How kethan1712/lexassist-ai works
LexAssist is a legal-information retrieval application: users submit natural-language queries and receive ranked statute results; its documented broader workflow routes questions to local, uploaded-document, or external evidence before generating grounded answers. The tree and excerpts show the statute-search UI and document-processing/search utilities, but not the README-named chat modules. Those documented capabilities are included with null paths; links to them rely on the README rather than sampled implementation.
Main entry points: app.py Flask search · document_chunks.json Document chunks · index.html Search page · document_preprocessor.py Text preprocessing
Components 23
User interface
- Search page
templates/index.html - Flask search
app.py - Ranked provisions
app.py
Legal retrieval
- Query embeddings
app.py - Statute vectors
data/statutes.faiss - Statute metadata
data/statutes_metadata.json - Case results
data/case_results.json
Document evidence
- Legal PDFs
documents/raw - Text preprocessing
document_preprocessor.py - Chunk generation
document_chunker.py - Document chunks
data/document_chunks.json - Document statute search
document_statute_search.py - Document precedent search
document_precedent_search.py - Document summaries
document_summarizer.py
Conversational research
- Chatbot router
- Local evidence
- Uploaded evidence
- External research
- Answer generation
- Conversation history
Other components
- User
- India Code API
- Gemini
Connections 24
- User → Search page: submits query
README.md - Search page → Flask search: posts form
app.py - Flask search → Query embeddings: encodes query
app.py - Flask search → Statute vectors: searches vectors
app.py - Flask search → Statute metadata: resolves results
app.py - Flask search → Case results: loads cases
app.py - Flask search → Ranked provisions: renders results
app.py - Legal PDFs → Text preprocessing: processes text
- Text preprocessing → Chunk generation: prepares pages
- Chunk generation → Document chunks: writes chunks
document_chunker.py - Document chunks → Document statute search: supplies chunks
document_statute_search.py - Document chunks → Document precedent search: supplies chunks
document_precedent_search.py - Document chunks → Document summaries: supplies chunks
document_summarizer.py - User → Chatbot router: asks question
README.md - Conversation history → Chatbot router: provides context
README.md - Chatbot router → Local evidence: routes local search
README.md - Chatbot router → Uploaded evidence: routes document search
README.md - Chatbot router → External research: routes external search
README.md - External research → India Code API: queries API
README.md - Local evidence → Answer generation: supplies evidence
README.md - Uploaded evidence → Answer generation: supplies evidence
README.md - External research → Answer generation: supplies evidence
README.md - Answer generation → Gemini: generates response
README.md - Answer generation → User: returns answer
README.md