feat:初始化工程

.env

@@ -0,0 +1,12 @@
+RUSTFS_ENDPOINT=http://114.66.28.183:42736
+RUSTFS_ACCESS_KEY=B4K79q5HGhPJlnXfLs20
+RUSTFS_SECRET_KEY=j9b3M2LRU80okVcZnBOxePvd7NXF5TSrqf6gImA1
+RUSTFS_BUCKET=study
+
+OCR_API_URL=https://paddleocr.aistudio-app.com/api/v2/ocr/jobs
+OCR_API_TOKEN=df7dcc85a5c3c9d64e421f353d11d13ec45512f6
+OCR_MODEL=PaddleOCR-VL-1.6
+
+MODEL_NAME=deepseek-v4-flash
+MODEL_BASE_URL=https://api.deepseek.com
+MODEL_API_KEY=sk-0b237d41f6bc44fc9732ea66bd7eade0

.gitignore

@@ -0,0 +1,68 @@
+# Python 字节码文件
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C 扩展
+*.so
+
+# 分发/打包
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# 虚拟环境
+venv/
+env/
+ENV/
+.env
+.venv
+
+# 测试
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+
+# Django 相关
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+media/
+
+# PyCharm IDE
+.idea/
+*.iml
+*.iws
+*.ipr
+
+# VS Code
+.vscode/
+*.code-workspace
+.history/
+
+# 其他
+.DS_Store
+
+logs/
+packages/

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/study-agent-service.iml" filepath="$PROJECT_DIR$/.idea/study-agent-service.iml" />
+    </modules>
+  </component>
+</project>

.idea/study-agent-service.iml

@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$">
+      <excludeFolder url="file://$MODULE_DIR$/.venv" />
+    </content>
+    <orderEntry type="jdk" jdkName="Python 3.10 (study-agent-service)" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>

