1. 簡介
什麼是 RAG
檢索增強生成 (RAG) 技術結合了大型語言模型 (LLM) 的強大功能,以及從外部知識來源擷取相關資訊的能力。也就是說,LLM 不只會依賴內部訓練資料,還能存取最新的特定資訊,並在產生回覆時納入這些資訊。
RAG 越來越受歡迎,原因如下:
- 提升準確度和相關性:RAG 可讓 LLM 以從外部來源擷取的事實資訊為依據,提供更準確且相關的回覆。這項功能特別適合用於需要最新知識的情況,例如回答有關時事的問題,或提供特定主題的資訊。
- 減少幻覺:大型語言模型有時會產生看似合理,但實際上不正確或毫無意義的回覆。RAG 會驗證與外部來源產生的資訊,以減輕這項問題。
- 更高的適應性:RAG 可讓 LLM 更能適應不同的領域和工作。只要善用不同的知識來源,就能輕鬆自訂 LLM,提供各式各樣的主題資訊。
- 提升使用者體驗:RAG 可提供更有參考價值、可靠且相關的回覆,進而改善整體使用者體驗。
為何採用多模態
在現今資料豐富的世界中,文件通常會結合文字和圖片,以全面的方式傳達資訊。不過,大多數的檢索增強生成 (RAG) 系統都忽略了圖片中隱藏的寶貴洞察資料。隨著多模態大型語言模型 (LLM) 越來越受重視,我們必須探索如何在 RAG 中運用視覺內容和文字,進一步瞭解資訊環境。
多模態 RAG 的兩種選項
- 多模態嵌入 -多模態嵌入模型會根據您提供的輸入內容生成 1408 維向量*,其中可包含圖片、文字和影片資料的組合。圖片嵌入向量和文字嵌入向量位於相同的語意空間,且維度相同。因此,這些向量可用於以文字搜尋圖片或以圖片搜尋影片等用途。請參閱這部示範影片。
- 使用多模態嵌入功能嵌入文字和圖片
- 使用相似度搜尋功能擷取兩者
- 將擷取的原始圖片和文字區塊傳遞至多模式 LLM,以便合成答案
- 文字嵌入:
- 使用多模態 LLM 產生圖像的文字摘要
- 嵌入及擷取文字
- 將文字片段傳送至 LLM 以合成答案
什麼是多媒介擷取器
多向量檢索會使用文件部分摘要,擷取原始內容來整合答案。這項功能可提升 RAG 的品質,特別適用於需要大量使用表格、圖表等的任務。詳情請參閱 Langchain 的網誌。
建構項目
用例:使用 Gemini Pro 開發問答系統
假設您有包含複雜圖表或包含大量資訊的圖表的文件。您想要擷取這些資料來回答問題或查詢。
在本程式碼研究室中,您將執行下列操作:
- 使用 LangChain 載入資料
document_loaders
- 使用 Google 的
gemini-pro
模型產生文字摘要 - 使用 Google 的
gemini-pro-vision
模型產生圖片摘要 - 使用 Google 的
textembedding-gecko
模型,並以 Croma Db 做為向量儲存空間,建立多向量擷取 - 開發用於回答問題的多模態 RAG 鏈
2. 事前準備
- 在 Google Cloud 控制台的專案選取器頁面中,選取或建立 Google Cloud 專案。
- 請確認 Google Cloud 專案已啟用計費功能。瞭解如何檢查專案是否已啟用計費功能。
- 在 Vertex AI 資訊主頁中啟用所有建議的 API
- 開啟 Colab Notebook,並登入與目前使用中的 Google Cloud 帳戶相同的帳戶。
3. 建構多模態 RAG
本程式碼實驗室使用 Vertex AI SDK for Python 和 Langchain,示範如何使用 Google Cloud 實作「選項 2」。
您可以參考參照的 存放區中的 Multi-modal RAG with Google Cloud 檔案中的完整程式碼。
4. 步驟 1:安裝及匯入依附元件
!pip install -U --quiet langchain langchain_community chromadb langchain-google-vertexai
!pip install --quiet "unstructured[all-docs]" pypdf pillow pydantic lxml pillow matplotlib chromadb tiktoken
輸入專案 ID 並完成驗證
#TODO : ENter project and location
PROJECT_ID = ""
REGION = "us-central1"
from google.colab import auth
auth.authenticate_user()
初始化 Vertex AI 平台
import vertexai
vertexai.init(project = PROJECT_ID , location = REGION)
5. 步驟 2:準備及載入資料
我們使用 ZIP 檔案,其中包含這篇 部落格文章中擷取的圖片和 PDF 檔案子集。如要按照完整流程操作,請使用原始示例。
首先下載資料
import logging
import zipfile
import requests
logging.basicConfig(level=logging.INFO)
data_url = "https://storage.googleapis.com/benchmarks-artifacts/langchain-docs-benchmarking/cj.zip"
result = requests.get(data_url)
filename = "cj.zip"
with open(filename, "wb") as file:
file.write(result.content)
with zipfile.ZipFile(filename, "r") as zip_ref:
zip_ref.extractall()
從文件載入文字內容
from langchain_community.document_loaders import PyPDFLoader
loader = PyPDFLoader("./cj/cj.pdf")
docs = loader.load()
tables = []
texts = [d.page_content for d in docs]
檢查第一頁內容
texts[0]
您應該會看到輸出內容
文件總頁數
len(texts)
預期的輸出內容如下:
6. 步驟 3:產生文字摘要
先匯入必要的程式庫
from langchain_google_vertexai import VertexAI , ChatVertexAI , VertexAIEmbeddings
