RAG-Anything 教學：在 Colab 中建立支援文字、表格、方程式與圖像的多模態檢索管道

In this tutorial, we build a RAG-Anything workflow and use it to explore how multimodal retrieval works across text, tables, equations, and images. We start by preparing the Colab environment, installing the required packages, and securely entering our OpenAI API key at runtime to keep the notebook practical and safe to run. We then create a synthetic multimodal report, generate a chart and PDF, convert the content into RAG-Anything’s direct content_list format, and insert it into the retrieval system. As we move through the tutorial, we configure clean OpenAI-based chat, vision, and embedding functions, initialize RAG-Anything, and test different retrieval modes such as naive, local, global, and hybrid. Installing RAG-Anything Dependencies Copy CodeCopiedUse a different Browserimport os import re import sys import json import time import shutil import hashlib import asyncio import inspect import getpass import subprocess import importlib import importlib.metadata from pathlib import Path from typing import List, Dict, Any def run_shell(cmd, check=True): print(f"\n$ {cmd}") result = subprocess.run(cmd, shell=True, text=True) if check and result.returncode != 0: raise RuntimeError(f"Command failed: {cmd}") return result.returncode print("=" * 80) print("RAG-Anything Advanced Colab Tutorial") print("=" * 80) print("\n[1/10] Installing dependencies...") for module_name in list(sys.modules): if module_name == "PIL" or module_name.startswith("PIL."): del sys.modules[module_name] run_shell( 'pip -q install -U ' '"raganything[image,text]" ' '"openai>=1.0.0" ' '"python-dotenv" ' '"reportlab" ' '"pandas" ' '"matplotlib" ' '"tabulate"' ) run_shell('pip -q install --no-cache-dir --force-reinstall "pillow==11.3.0"') for module_name in list(sys.modules): if module_name == "PIL" or module_name.startswith("PIL."): del sys.modules[module_name] importlib.invalidate_caches() try: print("Pillow version:", importlib.metadata.version("Pillow")) except Exception as e: print("Could not read Pillow version:", repr(e)) print("\n[2/10] Importing libraries...") import numpy as np import pandas as pd import matplotlib.pyplot as plt from IPython.display import display from reportlab.lib.pagesizes import letter from reportlab.pdfgen import canvas from reportlab.lib.units import inch from openai import AsyncOpenAI from raganything import RAGAnything, RAGAnythingConfig from lightrag.utils import EmbeddingFunc print("Imports successful.") We begin by setting up the complete Colab environment for the RAG-Anything workflow. We install the required libraries, repair the Pillow dependency, and import all the modules needed for plotting, PDF creation, OpenAI access, and RAG-Anything. We also define a reusable shell helper so the setup remains clear and easy to rerun. Configuring Directories, Runtime Variables Copy CodeCopiedUse a different Browserprint("\n[3/10] Preparing directories and runtime settings...") BASE_DIR = Path("/content/raganything_advanced_tutorial") if Path("/content").exists() else Path.cwd() / "raganything_advanced_tutorial" ASSET_DIR = BASE_DIR / "assets" OUTPUT_DIR = BASE_DIR / "output" WORKING_DIR = BASE_DIR / "rag_storage" LOG_DIR = BASE_DIR / "logs" RESET_STORAGE = True RUN_FULL_DOCUMENT_PARSE = False PARSER_FOR_FULL_PARSE = "mineru" PARSE_METHOD = "auto" for d in [BASE_DIR, ASSET_DIR, OUTPUT_DIR, WORKING_DIR, LOG_DIR]: d.mkdir(parents=True, exist_ok=True) if RESET_STORAGE and WORKING_DIR.exists(): shutil.rmtree(WORKING_DIR) WORKING_DIR.mkdir(parents=True, exist_ok=True) os.environ["LOG_DIR"] = str(LOG_DIR) os.environ["SUMMARY_LANGUAGE"] = "English" os.environ["ENABLE_LLM_CACHE"] = "false" os.environ["ENABLE_LLM_CACHE_FOR_EXTRACT"] = "false" os.environ["MAX_ASYNC"] = "2" os.environ["CHUNK_SIZE"] = "900" os.environ["CHUNK_OVERLAP_SIZE"] = "120" os.environ["TIMEOUT"] = "240" for var in [ "OPENAI_API_KEY", "OPENAI_ORG_ID", "OPENAI_ORGANIZATION", "OPENAI_PROJECT", "OPENAI_DEFAULT_HEADERS", "LLM_BINDING_API_KEY", "LLM_BINDING_HOST", ]: