.py`**: The backend of the chatbot, powered by LangGraph. It manages the conversation state, allowing the chatbot to remember previous messages in the conversation.\n* **`chatbot/chatbot_v1.py` and `chatbot/chatbot_v1_2.py`**: Earlier, simpler versions of the chatbot that demonstrate the basic principles of building conversational AI with LangGraph.\n\n---\n\n## How to Run These Projects\n\n1.  **Clone the repository:**\n    ```bash\n    git clone https://github.com/zeesshhh0/learning_langgraph.git\n    ```\n2.  **Install dependencies:**\n    ```bash\n    pip install -r requirements.txt\n    ```\n3.  **Explore the Jupyter Notebooks:** The workflows are contained in Jupyter Notebooks (`.ipynb`) in their respective folders. You can run them cell by cell to see how they work.\n4.  **Run the Chatbot:** To run the chatbot application, navigate to the `chatbot` directory and run the following command:\n    ```bash\n    streamlit run chatbot_app.py\n    ```","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzeesshhh0%2Flearning_langgraph","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzeesshhh0%2Flearning_langgraph","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzeesshhh0%2Flearning_langgraph/lists"}