Upload 4 files

app.py

@@ -0,0 +1,45 @@
+from flask import Flask,render_template,request,jsonify
+from flask_cors import CORS
+from checkvectordb import getdata,trainpdf1,loadIPCsections,loadmiyapurcourtorders
+app = Flask(__name__)
+CORS(app)
+
+@app.get("/")
+def index_get():
+  print("just started...")
+  #response=loadIPCsections("./uploads/ipc.json")
+  #response=loadmiyapurcourtorders("./uploads/court_history.json")
+
+  #print("------",response)
+  return render_template("base.html")
+
+
+@app.post("/trainpdf")
+def trainpdf():
+  try:
+   pdf_file = request.files['file']
+   response=trainpdf1(pdf_file)
+   print("response :",response);
+   message={"success":response}
+  except Exception as we:
+   message={"error":response}
+   print("-error -", we)
+
+
+  return response
+
+
+
+@app.post("/predict")
+def predict():
+   
+   text=request.get_json().get("message")
+   print("from web ",text);
+   response=getdata(text)
+   message={"answer":response}
+   print("message ",message)
+   return message
+
+if __name__ == "__main__":
+        app.run(host='0.0.0.0', port=5000)   
+  

checkvectordb.py

@@ -0,0 +1,236 @@
+import os
+from flask import Flask, request,render_template, send_from_directory
+
+from flask import Flask, request, jsonify, render_template_string
+import openai
+import langchain
+import os
+from langchain.document_loaders import PyPDFLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.vectorstores import Chroma
+from langchain import OpenAI
+from langchain.schema import Document
+from langchain.chains.question_answering import load_qa_chain
+from langchain.chains import RetrievalQA
+from langchain.chat_models import ChatOpenAI
+import re
+from pdfminer.high_level import extract_pages
+from pdfminer.layout import LTTextContainer, LTChar
+from langchain.prompts import PromptTemplate
+from langchain.chains import LLMChain
+
+import json
+
+import pdfplumber
+import fitz  # PyMuPDF
+
+
+import chromadb
+from chromadb.config import Settings
+
+app = Flask(__name__)
+os.environ["OPENAI_API_KEY"] = "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"
+
+app.config['UPLOAD_FOLDER'] = 'uploads'
+openapi_key="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"
+fpath="./SCHOOL ADMISSI0N TEST 2025-2026.pdf"
+text_splitter=RecursiveCharacterTextSplitter(chunk_size=800,chunk_overlap=50,length_function=len,separators=["\n\n","\n"," "])
+global_var = "I am global"
+
+
+def loadmiyapurcourtorders(pathtosjon):
+  try:
+    with open(pathtosjon, "r", encoding="utf-8") as f:
+     print("--processing pls wait---") 
+     courtcontent = json.load(f)
+
+     docs = []
+     for content in courtcontent:
+
+      content1 = f"""
+      Court Level: {content["court_level"]}
+      Case No: {content["caseno"]}
+      Year: {content["year"]}
+      Prayer: {content["prayer"]}
+      Verdict: {content["verdict"]}
+      Judgement Date: {content["verdictdate"]}
+      Status: {content["status"]}
+      Case Type: {content["casetype"]}
+      petitioner: {content["petitioner"]}
+      respondent 1: {content["Respondent 1"]}
+      judge: {content["judge"]}
+
+      """
+
+
+      metadata = {
+        "case no": str(content["caseno"]),
+        "year": content["year"]
+       
+
+      }
+
+      
+
+    docs.append(Document(page_content=content1, metadata=metadata))
+
+    embeddings = OpenAIEmbeddings(openai_api_key=openapi_key)
+   # store all IPC section Articles here
+    vectorstore = Chroma.from_documents(docs, embeddings, persist_directory="./MiyapurCase_db1")
+  except Exception as er:
+    print("--exception---",er)
+    return jsonify("exception occured while processing...") 
+  
+
+  return "Miyapur court cases are loaded sucessfully"
+
+
+
+def loadIPCsections(pathtosjon):
+  
+  try:
+   with open(pathtosjon, "r", encoding="utf-8") as f:
+    print("--processing pls wait---") 
+    ipc_sections = json.load(f)
+
+   docs = []
+   for section in ipc_sections:
+    content = f"Section {section['Section']}: {section['section_title']}\n{section['section_desc']}"
+    metadata = {
+        "chapter": str(section["chapter"]),
+        "chapter_title": section["chapter_title"],
+        "section": str(section["Section"]),
+        "section_title": section["section_title"]
+    }
+    docs.append(Document(page_content=content, metadata=metadata))
+
+   embeddings = OpenAIEmbeddings(openai_api_key=openapi_key)
+  # store all IPC section Articles here
+   vectorstore = Chroma.from_documents(docs, embeddings, persist_directory="./ChromaIPC_db")
+  except Exception as er:
+    print("--exception---",er)
+    return jsonify("expcetion occured while processing...") 
+  
+
+  return "IPC sections are loaded sucessfully"
+
+def trainpdf1(fpath1):
+
+   print("- fpath1---",fpath1)
+   try:
+    filepath = os.path.join(app.config['UPLOAD_FOLDER'], fpath1.filename)
+    fpath1.save(filepath)
+    embeddings = OpenAIEmbeddings(openai_api_key=openapi_key)
+    loader = PyPDFLoader(filepath)
+    pages = loader.load()  # Returns list of Document objects
+
+   
+    court_text = "\n".join([page.page_content for page in pages])
+
+    # Wrap as LangChain document
+    doc = Document(
+    page_content=court_text,
+    metadata={"source": "court order"}
+    )
+
+    print("- filepath---",filepath)
+
+    #text_splitter = RecursiveCharacterTextSplitter(
+    #    chunk_size=800,
+    #    chunk_overlap=200
+    #)
+    #documents = text_splitter.split_documents(pages)
+
+
+    # store all court order documents here
+    vectorstore = Chroma.from_documents([doc], embeddings, persist_directory="./ChromaCOURT_db")
+    vectorstore.persist()    
+    
+    llm = ChatOpenAI(model="gpt-4", temperature=0)
+
+    prompt = PromptTemplate.from_template("""
+    You are a legal assistant. Given the following court order, list the top 5 relevant legal issues or areas that this case involves (e.g., property rights, public nuisance, fundamental rights, illegal construction, etc.)
+
+    Court Order:
+    {order}
+
+    List 5 legal areas:
+    """)
+    
+    chain = LLMChain(llm=llm, prompt=prompt)
+    response = chain.run(order=court_text)
+ 
+    IPCsearch = Chroma(persist_directory="./ChromaIPC_db", embedding_function=embeddings )
+
+   
+    areas = [area.strip("1234567890. ").strip() for area in response.split('\n') if area.strip()]
+    ipc_matches = []
+    ipc_results = []
+
+    for area in areas[:5]:  # limit to top 5 areas
+     results = IPCsearch.similarity_search(area, k=1)
+    if results:
+        ipc_matches.append((area, results[0]))
+        
+    # 🖨️ Print matched IPC sections
+    for topic, doc in ipc_matches:
+     print(f"\n📘 Legal Area: {topic}")
+     print(f"🔗 IPC Section: {doc.metadata.get('section')} - {doc.metadata.get('section_title')}")
+     print(f"📄 Description: {doc.page_content}")
+
+    for topic, doc in ipc_matches:
+     ipc_results.append({
+        "legal_area": topic,
+        "ipc_section": doc.metadata.get("section"),
+        "section_title": doc.metadata.get("section_title"),
+        "description": doc.page_content,
+        "Orderdocumentation":response
+    })
+
+
+    
+   except Exception as er:
+    print("--exception---",er)
+    return jsonify("This pdf cannot be trained") 
+   
+
+   return ipc_results
+
+def getdata(query):
+ 
+ embeddings = OpenAIEmbeddings(openai_api_key=openapi_key)
+ os.environ['OPENAI_API_KEY'] = openapi_key
+
+ your_case_db = Chroma(persist_directory="./ChromaIPC_db", embedding_function=embeddings)
+ your_case_text = your_case_db.similarity_search("relavant IPC section for bribe", k=1)[0].page_content
+
+ print("---your_case_text-----",your_case_text)
+
+# Load SC case database
+ supreme_db = Chroma(persist_directory="./MiyapurCase_db", embedding_function=embeddings)
+ retriever = supreme_db.as_retriever(search_kwargs={"k": 5})
+
+# Ask for relevant judgments
+ llm = ChatOpenAI(model="gpt-4", temperature=1)
+ qa_chain = RetrievalQA.from_chain_type(llm=llm, retriever=retriever)
+
+ response = qa_chain.run(query)
+
+
+
+
+ return response
+   
+ 
+
+    
+
+
+
+        
+
+
+
+if __name__ == '__main__':
+    app.run(port=8080)

