From 4ac8e22a3b67e79cdcb8a8f93bd8df11d7bfba61 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=D0=A0=D0=B8=D0=BD=D0=B0=D1=80=20=D0=9C=D0=B8=D1=80=D0=B7?= =?UTF-8?q?=D0=B0=D0=B3=D0=B8=D1=82=D0=BE=D0=B2?= Date: Thu, 18 Jun 2026 09:54:44 +0000 Subject: [PATCH] Solution published: update README.md --- README.md | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-) diff --git a/README.md b/README.md index 3908416..6b8cd90 100644 --- a/README.md +++ b/README.md @@ -1,14 +1,15 @@ -# LangGraph research brief generator +# LangGraph Comparison Agent ## Overview -This repository contains a LangGraph agent that generates a connected research brief on a single topic. The agent: +This repository contains a **LangGraph** agent that, given three entities (e.g. vector databases, frameworks, or products), builds a comparative review. The agent: -1. Uses an LLM to generate concise section headings for the brief. -2. For each heading, performs a Tavily web search to fetch relevant content. -3. Aggregates the sections into a single Markdown brief with a summary. +1. **Plans criteria** – LLM generates 3‑5 comparison criteria based on the entities. +2. **Researches each entity‑criterion pair** – uses **Tavily** web search to fetch a short note for each pair. +3. **Builds a Markdown table** – rows are criteria, columns are entities. +4. **Produces a verdict** – LLM gives a concise recommendation. -The agent is implemented in `src/main.py` and can be run from the command line. +The final output is a Markdown table followed by a verdict paragraph. ## Requirements @@ -16,7 +17,7 @@ The agent is implemented in `src/main.py` and can be run from the command line. pip install -r requirements.txt ``` -The following environment variables must be set: +Environment variables: - `OPENAI_API_KEY` – key for the OpenAI model used by LangChain. - `TAVILY_API_KEY` – key for the Tavily API. @@ -24,11 +25,11 @@ The following environment variables must be set: ## Usage ```bash -# Default demo – generates a brief on "Artificial Intelligence" +# Default demo – compares Chroma, FAISS, Qdrant python -m src.main -# Custom topic -python -m src.main "Quantum Computing" +# Custom entities +python -m src.main "Chroma,FAISS,Qdrant" ``` -The script prints the generated brief in Markdown format. +The script prints the comparison table and verdict in Markdown format.