add: basic workflow to check code format and lint

.github/workflows/tests.yml

@@ -0,0 +1,21 @@
+name: Tests
+on:
+  pull_request:
+    paths:
+      - .github/workflows/tests.yml
+      - medrag_multi_modal/**
+      - pyproject.toml
+
+jobs:
+  code-format:
+    name: check code format using black
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: psf/black@stable
+  lint:
+    name: Check linting using ruff
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: chartboost/ruff-action@v1

medrag_multi_modal/document_loader/load_image.py

@@ -3,11 +3,11 @@ import os
 from typing import Optional
 
 import rich
-import wandb
 import weave
 from pdf2image.pdf2image import convert_from_path
 from PIL import Image
 
+import wandb
 from medrag_multi_modal.document_loader.text_loader import PyMuPDF4LLMTextLoader
 
 

test.ipynb

@@ -0,0 +1,209 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import rich\n",
+    "import weave\n",
+    "from dotenv import load_dotenv\n",
+    "\n",
+    "from medrag_multi_modal.retrieval import BM25sRetriever"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Logged in as Weights & Biases user: geekyrakshit.\n",
+      "View Weave data at https://wandb.ai/ml-colabs/medrag-multi-modal/weave\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<weave.trace.weave_client.WeaveClient at 0x31bb4b200>"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "load_dotenv()\n",
+    "weave.init(project_name=\"ml-colabs/medrag-multi-modal\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Using wandb-core as the SDK backend. Please refer to https://wandb.me/wandb-core for more information.\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m:   7 of 7 files downloaded.  \n"
+     ]
+    }
+   ],
+   "source": [
+    "retriever = BM25sRetriever.from_wandb_artifact(\n",
+    "    index_artifact_address=\"ml-colabs/medrag-multi-modal/grays-anatomy-bm25s:v2\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "6247f921c889469283505348967807da",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Split strings:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "0ccb25cf58c84023846d68561962adc5",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Stem Tokens:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "d2eddb186fac447d8e7dc8f185ce7c86",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "BM25S Retrieve:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "results = retriever.retrieve(query=\"What are Ribosomes?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">&lt;</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff; font-weight: bold\">class</span><span style=\"color: #000000; text-decoration-color: #000000\"> </span><span style=\"color: #008000; text-decoration-color: #008000\">'dict'</span><span style=\"font-weight: bold\">&gt;</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[1m<\u001b[0m\u001b[1;95mclass\u001b[0m\u001b[39m \u001b[0m\u001b[32m'dict'\u001b[0m\u001b[1m>\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "rich.print(list(list(results['results'])[0])[0])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "2"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[0.4504720866680145, 0.3982057571411133]"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "results[\"scores\"].flatten().tolist()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}