mydocker.dockerfile

@@ -0,0 +1,47 @@
+
+FROM python 3.10
+FROM continuumio/miniconda3
+
+RUN useradd user
+
+USER user
+
+
+COPY ./requirements.txt requirements.txt 
+
+
+
+ENV PYTHONDONTWRITEBYTECODE=1
+ENV PYTHONUNBUFFERED=1
+
+# Set working directory
+WORKDIR /app
+
+# Copy backend files
+COPY . /app
+
+# Create and activate conda env with Python 3.10
+RUN conda create -n myenv python=3.10 -y && \
+    echo "conda activate myenv" >> ~/.bashrc && \
+    /bin/bash -c "source ~/.bashrc && conda activate myenv && pip install --upgrade pip && pip install -r requirements.txt"
+
+# Clone React frontend from GitHub
+RUN apt-get update && \
+    apt-get install -y git curl && \
+    git clone https://github.com/vijaysagi12/myinzackBot.git /frontend
+
+# Install Node.js & npm (for React)
+RUN curl -fsSL https://deb.nodesource.com/setup_18.x | bash - && \
+    apt-get install -y nodejs && \
+    cd /frontend && npm install && npm run build
+
+# Expose Flask and React ports
+EXPOSE 5000 3000
+
+# Start both Flask and React servers
+CMD ["/bin/bash", "-c", "source activate myenv && \
+    (cd /frontend && npm start &) && \
+    python app.py"]
+
+
+

