ScreenerBot
DocsAssistantConfiguration
ScreenerBot
ScreenerBot

Need Help?

Join our community for support, updates, and trading discussions.

Telegram ChannelTelegram GroupFollow on X (Twitter)Contact Support

Assistant Configuration

Learn how to configure Assistant providers, set up API keys, enable analysis features, and optimize settings for intelligent token screening in ScreenerBot.

Configuration Overview

How Assistant Configuration Works

The Assistant is configured in two main sections of your ScreenerBot config file:

  • •Assistant Providers - Configure API keys, models, and rate limits for each provider
  • •Analysis Features - Enable/disable specific Assistant analysis features like filtering, entry/exit suggestions

All Assistant features are disabled by default to avoid unexpected API costs. You must explicitly enable the features you want to use.

Provider Configuration

Configure one or more Assistant providers in your config.toml file:

config.toml
# AI Provider Configuration
[ai.providers.groq]
enabled = true
api_key = "gsk_xxxxxxxxxxxxxxxxxxxxx"
model = "llama-3.1-70b-versatile"
rate_limit = 30  # requests per minute
timeout = 10     # seconds

[ai.providers.openai]
enabled = true
api_key = "sk-xxxxxxxxxxxxxxxxxxxxx"
model = "gpt-4o-mini"
rate_limit = 60
timeout = 15

[ai.providers.deepseek]
enabled = true
api_key = "sk-xxxxxxxxxxxxxxxxxxxxx"
model = "deepseek-chat"
rate_limit = 500
timeout = 10

Provider Settings Explained

enabledSet to true to activate this provider,false to disable it
api_keyYour API key from the provider. Keep this secret and never commit to version control
modelModel identifier to use. See provider documentation for available models
rate_limitMaximum requests per minute. Prevents hitting provider rate limits
timeoutRequest timeout in seconds. Faster providers can use lower values

API Key Setup by Provider

Groq

Free Tier: 30 requests/minute

Best For: Real-time trading (ultra-fast)

Setup Steps:

  1. Visit console.groq.com
  2. Sign up for a free account
  3. Navigate to API Keys section
  4. Create a new API key
  5. Copy key starting with gsk_

Recommended Model: llama-3.1-70b-versatile

OpenAI

Free Tier: Trial credits only

Best For: Highest accuracy

Setup Steps:

  1. Visit platform.openai.com
  2. Create an account and add payment method
  3. Go to API Keys section
  4. Create a new secret key
  5. Copy key starting with sk-

Recommended Model: gpt-4o-mini

DeepSeek

Free Tier: 500,000 requests/day

Best For: High-volume screening

Setup Steps:

  1. Visit platform.deepseek.com
  2. Create an account
  3. Navigate to API Keys
  4. Generate a new key
  5. Copy the provided key

Recommended Model: deepseek-chat

Ollama (Local)

Free Tier: Unlimited (runs locally)

Best For: Privacy & zero API costs

Setup Steps:

  1. Download from ollama.com
  2. Install and run Ollama
  3. Pull a model: ollama pull llama3.2
  4. Set api_key = "ollama" (not used)
  5. Set base_url = "http://localhost:11434"

Recommended Model: llama3.2 or mistral

See the Providers Reference for setup instructions for all 10+ supported providers.

Enable Analysis Features

After configuring providers, enable the specific AI analysis features you want to use:

config.toml - Assistant Features
# Assistant Features
[ai.analysis]

# Filtering - Assistant helps decide if token should pass filters
filtering_enabled = true
filtering_provider = "groq"

# Entry Analysis - Assistant recommends entry timing
entry_enabled = true
entry_provider = "groq"

# Exit Suggestions - Assistant suggests when to take profits
exit_enabled = true
exit_provider = "groq"

# Auto-Blacklist - Automatically blacklist scam tokens
auto_blacklist_enabled = true
auto_blacklist_provider = "groq"
auto_blacklist_confidence = 0.8  # 0.0-1.0

Filtering Analysis

The Assistant analyzes tokens during filtering to detect scams, poor quality projects, or other red flags. Can prevent tokens from passing filters even if they meet numerical criteria.

When to use:

  • • You want an extra safety layer against scams
  • • You screen hundreds of tokens daily
  • • You trade in high-risk markets

Entry Analysis

Provides Assistant recommendations on whether to enter positions based on market conditions, price action, and risk indicators beyond your configured strategy.

When to use:

  • • You want to avoid FOMO entries
  • • Market conditions are volatile
  • • You need a second opinion on entries

Exit Suggestions

The Assistant suggests optimal exit timing for open positions based on momentum analysis, profit levels, and changing market conditions.