.idea/workspace.xml

@@ -0,0 +1,114 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="AutoImportSettings">
+    <option name="autoReloadType" value="SELECTIVE" />
+  </component>
+  <component name="ChangeListManager">
+    <list default="true" id="c72023a9-a934-49fc-81d0-53a83489c638" name="Changes" comment="">
+      <change afterPath="$PROJECT_DIR$/.env" afterDir="false" />
+      <change afterPath="$PROJECT_DIR$/.idea/inspectionProfiles/profiles_settings.xml" afterDir="false" />
+      <change afterPath="$PROJECT_DIR$/.idea/modules.xml" afterDir="false" />
+      <change afterPath="$PROJECT_DIR$/.idea/study-agent-service.iml" afterDir="false" />
+      <change afterPath="$PROJECT_DIR$/.idea/vcs.xml" afterDir="false" />
+      <change afterPath="$PROJECT_DIR$/.idea/workspace.xml" afterDir="false" />
+      <change afterPath="$PROJECT_DIR$/agent/model.py" afterDir="false" />
+      <change afterPath="$PROJECT_DIR$/agent/prompt.py" afterDir="false" />
+      <change afterPath="$PROJECT_DIR$/agent/study.py" afterDir="false" />
+      <change afterPath="$PROJECT_DIR$/main.py" afterDir="false" />
+      <change afterPath="$PROJECT_DIR$/models/agent.py" afterDir="false" />
+      <change afterPath="$PROJECT_DIR$/ocr.py" afterDir="false" />
+      <change afterPath="$PROJECT_DIR$/requirements.txt" afterDir="false" />
+      <change afterPath="$PROJECT_DIR$/service.py" afterDir="false" />
+      <change afterPath="$PROJECT_DIR$/storage.py" afterDir="false" />
+    </list>
+    <option name="SHOW_DIALOG" value="false" />
+    <option name="HIGHLIGHT_CONFLICTS" value="true" />
+    <option name="HIGHLIGHT_NON_ACTIVE_CHANGELIST" value="false" />
+    <option name="LAST_RESOLUTION" value="IGNORE" />
+  </component>
+  <component name="FileTemplateManagerImpl">
+    <option name="RECENT_TEMPLATES">
+      <list>
+        <option value="FastAPI main" />
+        <option value="FastAPI test_main" />
+        <option value="Python Script" />
+      </list>
+    </option>
+  </component>
+  <component name="Git.Settings">
+    <option name="RECENT_GIT_ROOT_PATH" value="$PROJECT_DIR$" />
+  </component>
+  <component name="ProjectColorInfo"><![CDATA[{
+  "associatedIndex": 4
+}]]></component>
+  <component name="ProjectId" id="3H4xOetugdBhU5dfrCgc0HWwHSq" />
+  <component name="ProjectLevelVcsManager" settingsEditedManually="true" />
+  <component name="ProjectViewState">
+    <option name="hideEmptyMiddlePackages" value="true" />
+    <option name="showLibraryContents" value="true" />
+  </component>
+  <component name="PropertiesComponent"><![CDATA[{
+  "keyToString": {
+    "FastAPI.study-agent-service.executor": "Run",
+    "RunOnceActivity.ShowReadmeOnStart": "true",
+    "git-widget-placeholder": "master",
+    "last_opened_file_path": "D:/Cxx/PythonProjects/study-agent-service",
+    "node.js.detected.package.eslint": "true",
+    "node.js.detected.package.tslint": "true",
+    "node.js.selected.package.eslint": "(autodetect)",
+    "node.js.selected.package.tslint": "(autodetect)",
+    "nodejs_package_manager_path": "npm",
+    "vue.rearranger.settings.migration": "true"
+  }
+}]]></component>
+  <component name="RecentsManager">
+    <key name="CopyFile.RECENT_KEYS">
+      <recent name="D:\Cxx\PythonProjects\study-agent-service" />
+      <recent name="D:\Cxx\PythonProjects\study-agent-service\models" />
+      <recent name="D:\Cxx\PythonProjects\study-agent-service\agent" />
+    </key>
+  </component>
+  <component name="RunManager">
+    <configuration name="study-agent-service" type="Python.FastAPI">
+      <option name="file" value="$PROJECT_DIR$/main.py" />
+      <module name="study-agent-service" />
+      <option name="ENV_FILES" value="" />
+      <option name="INTERPRETER_OPTIONS" value="" />
+      <option name="PARENT_ENVS" value="true" />
+      <option name="SDK_HOME" value="" />
+      <option name="WORKING_DIRECTORY" value="" />
+      <option name="IS_MODULE_SDK" value="false" />
+      <option name="ADD_CONTENT_ROOTS" value="true" />
+      <option name="ADD_SOURCE_ROOTS" value="true" />
+      <EXTENSION ID="PythonCoverageRunConfigurationExtension" runner="coverage.py" />
+      <option name="launchJavascriptDebuger" value="false" />
+      <method v="2" />
+    </configuration>
+  </component>
+  <component name="SharedIndexes">
+    <attachedChunks>
+      <set>
+        <option value="bundled-js-predefined-d6986cc7102b-1632447f56bf-JavaScript-PY-243.26053.29" />
+        <option value="bundled-python-sdk-b1dbf8ef85a6-4df51de95216-com.jetbrains.pycharm.pro.sharedIndexes.bundled-PY-243.26053.29" />
+      </set>
+    </attachedChunks>
+  </component>
+  <component name="SpellCheckerSettings" RuntimeDictionaries="0" Folders="0" CustomDictionaries="0" DefaultDictionary="application-level" UseSingleDictionary="true" transferred="true" />
+  <component name="TaskManager">
+    <task active="true" id="Default" summary="Default task">
+      <changelist id="c72023a9-a934-49fc-81d0-53a83489c638" name="Changes" comment="" />
+      <created>1785141112222</created>
+      <option name="number" value="Default" />
+      <option name="presentableId" value="Default" />
+      <updated>1785141112222</updated>
+      <workItem from="1785141113303" duration="9082000" />
+    </task>
+    <servers />
+  </component>
+  <component name="TypeScriptGeneratedFilesManager">
+    <option name="version" value="3" />
+  </component>
+  <component name="com.intellij.coverage.CoverageDataManagerImpl">
+    <SUITE FILE_PATH="coverage/study_agent_service$study_agent_service.coverage" NAME="study-agent-service Coverage Results" MODIFIED="1785153562933" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="" />
+  </component>
+</project>

agent/model.py

@@ -0,0 +1,13 @@
+import os
+
+from dotenv import load_dotenv
+from langchain.chat_models import init_chat_model
+
+load_dotenv()
+
+model = init_chat_model(
+    model=os.getenv('MODEL_NAME'),
+    model_provider="openai",
+    base_url=os.getenv('MODEL_BASE_URL'),
+    api_key=os.getenv('MODEL_API_KEY')
+)

agent/prompt.py

@@ -0,0 +1,27 @@
+study_prompt = """
+你是一位专业的出题专家，擅长根据学习材料生成高质量选择题。
+
+要求：
+1. 题目必须严格基于学习内容，不得编造知识点。
+2. 每道题只有 1 个正确答案。
+3. 干扰项要有迷惑性。
+4. 输出必须是纯 JSON，禁止 Markdown。
+5. 不要修改专业术语。
+
+返回格式：
+{
+  "questions": [
+    {
+      "id": 1,
+      "question": "题目内容",
+      "options": {
+        "A": "选项A内容",
+        "B": "选项B内容",
+        "C": "选项C内容",
+        "D": "选项D内容"
+      },
+      "answer": "A"
+    }
+  ]
+}
+"""