requirements.txt

@@ -0,0 +1,150 @@
+aiohappyeyeballs==2.6.1
+aiohttp==3.12.0
+aiosignal==1.3.2
+annotated-types==0.7.0
+anyio==4.9.0
+asgiref==3.8.1
+async-timeout==4.0.3
+attrs==25.3.0
+backoff==2.2.1
+bcrypt==4.3.0
+blinker==1.9.0
+build==1.2.2.post1
+cachetools==5.5.2
+certifi==2025.4.26
+cffi==1.17.1
+charset-normalizer==3.4.2
+chromadb==1.0.10
+click==8.1.8
+colorama==0.4.6
+coloredlogs==15.0.1
+contourpy==1.3.2
+cryptography==45.0.4
+cycler==0.12.1
+dataclasses-json==0.6.7
+Deprecated==1.2.18
+distro==1.9.0
+durationpy==0.10
+exceptiongroup==1.3.0
+fastapi==0.115.9
+filelock==3.18.0
+Flask==3.1.1
+flask-cors==6.0.0
+flatbuffers==25.2.10
+fonttools==4.58.4
+frozenlist==1.6.0
+fsspec==2025.5.1
+google-auth==2.40.2
+googleapis-common-protos==1.70.0
+greenlet==3.2.2
+grpcio==1.71.0
+h11==0.16.0
+httpcore==1.0.9
+httptools==0.6.4
+httpx==0.28.1
+httpx-sse==0.4.0
+huggingface-hub==0.32.1
+humanfriendly==10.0
+idna==3.10
+importlib_metadata==8.6.1
+importlib_resources==6.5.2
+itsdangerous==2.2.0
+Jinja2==3.1.6
+jiter==0.10.0
+joblib==1.5.1
+jsonpatch==1.33
+jsonpointer==3.0.0
+jsonschema==4.23.0
+jsonschema-specifications==2025.4.1
+kiwisolver==1.4.8
+kubernetes==32.0.1
+langchain==0.3.25
+langchain-community==0.3.24
+langchain-core==0.3.61
+langchain-text-splitters==0.3.8
+langsmith==0.3.42
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+marshmallow==3.26.1
+mdurl==0.1.2
+mmh3==5.1.0
+mpmath==1.3.0
+multidict==6.4.4
+mypy_extensions==1.1.0
+numpy==2.2.6
+oauthlib==3.2.2
+onnxruntime==1.22.0
+openai==1.82.0
+opentelemetry-api==1.33.1
+opentelemetry-exporter-otlp-proto-common==1.33.1
+opentelemetry-exporter-otlp-proto-grpc==1.33.1
+opentelemetry-instrumentation==0.54b1
+opentelemetry-instrumentation-asgi==0.54b1
+opentelemetry-instrumentation-fastapi==0.54b1
+opentelemetry-proto==1.33.1
+opentelemetry-sdk==1.33.1
+opentelemetry-semantic-conventions==0.54b1
+opentelemetry-util-http==0.54b1
+orjson==3.10.18
+overrides==7.7.0
+packaging==24.2
+pdfminer.six==20250506
+pdfplumber==0.11.7
+pillow==11.2.1
+posthog==4.2.0
+propcache==0.3.1
+protobuf==5.29.4
+pyasn1==0.6.1
+pyasn1_modules==0.4.2
+pycparser==2.22
+pydantic==2.11.5
+pydantic-settings==2.9.1
+pydantic_core==2.33.2
+Pygments==2.19.1
+PyMuPDF==1.26.1
+pyparsing==3.2.3
+pypdf==5.5.0
+PyPDF2==3.0.1
+pypdfium2==4.30.1
+PyPika==0.48.9
+pyproject_hooks==1.2.0
+pyreadline3==3.5.4
+python-dateutil==2.9.0.post0
+python-dotenv==1.1.0
+PyYAML==6.0.2
+referencing==0.36.2
+regex==2024.11.6
+requests==2.32.3
+requests-oauthlib==2.0.0
+requests-toolbelt==1.0.0
+rich==14.0.0
+rpds-py==0.25.1
+rsa==4.9.1
+scikit-learn==1.7.0
+scipy==1.15.3
+shellingham==1.5.4
+six==1.17.0
+sniffio==1.3.1
+SQLAlchemy==2.0.41
+starlette==0.45.3
+sympy==1.14.0
+tenacity==9.1.2
+threadpoolctl==3.6.0
+tiktoken==0.9.0
+tokenizers==0.21.1
+tomli==2.2.1
+tqdm==4.67.1
+typer==0.15.4
+typing-inspect==0.9.0
+typing-inspection==0.4.1
+typing_extensions==4.13.2
+urllib3==2.4.0
+uvicorn==0.34.2
+watchfiles==1.0.5
+websocket-client==1.8.0
+websockets==15.0.1
+Werkzeug==3.1.3
+wrapt==1.17.2
+yarl==1.20.0
+zipp==3.21.0
+zstandard==0.23.0