from langchain.prompts import PromptTemplate
from langchain_core.messages import AIMessage
from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnableLambda
取得文字摘要
# Generate summaries of text elements
def generate_text_summaries(texts, tables, summarize_texts=False):
"""
Summarize text elements
texts: List of str
tables: List of str
summarize_texts: Bool to summarize texts
"""
# Prompt
prompt_text = """You are an assistant tasked with summarizing tables and text for retrieval. \
These summaries will be embedded and used to retrieve the raw text or table elements. \
Give a concise summary of the table or text that is well optimized for retrieval. Table or text: {element} """
prompt = PromptTemplate.from_template(prompt_text)
empty_response = RunnableLambda(
lambda x: AIMessage(content="Error processing document")
)
# Text summary chain
model = VertexAI(
temperature=0, model_name="gemini-pro", max_output_tokens=1024
).with_fallbacks([empty_response])
summarize_chain = {"element": lambda x: x} | prompt | model | StrOutputParser()
# Initialize empty summaries
text_summaries = []
table_summaries = []
# Apply to text if texts are provided and summarization is requested
if texts and summarize_texts:
text_summaries = summarize_chain.batch(texts, {"max_concurrency": 1})
elif texts:
text_summaries = texts
# Apply to tables if tables are provided
if tables:
table_summaries = summarize_chain.batch(tables, {"max_concurrency": 1})
return text_summaries, table_summaries
# Get text summaries
text_summaries, table_summaries = generate_text_summaries(
texts, tables, summarize_texts=True
)
text_summaries[0]
預期的輸出內容如下:
7. 步驟 4:產生圖片摘要
先匯入必要的程式庫
import base64
import os
from langchain_core.messages import HumanMessage
產生圖像摘要
def encode_image(image_path):
"""Getting the base64 string"""
with open(image_path, "rb") as image_file:
return base64.b64encode(image_file.read()).decode("utf-8")
def image_summarize(img_base64, prompt):
"""Make image summary"""
model = ChatVertexAI(model_name="gemini-pro-vision", max_output_tokens=1024)
msg = model(
[
HumanMessage(
content=[
{"type": "text", "text": prompt},
{
"type": "image_url",
"image_url": {"url": f"data:image/jpeg;base64,{img_base64}"},
},
]
)
]
)
return msg.content
def generate_img_summaries(path):
"""
Generate summaries and base64 encoded strings for images
path: Path to list of .jpg files extracted by Unstructured
"""
# Store base64 encoded images
img_base64_list = []
# Store image summaries
image_summaries = []
# Prompt
prompt = """You are an assistant tasked with summarizing images for retrieval. \
These summaries will be embedded and used to retrieve the raw image. \
Give a concise summary of the image that is well optimized for retrieval."""
