Upload 18 files

.env

@@ -0,0 +1 @@
+TOGETHER_AI="92b5eec828c7ac0c34b60bf5daf97aebc2594196c5005e6c0d9ec2826e3eee11"

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+ipc_vector_db/index.faiss filter=lfs diff=lfs merge=lfs -text
+ipc-data/Indian[[:space:]]Penal[[:space:]]Code[[:space:]]Book.pdf filter=lfs diff=lfs merge=lfs -text

.idea/.gitignore

@@ -0,0 +1,8 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml

.idea/aws.xml

@@ -0,0 +1,11 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="accountSettings">
+    <option name="activeRegion" value="us-east-1" />
+    <option name="recentlyUsedRegions">
+      <list>
+        <option value="us-east-1" />
+      </list>
+    </option>
+  </component>
+</project>

.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="Eslint" enabled="true" level="WARNING" enabled_by_default="true" />
+  </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/lawforher.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 3.11 (lawforher)" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/misc.xml

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Black">
+    <option name="sdkName" value="Python 3.11 (lawforher)" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.11 (lawforher)" 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/lawforher.iml" filepath="$PROJECT_DIR$/.idea/lawforher.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 +1,112 @@
+<?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="858a48fb-95a2-4510-8cfc-e62f98d77bef" 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="FileTemplateManagerImpl">
+    <option name="RECENT_TEMPLATES">
+      <list>
+        <option value="Python Script" />
+      </list>
+    </option>
+  </component>
+  <component name="FlaskConsoleOptions" custom-start-script="import sys&#10;sys.path.extend([WORKING_DIR_AND_PYTHON_PATHS])&#10;from flask.cli import ScriptInfo&#10;locals().update(ScriptInfo(create_app=None).load_app().make_shell_context())&#10;print(&quot;Python %s on %s\nApp: %s [%s]\nInstance: %s&quot; % (sys.version, sys.platform, app.import_name, app.env, app.instance_path))">
+    <envs>
+      <env key="FLASK_APP" value="app" />
+    </envs>
+    <option name="myCustomStartScript" value="import sys&#10;sys.path.extend([WORKING_DIR_AND_PYTHON_PATHS])&#10;from flask.cli import ScriptInfo&#10;locals().update(ScriptInfo(create_app=None).load_app().make_shell_context())&#10;print(&quot;Python %s on %s\nApp: %s [%s]\nInstance: %s&quot; % (sys.version, sys.platform, app.import_name, app.env, app.instance_path))" />
+    <option name="myEnvs">
+      <map>
+        <entry key="FLASK_APP" value="app" />
+      </map>
+    </option>
+  </component>
+  <component name="Git.Settings">
+    <option name="RECENT_GIT_ROOT_PATH" value="$PROJECT_DIR$" />
+  </component>
+  <component name="GitHubPullRequestSearchHistory"><![CDATA[{
+  "lastFilter": {
+    "state": "OPEN",
+    "assignee": "chaithanyashaji"
+  }
+}]]></component>
+  <component name="GithubPullRequestsUISettings"><![CDATA[{
+  "selectedUrlAndAccountId": {
+    "url": "https://github.com/chaithanyashaji/lawforher_chatbot.git",
+    "accountId": "a9c524c8-9c87-4292-85a5-6ee1841e6195"
+  }
+}]]></component>
+  <component name="ProblemsViewState">
+    <option name="selectedTabId" value="CurrentFile" />
+  </component>
+  <component name="ProjectColorInfo">{
+  &quot;associatedIndex&quot;: 2
+}</component>
+  <component name="ProjectId" id="2quUzOFT2DnZdoWyesJ4S7EFORH" />
+  <component name="ProjectViewState">
+    <option name="hideEmptyMiddlePackages" value="true" />
+    <option name="showLibraryContents" value="true" />
+  </component>
+  <component name="PropertiesComponent"><![CDATA[{
+  "keyToString": {
+    "RunOnceActivity.ShowReadmeOnStart": "true",
+    "git-widget-placeholder": "main",
+    "last_opened_file_path": "C:/Users/Chaithanya/PycharmProjects/law4her_test",
+    "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",
+    "settings.editor.selected.configurable": "project.propVCSSupport.DirectoryMappings",
+    "vue.rearranger.settings.migration": "true"
+  }
+}]]></component>
+  <component name="RecentsManager">
+    <key name="CopyFile.RECENT_KEYS">
+      <recent name="C:\Users\Chaithanya\PycharmProjects\lawforher\ipc-data" />
+    </key>
+    <key name="MoveFile.RECENT_KEYS">
+      <recent name="C:\Users\Chaithanya\PycharmProjects\lawforher\models\llama-2-7b-chat" />
+    </key>
+  </component>
+  <component name="SharedIndexes">
+    <attachedChunks>
+      <set>
+        <option value="bundled-js-predefined-1d06a55b98c1-0b3e54e931b4-JavaScript-PY-241.18034.82" />
+        <option value="bundled-python-sdk-975db3bf15a3-2767605e8bc2-com.jetbrains.pycharm.pro.sharedIndexes.bundled-PY-241.18034.82" />
+      </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="858a48fb-95a2-4510-8cfc-e62f98d77bef" name="Changes" comment="" />
+      <created>1735512215507</created>
+      <option name="number" value="Default" />
+      <option name="presentableId" value="Default" />
+      <updated>1735512215507</updated>
+      <workItem from="1735512216915" duration="1122000" />
+      <workItem from="1735517820889" duration="182000" />
+      <workItem from="1735529743314" duration="1093000" />
+      <workItem from="1735532197204" duration="1335000" />
+      <workItem from="1735540268170" duration="615000" />
+      <workItem from="1735571841326" duration="8671000" />
+      <workItem from="1735586361032" duration="5331000" />
+      <workItem from="1735988510923" duration="22397000" />
+      <workItem from="1736014550072" duration="4536000" />
+      <workItem from="1736019186160" duration="12295000" />
+      <workItem from="1736064097307" duration="21545000" />
+    </task>
+    <servers />
+  </component>
+  <component name="TypeScriptGeneratedFilesManager">
+    <option name="version" value="3" />
+  </component>
+</project>

