init

.idea/LLM.iml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,20 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="DuplicatedCode" enabled="true" level="WEAK WARNING" enabled_by_default="true">
+      <Languages>
+        <language minSize="161" name="Python" />
+      </Languages>
+    </inspection_tool>
+    <inspection_tool class="PyPackageRequirementsInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredPackages">
+        <value>
+          <list size="2">
+            <item index="0" class="java.lang.String" itemvalue="sentence_transformers" />
+            <item index="1" class="java.lang.String" itemvalue="cpm_kernels" />
+          </list>
+        </value>
+      </option>
+    </inspection_tool>
+  </profile>
+</component>

.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/misc.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="LLM" project-jdk-type="Python SDK" />
+</project>

.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/LLM.iml" filepath="$PROJECT_DIR$/.idea/LLM.iml" />
+    </modules>
+  </component>
+</project>

.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 +1,50 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ChangeListManager">
+    <list default="true" id="db7f4434-7cc2-4790-b42e-92159334a8b4" name="Changes" comment="" />
+    <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="Git.Settings">
+    <option name="RECENT_GIT_ROOT_PATH" value="$PROJECT_DIR$" />
+  </component>
+  <component name="ProjectColorInfo"><![CDATA[{
+  "associatedIndex": 8
+}]]></component>
+  <component name="ProjectId" id="2gEthR7lQkfXVFalbjvQftZcFMK" />
+  <component name="ProjectLevelVcsManager" settingsEditedManually="true" />
+  <component name="ProjectViewState">
+    <option name="hideEmptyMiddlePackages" value="true" />
+    <option name="showLibraryContents" value="true" />
+  </component>
+  <component name="PropertiesComponent"><![CDATA[{
+  "keyToString": {
+    "RunOnceActivity.OpenProjectViewOnStart": "true",
+    "RunOnceActivity.ShowReadmeOnStart": "true",
+    "git-widget-placeholder": "master",
+    "nodejs_package_manager_path": "npm",
+    "vue.rearranger.settings.migration": "true"
+  }
+}]]></component>
+  <component name="SharedIndexes">
+    <attachedChunks>
+      <set>
+        <option value="bundled-python-sdk-d68999036c7f-b11f5e8da5ad-com.jetbrains.pycharm.pro.sharedIndexes.bundled-PY-233.14475.56" />
+      </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="db7f4434-7cc2-4790-b42e-92159334a8b4" name="Changes" comment="" />
+      <created>1715274683455</created>
+      <option name="number" value="Default" />
+      <option name="presentableId" value="Default" />
+      <updated>1715274683455</updated>
+      <workItem from="1715274700837" duration="5000" />
+    </task>
+    <servers />
+  </component>
+</project>

requirements.txt

@@ -0,0 +1,4 @@
+langchain~=0.1.19
+httpx-sse
+langchainhub
+pyjwt

src/base/chinese_text_splitter.py

@@ -0,0 +1,25 @@
+import re
+from typing import List
+
+from langchain.text_splitter import CharacterTextSplitter
+
+
+class ChineseTextSplitter(CharacterTextSplitter):
+    def __init__(self, pdf: bool = False, **kwargs):
+        super().__init__(**kwargs)
+        self.pdf = pdf
+
+    def split_text(self, text: str) -> List[str]:
+        if self.pdf:
+            text = re.sub(r"\n{3,}", "\n", text)
+            text = re.sub('\s', ' ', text)
+            text = text.replace("\n\n", "")
+        sent_sep_pattern = re.compile(
+            '([﹒﹔﹖﹗．。！？]["’”」』]{0,2}|(?=["‘“「『]{1,2}|$))')
+        sent_list = []
+        for ele in sent_sep_pattern.split(text):
+            if sent_sep_pattern.match(ele) and sent_list:
+                sent_list[-1] += ele
+            elif ele:
+                sent_list.append(ele)
+        return sent_list