# Apply to images
for img_file in sorted(os.listdir(path)):
if img_file.endswith(".jpg"):
img_path = os.path.join(path, img_file)
base64_image = encode_image(img_path)
img_base64_list.append(base64_image)
image_summaries.append(image_summarize(base64_image, prompt))
return img_base64_list, image_summaries
# Image summaries
img_base64_list, image_summaries = generate_img_summaries("./cj")
len(img_base64_list)
len(image_summaries)
image_summaries[0]
輸出內容應如下所示
8. 步驟 5:建構多向擷取
我們來產生文字和圖片摘要,並儲存至 ChromaDB 向量儲存庫。
匯入必要程式庫
import uuid
from langchain.retrievers.multi_vector import MultiVectorRetriever
from langchain.storage import InMemoryStore
from langchain_community.vectorstores import Chroma
from langchain_core.documents import Document
建立多向量擷取
def create_multi_vector_retriever(
vectorstore, text_summaries, texts, table_summaries, tables, image_summaries, images
):
"""
Create retriever that indexes summaries, but returns raw images or texts
"""
# Initialize the storage layer
store = InMemoryStore()
id_key = "doc_id"
# Create the multi-vector retriever
retriever = MultiVectorRetriever(
vectorstore=vectorstore,
docstore=store,
id_key=id_key,
)
# Helper function to add documents to the vectorstore and docstore
def add_documents(retriever, doc_summaries, doc_contents):
doc_ids = [str(uuid.uuid4()) for _ in doc_contents]
summary_docs = [
Document(page_content=s, metadata={id_key: doc_ids[i]})
for i, s in enumerate(doc_summaries)
]
retriever.vectorstore.add_documents(summary_docs)
retriever.docstore.mset(list(zip(doc_ids, doc_contents)))
# Add texts, tables, and images
# Check that text_summaries is not empty before adding
if text_summaries:
add_documents(retriever, text_summaries, texts)
# Check that table_summaries is not empty before adding
if table_summaries:
add_documents(retriever, table_summaries, tables)
# Check that image_summaries is not empty before adding
if image_summaries:
add_documents(retriever, image_summaries, images)
return retriever
# The vectorstore to use to index the summaries
vectorstore = Chroma(
collection_name="mm_rag_cj_blog",
embedding_function=VertexAIEmbeddings(model_name="textembedding-gecko@latest"),
)
# Create retriever
retriever_multi_vector_img = create_multi_vector_retriever(
vectorstore,
text_summaries,
texts,
table_summaries,
tables,
image_summaries,
img_base64_list,
)
9. 步驟 6:建構多模態 RAG
- 定義公用函式
import io
import re
from IPython.display import HTML, display
from langchain_core.runnables import RunnableLambda, RunnablePassthrough
from PIL import Image
def plt_img_base64(img_base64):
"""Disply base64 encoded string as image"""
# Create an HTML img tag with the base64 string as the source
image_html = f'<img src="data:image/jpeg;base64,{img_base64}" />'
# Display the image by rendering the HTML
display(HTML(image_html))
def looks_like_base64(sb):
"""Check if the string looks like base64"""
return re.match("^[A-Za-z0-9+/]+[=]{0,2}$", sb) is not None
def is_image_data(b64data):
"""
Check if the base64 data is an image by looking at the start of the data
"""
image_signatures = {
b"\xFF\xD8\xFF": "jpg",
b"\x89\x50\x4E\x47\x0D\x0A\x1A\x0A": "png",
b"\x47\x49\x46\x38": "gif",