.streamlit/config.toml

@@ -0,0 +1,4 @@
+[server]
+headless = true
+port = 8501
+enableCORS = false

embedding.py

@@ -0,0 +1,21 @@
+from langchain_community.document_loaders import PyPDFLoader,DirectoryLoader
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.vectorstores import FAISS
+
+loader = DirectoryLoader('ipc-data', glob="./*.pdf", loader_cls=PyPDFLoader)
+documents = loader.load()
+
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=1024, chunk_overlap=200)
+texts = text_splitter.split_documents(documents)
+
+embeddings = HuggingFaceEmbeddings(
+    model_name="nomic-ai/nomic-embed-text-v1",
+    model_kwargs={"trust_remote_code": True, "revision": "289f532e14dbbbd5a04753fa58739e9ba766f3c7"},
+)
+
+# Creates vector embeddings and saves it in the FAISS DB
+faiss_db = FAISS.from_documents(texts, embeddings)
+
+# Saves and export the vector embeddings databse
+faiss_db.save_local("ipc_vector_db")

ipc-data/Indian Penal Code Book.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5706a1b995df774c4c4ea1868223e18a13ba619977d323d3cab76a1cc095e237
+size 20095787

ipc_vector_db/index.faiss

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d95e6cc1b7e77537e6bff530fa443dfcf2638efcb858eccf44de03185fc52c7c
+size 18284589

ipc_vector_db/index.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88316941d341e914e168e058c26609184e62baf5223b96b510ec65a1da8313cd
+size 5879209