When to use:

  • • You struggle with exit timing
  • • You want to maximize profits
  • • You need help identifying tops

Auto-Blacklist

Automatically adds tokens to the blacklist when the Assistant detects high confidence scam indicators. Prevents future consideration of obvious scams.

When to use:

  • • You want automated scam protection
  • • You screen many new tokens
  • • You prefer conservative filtering

Auto-Blacklist Feature Explained

The Auto-Blacklist feature provides automated protection against scam tokens by permanently blocking tokens that AI identifies as highly suspicious.

How it works:

  1. AI analyzes each token during filtering or entry analysis
  2. If scam indicators exceed the confidence threshold, token is flagged
  3. Token is automatically added to your permanent blacklist
  4. Blacklisted tokens are never analyzed or traded again

Confidence Threshold Settings:

0.9 - 1.0Very Conservative - Only obvious scams
0.8 - 0.9Balanced - Recommended default
0.7 - 0.8Aggressive - Blocks suspicious tokens
Below 0.7Not recommended - Many false positives

Typical scam indicators detected:

  • • Suspicious metadata (excessive emojis, fake branding, scam keywords)
  • • Poor holder distribution (single wallet holds majority)
  • • Unusual liquidity patterns (locked/unlocked inconsistencies)
  • • Known scam contract patterns or similarities
  • • Social links pointing to phishing or suspicious domains

Important Note

Auto-blacklisting is permanent. Review blacklisted tokens periodically in the dashboard to ensure no legitimate tokens were incorrectly flagged. You can manually remove tokens from the blacklist if needed.

Advanced Configuration

Provider Fallback Chain

Configure multiple providers for automatic fallback when one is unavailable or rate-limited:

[ai.analysis]
filtering_enabled = true
# Try Groq first, fall back to DeepSeek if unavailable
filtering_providers = ["groq", "deepseek", "gemini"]

ScreenerBot will try providers in order until one succeeds or all fail.

Rate Limit Management

Adjust rate limits to stay within provider quotas and avoid throttling:

Conservative (Safe)

  • • Groq: 20 RPM
  • • OpenAI: 40 RPM
  • • DeepSeek: 400 RPM

Aggressive (Max Speed)

  • • Groq: 30 RPM
  • • OpenAI: 60 RPM
  • • DeepSeek: 500 RPM

Cache Configuration

AI responses can be cached to reduce API costs and improve response times for repeat analysis:

config.toml - Cache Settings
# AI Cache Configuration
[ai.cache]
enabled = true
ttl = 3600  # Cache duration in seconds (1 hour)
max_entries = 10000  # Maximum cached responses

# Cache filtering results for tokens
cache_filtering = true

# Cache entry/exit analysis
cache_entry_exit = true

How caching works:

  • • AI responses for identical token data are cached and reused
  • • Reduces API costs by avoiding duplicate analysis requests
  • • Speeds up repeat token evaluations significantly
  • • Cache expires after TTL to ensure fresh analysis

Performance Tuning

Optimize AI analysis performance for your trading volume and requirements:

config.toml - Performance Settings
# AI Performance Settings
[ai.performance]
# Maximum concurrent AI requests
max_concurrent = 5

# Request timeout in seconds
timeout = 15

# Retry failed requests
retry_enabled = true
retry_attempts = 3
retry_delay = 2  # seconds between retries

# Skip AI analysis for tokens already blacklisted
skip_blacklisted = true

High-Volume Settings

  • • max_concurrent = 10
  • • timeout = 10
  • • cache.ttl = 7200
  • • Use fast providers (Groq, DeepSeek)

Conservative Settings

  • • max_concurrent = 2
  • • timeout = 30
  • • retry_attempts = 5
  • • Use premium providers (OpenAI, Claude)

Configuration Best Practices

  • Start with Free Providers:Use Groq or DeepSeek initially to test Assistant features before committing to paid providers.
  • Configure Fallbacks:Always set up 2-3 providers for redundancy. If your primary hits rate limits, the bot continues working.
  • Enable Features Gradually:Start with just filtering analysis, monitor results, then enable entry/exit features as you build confidence.
  • Monitor API Usage:Check provider dashboards regularly to track API usage and costs. Adjust rate limits if needed.
  • Secure Your API Keys:Never commit API keys to version control. Use environment variables or keep them in config files that are gitignored.

Important Notes

Test Before Live Trading

Test Assistant configuration thoroughly in paper trading mode before enabling on live positions. Verify that API keys work and responses are as expected.

Restart Required

Changes to Assistant provider configuration require a bot restart to take effect. Changes to enabled features may be applied dynamically depending on the setting.

Next Steps

Provider Reference

Detailed setup instructions, model recommendations, and pricing for all supported providers.

Best Practices

Learn strategies for optimizing AI usage, managing costs, and improving analysis accuracy.