Skip to content

Made env example local-dev friendly #158

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ishaanxgupta merged 1 commit into from
May 7, 2026
Merged

Made env example local-dev friendly #158

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
71 changes: 13 additions & 58 deletions .env.example
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,25 +1,9 @@
# =============================================================================
# Amazon Nova models
# =============================================================================
AWS_ACCESS_KEY_ID=your_aws_access_key_id_here
AWS_SECRET_ACCESS_KEY=your_aws_secret_access_key_here
BEDROCK_REGION=us-east-1
BEDROCK_MODEL=us.amazon.nova-pro-v1:0

# Google Gemini
GEMINI_API_KEY=your_gemini_api_key_here
GEMINI_MODEL=gemini-2.5-flash
Copy link
Copy Markdown

@gemini-code-assist gemini-code-assist Bot May 7, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

The model version gemini-2.5-flash appears to be a typo, as Gemini 2.5 is not a currently available version. For a working local setup, you should likely use gemini-1.5-flash or gemini-2.0-flash.

GEMINI_MODEL=gemini-1.5-flash

# LLM Settings
TEMPERATURE=0.3
FALLBACK_ORDER='["bedrock","openrouter", "gemini", "claude", "openai"]'

# =============================================================================
# Per-Agent Model Overrides (uncomment to use a different model per agent)
# If not set, each agent falls back to GEMINI_MODEL above
# =============================================================================
# CLASSIFIER_MODEL=gemini-2.5-flash
# PROFILER_MODEL=gemini-2.5-flash
# TEMPORAL_MODEL=gemini-2.5-flash
# SUMMARIZER_MODEL=gemini-2.5-flash
# JUDGE_MODEL=gemini-2.5-pro
# RETRIEVAL_MODEL=gemini-3.1-flash-lite-preview
FALLBACK_ORDER='["gemini"]'

# =============================================================================
# Vector Store Configuration (Pinecone)
Expand All @@ -31,13 +15,13 @@ PINECONE_DIMENSION=384
PINECONE_METRIC=cosine
PINECONE_CLOUD=aws
PINECONE_REGION=us-east-1

# EMBEDDING_MODEL=all-MiniLM-L6-v2
EMBEDDING_MODEL=gemini-embedding-001

# =============================================================================
# Database Configuration
# =============================================================================

# MongoDB (for sessions and user profiles)
MONGODB_URI=mongodb+srv://your_user:your_password@cluster.mongodb.net/
MONGODB_DATABASE=xmem
Expand All @@ -55,43 +39,14 @@ API_PORT=8000
CORS_ORIGINS='["http://localhost:3000", "http://localhost:5173"]'
RATE_LIMIT=60

# Google Gemini
GEMINI_API_KEY=your_gemini_api_key_here
GEMINI_MODEL=gemini-2.5-flash
# GEMINI_THINKING_LEVEL=low

# Anthropic Claude
CLAUDE_API_KEY=your_claude_api_key_here
CLAUDE_MODEL=claude-3.5-sonnet

# OpenAI
OPENAI_API_KEY=your_openai_api_key_here
OPENAI_MODEL=gpt-4.1-mini

# OpenRouter (access 200+ models via one API key)
OPENROUTER_API_KEY=your_openrouter_api_key_here
OPENROUTER_MODEL=openai/gpt-4o

# =============================================================================
# Monitoring & Observability
# Authentication
# =============================================================================
Comment on lines 42 to 44
Copy link
Copy Markdown

@gemini-code-assist gemini-code-assist Bot May 7, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

The ENVIRONMENT variable was removed in this PR. Since the default value in src/config/settings.py is production, local instances will default to production mode. To ensure a local-friendly setup (e.g., disabling production-only monitoring or analytics), it is better to explicitly set this to development.

# =============================================================================
# General Settings
# =============================================================================
ENVIRONMENT=development

# =============================================================================
# Authentication
# =============================================================================

ENVIRONMENT=production
GOOGLE_CLIENT_ID=your_google_client_id_here
GOOGLE_CLIENT_SECRET=your-google_client_secret_here
Copy link
Copy Markdown

@gemini-code-assist gemini-code-assist Bot May 7, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

The placeholder for GOOGLE_CLIENT_SECRET uses a hyphen (your-google_client_secret_here), while GOOGLE_CLIENT_ID uses underscores. For consistency across the configuration file, it's recommended to use underscores for all placeholders.

GOOGLE_CLIENT_SECRET=your_google_client_secret_here

GOOGLE_REDIRECT_URI=http://localhost:8000/auth/callback
JWT_SECRET_KEY=your_jwt_secret_key_here
JWT_ALGORITHM=HS256
JWT_EXPIRATION_DAYS=7
FRONTEND_URL=http://localhost:5173

# Sentry error tracking (get DSN from https://sentry.io)
SENTRY_DSN=https://your_dsn@sentry.io/project_id
SENTRY_TRACES_SAMPLE_RATE=1.0
SENTRY_PROFILE_SAMPLE_RATE=1.0
# SENTRY_SERVER_NAME=xmem-prod-01

# Prometheus metrics (exposed at /metrics)
ENABLE_PROMETHEUS=true

# Analytics (fire-and-forget to MongoDB)
ENABLE_ANALYTICS=true

# =============================================================================
# GitHub Integration (admin dashboard traffic graphs)
# =============================================================================
GITHUB_TOKEN=ghp_your_github_personal_access_token
GITHUB_REPO_OWNER=xmemlabs
GITHUB_REPO_NAME=xmem
Loading