랭체인 심화

- BM25로 데이터 검색
- 유사도 검색
- 질문 + 문서를 보내 질문과 관련 내용만 추출LLMChainExtractor
- pdf ocr이 없는 경우 이미지로 변환하여 ocr처리하여 텍스트 인식
- 정규식으로 데이터 정제

.idea/Source.iml

@@ -6,7 +6,7 @@
       <excludeFolder url="file://$MODULE_DIR$/.venv" />
       <excludeFolder url="file://$MODULE_DIR$/ollama/.venv" />
     </content>
-    <orderEntry type="jdk" jdkName="Python 3.12 (Source)" jdkType="Python SDK" />
+    <orderEntry type="jdk" jdkName="~/Source/.venv" jdkType="Python SDK" />
     <orderEntry type="sourceFolder" forTests="false" />
   </component>
   <component name="PyDocumentationSettings">

.idea/pyLspTools.xml

@@ -0,0 +1,29 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="PyToolsState">
+    <option name="tools">
+      <map>
+        <entry key="pyrefly">
+          <value>
+            <ToolEntry />
+          </value>
+        </entry>
+        <entry key="pyright">
+          <value>
+            <ToolEntry />
+          </value>
+        </entry>
+        <entry key="ruff">
+          <value>
+            <ToolEntry />
+          </value>
+        </entry>
+        <entry key="ty">
+          <value>
+            <ToolEntry />
+          </value>
+        </entry>
+      </map>
+    </option>
+  </component>
+</project>