[ADD] semantic retrieval process and few improvement

.gitignore

@@ -0,0 +1,57 @@
+# Virtual Environment
+.venv/
+venv/
+ENV/
+
+# Python bytecode
+__pycache__/
+*.py[cod]
+*$py.class
+
+# Distribution / packaging
+dist/
+build/
+*.egg-info/
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IDE specific files
+.idea/
+.vscode/
+*.swp
+*.swo
+
+# OS specific files
+.DS_Store
+.DS_Store?
+._*
+.Spotlight-V100
+.Trashes
+ehthumbs.db
+Thumbs.db
+
+# Logs
+*.log
+
+# Sentence transformers model cache
+.sentence_transformers/
+
+# Gradio specific
+gradio_cached_examples/
+flagged/
+
+# Environment variables
+.env
+.env.local

requirements.txt

@@ -1,4 +1,6 @@
-datasets 
-smolagents 
-langchain-community 
-rank_bm25
+datasets
+smolagents
+langchain-community
+rank_bm25
+gradio
+sentence-transformers