os.environ.pop(var, None) print(f"Base directory: {BASE_DIR}") print(f"Assets directory: {ASSET_DIR}") print(f"Storage directory: {WORKING_DIR}") print("\n[4/10] Entering OpenAI API key securely...") def clean_api_key(raw_value: str) -> str: raw_value = str(raw_value or "").strip() raw_value = raw_value.replace("Bearer ", "").replace("bearer ", "").strip() raw_value = raw_value.strip("'").strip('"').strip("`").strip() if "=" in raw_value: raw_value = raw_value.split("=", 1)[1].strip().strip("'").strip('"').strip("`") raw_value = re.sub(r"\s+", "", raw_value) raw_value = raw_value.encode("ascii", errors="ignore").decode("ascii").strip() return raw_value OPENAI_API_KEY_RAW = getpass.getpass("Paste your OpenAI API key here. Input is hidden: ") OPENAI_API_KEY = clean_api_key(OPENAI_API_KEY_RAW) if not OPENAI_API_KEY: raise ValueError( "No API key was captured. Paste the key into the hidden input box and press Enter." ) print("Captured key length:", len(OPENAI_API_KEY)) print("Captured key prefix:", OPENAI_API_KEY[:12] + "...") print("Captured key suffix:", "..." + OPENAI_API_KEY[-6:]) LLM_MODEL = "gpt-4o-mini" VISION_MODEL = "gpt-4o-mini" EMBEDDING_MODEL = "text-embedding-3-small" EMBEDDING_DIM = 1536 openai_client = AsyncOpenAI(api_key=OPENAI_API_KEY) os.environ["LLM_MODEL"] = LLM_MODEL os.environ["VISION_MODEL"] = VISION_MODEL os.environ["EMBEDDING_MODEL"] = EMBEDDING_MODEL os.environ["EMBEDDING_DIM"] = str(EMBEDDING_DIM) print("Testing OpenAI chat API with the captured key...") try: test_response = await openai_client.chat.completions.create( model=LLM_MODEL, messages=[{"role": "user", "content": "Reply with exactly: ok"}], temperature=0, ) print("Chat API test response:", test_response.choices[0].message.content) except Exception as e: raise RuntimeError( "The key was captured, but OpenAI rejected the request or the account/model access failed. " "Check billing, project permissions, and make sure this is an OpenAI Platform API key." ) from e print("\nTesting OpenAI embedding API...") try: test_embedding = await openai_client.embeddings.create( model=EMBEDDING_MODEL, input=["RAG-Anything embedding test"], ) print("Embedding vector length:", len(test_embedding.data[0].embedding)) except Exception as e: raise RuntimeError( "Chat worked, but embeddings failed. Make sure your API key has permission for embeddings." ) from e print("OpenAI API key is working.") print(f"Chat model: {LLM_MODEL}") print(f"Vision model: {VISION_MODEL}") print(f"Embedding model: {EMBEDDING_MODEL}") print(f"Embedding dimension: {EMBEDDING_DIM}") We prepare the working directories, output folders, logs, and runtime environment variables that RAG-Anything uses during execution. We securely capture the OpenAI API key via a hidden input, clean the pasted value, and verify that both the chat and embedding calls work correctly. We also define the models and embedding dimensions that power the rest of the tutorial. Generating a Synthetic Multimodal Report Copy CodeCopiedUse a different Browserprint("\n[5/10] Creating a synthetic multimodal report...") monthly_data = pd.DataFrame( { "Month": ["Jan", "Feb", "Mar", "Apr", "May", "Jun"], "Query Volume": [1200, 1700, 2100, 2600, 3300, 4100], "Hybrid Accuracy": [0.71, 0.74, 0.79, 0.83, 0.87, 0.91], "Average Latency ms": [980, 920, 850, 790, 760, 730], } ) table_md = monthly_data.to_markdown(index=False) plt.figure(figsize=(8, 4.8)) plt.plot(monthly_data["Month"], monthly_data["Query Volume"], marker="o", label="Query Volume") plt.plot(monthly_data["Month"], monthly_data["Hybrid Accuracy"] * 4000, marker="s", label="Hybrid Accuracy scaled") plt.title("Multimodal RAG Usage and Quality Trend") plt.xlabel("Month") plt.ylabel("Volume / Scaled Accuracy") plt.legend() plt.grid(True, alpha=0.3) plt.text( 0.02, 0.95, "Synthetic figure: usage rises while latency falls", transform=plt.gca().transAxes, fontsize=9, verticalalignment="top", bbox=dict(boxstyle="round", alpha=0.15), ) chart_path = ASSET_DIR / "raganything_quality_trend.png" pl