main.py

@@ -0,0 +1,158 @@
+
+import logging
+from langchain_community.document_loaders import PyPDFLoader, DirectoryLoader
+from langchain_huggingface import HuggingFaceEmbeddings
+from sentence_transformers import SentenceTransformer
+
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.vectorstores import FAISS
+from langchain.prompts import PromptTemplate
+from langchain_together import Together
+from langchain.memory import ConversationBufferMemory
+from langchain.chains import ConversationalRetrievalChain
+import streamlit as st
+import os
+
+from dotenv import load_dotenv
+import warnings
+logging.basicConfig(level=logging.DEBUG)  # Logs at DEBUG level and above
+logger = logging.getLogger(__name__)
+
+logger.debug("Starting Streamlit app...")
+# Suppress PyTorch FutureWarning
+warnings.filterwarnings("ignore", message="You are using `torch.load` with `weights_only=False`")
+warnings.filterwarnings("ignore", message="Tried to instantiate class '__path__._path'")
+warnings.filterwarnings("ignore", category=FutureWarning)
+# Suppress generic DeprecationWarnings (including LangChain)
+warnings.filterwarnings("ignore", category=DeprecationWarning)
+
+
+
+load_dotenv()
+TOGETHER_AI_API = os.getenv("TOGETHER_AI")
+
+# Streamlit Page Config
+st.set_page_config(page_title="Law4her")
+col1, col2, col3 = st.columns([1, 4, 1])
+with col2:
+    st.image(
+        "https://res.cloudinary.com/dzzhbgbnp/image/upload/v1736073326/lawforher_logo1_yznqxr.png"
+    )
+
+st.markdown(
+    """
+    <style>
+   div.stButton > button:first-child {
+    background-color: #ffffff; /* White background */
+    color: #000000; /* Black text */
+    border: 1px solid #000000; /* Optional: Add a black border */
+}
+
+div.stButton > button:active {
+    background-color: #e0e0e0; /* Slightly darker white for active state */
+    color: #000000; /* Black text remains the same */
+}
+
+    div[data-testid="stStatusWidget"] div button {
+        display: none;
+    }
+    .reportview-container {
+        margin-top: -2em;
+    }
+    #MainMenu {visibility: hidden;}
+    .stDeployButton {display:none;}
+    footer {visibility: hidden;}
+    #stDecoration {display:none;}
+    button[title="View fullscreen"]{
+        visibility: hidden;}
+    </style>
+    """,
+    unsafe_allow_html=True,
+)
+
+# Reset Conversation
+def reset_conversation():
+    st.session_state.messages = [{"role": "assistant", "content": "Hi, how can I help you?"}]
+    st.session_state.memory.clear()
+
+# Initialize chat messages and memory
+if "messages" not in st.session_state:
+    st.session_state.messages = [{"role": "assistant", "content": "Hi, how can I help you?"}]
+
+if "memory" not in st.session_state:
+    st.session_state.memory = ConversationBufferMemory(
+        memory_key="chat_history",
+        return_messages=True
+    )
+
+# Load embeddings and vectorstore
+embeddings = HuggingFaceEmbeddings(
+    model_name="nomic-ai/nomic-embed-text-v1",
+    model_kwargs={"trust_remote_code": True, "revision": "289f532e14dbbbd5a04753fa58739e9ba766f3c7"},
+)
+
+# Enable dangerous deserialization (safe only if the file is trusted and created by you)
+db = FAISS.load_local("ipc_vector_db", embeddings, allow_dangerous_deserialization=True)
+db_retriever = db.as_retriever(search_type="similarity", search_kwargs={"k": 2, "max_length": 512})
+
+prompt_template = """<s>[INST]As a legal chatbot specializing in the Indian Penal Code, provide a concise and accurate answer based on the given context. Avoid unnecessary details or unrelated content. Only respond if the answer can be derived from the provided context; otherwise, say "The information is not available in the provided context." 
+CONTEXT: {context}
+CHAT HISTORY: {chat_history}
+QUESTION: {question}
+ANSWER:
+</s>[INST]
+"""
+
+prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question", "chat_history"])
+
+# Initialize the Together API
+llm = Together(
+    model="mistralai/Mistral-7B-Instruct-v0.2",
+    temperature=0.5,
+    max_tokens=1024,
+    together_api_key=TOGETHER_AI_API,
+)
+
+qa = ConversationalRetrievalChain.from_llm(
+    llm=llm,
+    memory=st.session_state.memory,
+    retriever=db_retriever,
+    combine_docs_chain_kwargs={"prompt": prompt},
+)
+
+# Display chat history
+for message in st.session_state.messages:
+    with st.chat_message(message.get("role")):
+        st.write(message.get("content"))
+
+# User input
+input_prompt = st.chat_input("Ask a legal question about the Indian Penal Code")
+
+if input_prompt:
+    with st.chat_message("user"):
+        st.write(input_prompt)
+
+    st.session_state.messages.append({"role": "user", "content": input_prompt})
+
+    with st.chat_message("assistant"):
+        with st.status("Thinking 💡...", expanded=True):
+            try:
+                # Pass the user question
+                result = qa.invoke(input=input_prompt)
+                full_response = result.get("answer", "")
+
+                # Ensure the answer is a string
+                if isinstance(full_response, list):
+                    full_response = " ".join(full_response)
+                elif not isinstance(full_response, str):
+                    full_response = str(full_response)
+
+                # Display the response
+                st.session_state.messages.append({"role": "assistant", "content": full_response})
+                st.write(full_response)
+
+            except Exception as e:
+                st.error(f"Error occurred: {e}")
+
+# Add reset button
+st.button("Reset All Chat 🗑", on_click=reset_conversation)

requirements.txt

@@ -0,0 +1,13 @@
+fastapi==0.115.6
+langchain==0.3.14
+langchain_community==0.3.14
+langchain_together==0.2.0
+python-dotenv==1.0.1
+streamlit==1.41.1
+transformers==4.47.1
+uvicorn==0.34.0
+sentence-transformers==3.3.1
+einops==0.8.0
+faiss-cpu==1.9.0.post1
+langchain_huggingface==0.1.2
+torch==2.5.1