PDF検索自動化で業務時間を1/3に削減した実例レポート

python

from sentence_transformers import SentenceTransformer

python

model = SentenceTransformer('all-MiniLM-L6-v2')

def embed_chunks(chunks):

    return model.encode(chunks)

python

import faiss

import numpy as np

python

def build_index(embeddings):

    dim = embeddings.shape

    index = faiss.IndexFlatL2(dim)

    index.add(embeddings)

    return index

<code>python

from transformers import CLIPProcessor, CLIPModel

from PIL import Image

</code>

python

clip_model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")

processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")



<pre><code class="language-python">def embed_image(image_path):

    image = Image.open(image_path)

    inputs = processor(images=image, return_tensors="pt")

    with torch.no_grad():

        image_features = clip_model.get_image_features(**inputs)

    return image_features.squeeze().numpy()

</code>




ほんと疲れるけど仕方ないね…。LangChainでトップドキュメント取得してLLMへの連携部分もゴニョゴニョ実装したことがあったっけ。ちょうどこの手順が地味に厄介だった覚えある。



<code class="language-python">

from langchain.chains import RetrievalQA

from langchain.vectorstores import FAISS

from langchain.llms import Ollama




retriever = FAISS.load_local("index", embeddings=model)

llm = Ollama(model="mistral")

qa = RetrievalQA.from_chain_type(llm=llm, retriever=retriever)

<pre><code class="language-html"><code class="language-bash">qa.run("What's the warranty coverage of Product X?")</code>

from fastapi import FastAPI

from pydantic import BaseModel

class Query(BaseModel):

    question: str

app = FastAPI()

@app.post("/ask")

def ask(query: Query):

    response = qa.run(query.question)

    return {"answer": response}

import gradio as gr

def answer_question(q):

    return qa.run(q)

gr.Interface(fn=answer_question, inputs="text", outputs="text", title="AI PDF Assistant").launch()

python

@app.post("/upload")

async def upload_pdf(file: UploadFile):

    save_path = f"./docs/{file.filename}"

    with open(save_path, "wb") as f:

        f.write(await file.read())

    # Extract, chunk, embed, and update FAISS index

python

# アシスタントに”記憶力”という名の後付機能を盛り込むため、SQLite採用。

import sqlite3

python

def save_interaction(question, answer):

    conn = sqlite3.connect("history.db")

    conn.execute("INSERT INTO log (q, a) VALUES (?, ?)", (question, answer))

    conn.commit()