agent/study.py

@@ -0,0 +1,9 @@
+from langchain.agents import create_agent
+
+from agent.model import model
+from agent.prompt import study_prompt
+
+study_agent = create_agent(
+    model=model,
+    system_prompt=study_prompt
+)

main.py

@@ -0,0 +1,28 @@
+from fastapi import FastAPI, UploadFile, File
+from starlette.responses import StreamingResponse
+
+from models.agent import QueryRequest
+from service import query_agent
+from storage import upload_rustfs
+from ocr import ocr_from_url
+
+app = FastAPI(title="AI Study Service")
+
+
+@app.post("/upload")
+def upload(file: UploadFile = File(...)):
+    url = upload_rustfs(file.file, file.filename)
+    text = ocr_from_url(url)
+
+    return {
+        "text": text,
+    }
+
+
+@app.post("/generate")
+def generate(query: QueryRequest):
+    """流式对话"""
+    return StreamingResponse(
+        query_agent(query),
+        media_type="text/event-stream"
+    )

models/agent.py

@@ -0,0 +1,5 @@
+from pydantic import BaseModel
+
+
+class QueryRequest(BaseModel):
+    message: str

ocr.py

@@ -0,0 +1,53 @@
+import os
+import time
+import requests
+from dotenv import load_dotenv
+
+load_dotenv()
+
+API_URL = os.getenv('OCR_API_URL')
+HEADERS = {
+    "Authorization": f"bearer {os.getenv('OCR_API_TOKEN')}",
+    "Content-Type": "application/json",
+}
+MODEL = os.getenv("OCR_MODEL")
+
+
+def ocr_from_url(image_url: str) -> str:
+    r = requests.post(
+        API_URL,
+        json={
+            "fileUrl": image_url,
+            "model": MODEL,
+            "optionalPayload": {
+                "useDocOrientationClassify": False,
+                "useDocUnwarping": False,
+                "useChartRecognition": False,
+            },
+        },
+        headers=HEADERS,
+    )
+    r.raise_for_status()
+    job_id = r.json()["data"]["jobId"]
+
+    while True:
+        r = requests.get(f"{API_URL}/{job_id}", headers=HEADERS)
+        r.raise_for_status()
+        data = r.json()["data"]
+
+        if data["state"] == "done":
+            jsonl_url = data["resultUrl"]["jsonUrl"]
+            break
+        if data["state"] == "failed":
+            raise RuntimeError("OCR failed")
+
+        time.sleep(3)
+
+    lines = requests.get(jsonl_url).text.strip().splitlines()
+    text = ""
+    for line in lines:
+        item = __import__("json").loads(line)
+        for res in item["result"]["layoutParsingResults"]:
+            text += res["markdown"]["text"]
+
+    return text

requirements.txt

@@ -0,0 +1,10 @@
+fastapi~=0.140.0
+python-dotenv~=1.2.2
+requests~=2.34.2
+boto3~=1.43.56
+botocore~=1.43.56
+langchain~=1.3.14
+langchain-core~=1.5.1
+langchain-openai~=1.4.1
+starlette~=1.3.1
+pydantic~=2.13.4

service.py

@@ -0,0 +1,21 @@
+from langchain_core.messages import AIMessageChunk, HumanMessage
+
+from agent.study import study_agent
+from models.agent import QueryRequest
+
+
+def query_agent(query: QueryRequest):
+    try:
+        user_msg = f"学习内容：\n{query.message}"
+
+        # 流式调用Agent
+        for chunk, metadata in study_agent.stream(
+                {"messages": [HumanMessage(content=user_msg)]},
+                stream_mode="messages"
+        ):
+            if isinstance(chunk, AIMessageChunk):
+                if isinstance(chunk, AIMessageChunk) and chunk.content:
+                    yield chunk.content
+    except Exception as e:
+        print(f"\n[错误]: {str(e)}")
+        yield "信息检索失败，请重新输入问题提问"

storage.py

@@ -0,0 +1,24 @@
+import os
+import boto3
+from botocore.config import Config
+from dotenv import load_dotenv
+
+load_dotenv()
+
+ENDPOINT = os.getenv("RUSTFS_ENDPOINT")
+BUCKET = os.getenv("RUSTFS_BUCKET")
+
+_s3 = boto3.client(
+    "s3",
+    endpoint_url=ENDPOINT,
+    aws_access_key_id=os.getenv("RUSTFS_ACCESS_KEY"),
+    aws_secret_access_key=os.getenv("RUSTFS_SECRET_KEY"),
+    config=Config(signature_version="s3v4"),
+    region_name="us-east-1",
+)
+
+
+def upload_rustfs(file_obj, filename: str) -> str:
+    _s3.upload_fileobj(file_obj, BUCKET, filename)
+
+    return f"{ENDPOINT}/{BUCKET}/{filename}"