b"\x52\x49\x46\x46": "webp",
}
try:
header = base64.b64decode(b64data)[:8] # Decode and get the first 8 bytes
for sig, format in image_signatures.items():
if header.startswith(sig):
return True
return False
except Exception:
return False
def resize_base64_image(base64_string, size=(128, 128)):
"""
Resize an image encoded as a Base64 string
"""
# Decode the Base64 string
img_data = base64.b64decode(base64_string)
img = Image.open(io.BytesIO(img_data))
# Resize the image
resized_img = img.resize(size, Image.LANCZOS)
# Save the resized image to a bytes buffer
buffered = io.BytesIO()
resized_img.save(buffered, format=img.format)
# Encode the resized image to Base64
return base64.b64encode(buffered.getvalue()).decode("utf-8")
def split_image_text_types(docs):
"""
Split base64-encoded images and texts
"""
b64_images = []
texts = []
for doc in docs:
# Check if the document is of type Document and extract page_content if so
if isinstance(doc, Document):
doc = doc.page_content
if looks_like_base64(doc) and is_image_data(doc):
doc = resize_base64_image(doc, size=(1300, 600))
b64_images.append(doc)
else:
texts.append(doc)
if len(b64_images) > 0:
return {"images": b64_images[:1], "texts": []}
return {"images": b64_images, "texts": texts}
- 定義特定網域的圖像提示
def img_prompt_func(data_dict):
"""
Join the context into a single string
"""
formatted_texts = "\n".join(data_dict["context"]["texts"])
messages = []
# Adding the text for analysis
text_message = {
"type": "text",
"text": (
"You are financial analyst tasking with providing investment advice.\n"
"You will be given a mixed of text, tables, and image(s) usually of charts or graphs.\n"
"Use this information to provide investment advice related to the user question. \n"
f"User-provided question: {data_dict['question']}\n\n"
"Text and / or tables:\n"
f"{formatted_texts}"
),
}
messages.append(text_message)
# Adding image(s) to the messages if present
if data_dict["context"]["images"]:
for image in data_dict["context"]["images"]:
image_message = {
"type": "image_url",
"image_url": {"url": f"data:image/jpeg;base64,{image}"},
}
messages.append(image_message)
return [HumanMessage(content=messages)]
- 定義多模態 RAG 鏈結
def multi_modal_rag_chain(retriever):
"""
Multi-modal RAG chain
"""
# Multi-modal LLM
model = ChatVertexAI(
temperature=0, model_name="gemini-pro-vision", max_output_tokens=1024
)
# RAG pipeline
chain = (
{
"context": retriever | RunnableLambda(split_image_text_types),
"question": RunnablePassthrough(),
}
| RunnableLambda(img_prompt_func)
| model
| StrOutputParser()
)
return chain
# Create RAG chain
chain_multimodal_rag = multi_modal_rag_chain(retriever_multi_vector_img)
10. 步驟 7:測試查詢
- 擷取相關文件
query = "What are the EV / NTM and NTM rev growth for MongoDB, Cloudflare, and Datadog?"
docs = retriever_multi_vector_img.get_relevant_documents(query, limit=1)
# We get relevant docs
len(docs)
docs
You may get similar output
plt_img_base64(docs[3])
- 對相同查詢執行 RAG
result = chain_multimodal_rag.invoke(query)
from IPython.display import Markdown as md
md(result)
輸出內容範例 (執行程式碼時可能會有所不同)
11. 清理
如要避免系統向您的 Google Cloud 帳戶收取本程式碼研究室所用資源的費用,請按照下列步驟操作:
12. 恭喜
恭喜!您已成功使用 Gemini 開發多模態 RAG。