Feature/hybrid rag pipeline

.env.example

@@ -1,6 +1,46 @@
-# Elastic Cloud Configuration
-# Copy this file to .env and fill in your actual credentials
+# Hybrid RAG Pipeline Environment Configuration
+# Copy this file to .env and fill in your actual values
 
-# Authentication Option 2: API Key (recommended for production)
-# Use either username/password OR api_key, not both
-ELASTIC_API_KEY=elastic-search-api-key-for-elasticsearch-index
+# ===================================================================
+# AWS CONFIGURATION
+# ===================================================================
+# AWS credentials for S3 access (both source and destination)
+AWS_ACCESS_KEY_ID=your-aws-access-key-id
+AWS_SECRET_ACCESS_KEY=your-aws-secret-access-key
+AWS_REGION=us-east-1
+
+# ===================================================================
+# UNSTRUCTURED API CONFIGURATION  
+# ===================================================================
+# Get your API key from: https://unstructured.io
+UNSTRUCTURED_API_KEY=your-unstructured-api-key
+UNSTRUCTURED_API_URL=https://platform.unstructuredapp.io/api/v1
+
+# ===================================================================
+# ELASTICSEARCH CONFIGURATION
+# ===================================================================
+# Elasticsearch Cloud host URL (without https://)
+# Example: my-cluster-abc123.es.us-east-1.aws.found.io:9243
+ELASTICSEARCH_HOST=your-elasticsearch-host-url
+
+# Elasticsearch API key (base64 encoded)
+# Generate this in Kibana: Stack Management > API Keys
+ELASTICSEARCH_API_KEY=your-elasticsearch-api-key
+
+# ===================================================================
+# PIPELINE DATA SOURCES
+# ===================================================================
+# S3 bucket containing Bose product PDFs (manuals, troubleshooting, MSDS)
+S3_SOURCE_BUCKET=example-data-bose-headphones
+
+# Elasticsearch index containing synthetic sales data
+ELASTICSEARCH_INDEX=sales-records
+
+# ===================================================================
+# OPTIONAL: ADVANCED CONFIGURATION
+# ===================================================================
+# AWS Session Token (only needed for temporary credentials)
+# AWS_SESSION_TOKEN=your-session-token
+
+# Custom S3 endpoint (only needed for S3-compatible services)
+# S3_ENDPOINT_URL=https://s3.amazonaws.com

.gitignore

@@ -1,2 +1,33 @@
 .env
-venv/
+venv/
+.env.backup
+__pycache__/
+*.pyc
+*.pyo
+*.pyd
+.DS_Store
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+output-downloads-*/
+
+hybrid_rag_pipeline.py.bak
+hybrid_rag_pipeline_enriched.ipynb.bak
+
+feedback_r1.md
+feedback_r1_cleaned.md
+feedback_r2.md
+feedback_r2_cleaned.md