11cc14d707
Sovereign backup of all Hermes Agent configuration and data. Excludes: secrets, auth tokens, sessions, caches, code (separate repo). Tracked: - config.yaml (model, fallback chain, toolsets, display prefs) - SOUL.md (Timmy personality charter) - memories/ (persistent MEMORY.md + USER.md) - skills/ (371 files — full skill library) - cron/jobs.json (scheduled tasks) - channel_directory.json (platform channels) - hooks/ (custom hooks)
1.3 KiB
1.3 KiB
Provider Configuration
Guide to using Instructor with different LLM providers.
Anthropic Claude
import instructor
from anthropic import Anthropic
# Basic setup
client = instructor.from_anthropic(Anthropic())
# With API key
client = instructor.from_anthropic(
Anthropic(api_key="your-api-key")
)
# Recommended mode
client = instructor.from_anthropic(
Anthropic(),
mode=instructor.Mode.ANTHROPIC_TOOLS
)
# Usage
result = client.messages.create(
model="claude-sonnet-4-5-20250929",
max_tokens=1024,
messages=[{"role": "user", "content": "..."}],
response_model=YourModel
)
OpenAI
from openai import OpenAI
client = instructor.from_openai(OpenAI())
result = client.chat.completions.create(
model="gpt-4o-mini",
response_model=YourModel,
messages=[{"role": "user", "content": "..."}]
)
Local Models (Ollama)
client = instructor.from_openai(
OpenAI(
base_url="http://localhost:11434/v1",
api_key="ollama"
),
mode=instructor.Mode.JSON
)
result = client.chat.completions.create(
model="llama3.1",
response_model=YourModel,
messages=[...]
)
Modes
Mode.ANTHROPIC_TOOLS: Recommended for ClaudeMode.TOOLS: OpenAI function callingMode.JSON: Fallback for unsupported providers