mirror of
https://github.com/blakeblackshear/frigate.git
synced 2026-01-24 21:18:30 +03:00
2c34e1ec10
Some checks are pending
CI / ARM Extra Build (push) Blocked by required conditions
CI / Synaptics Build (push) Blocked by required conditions
CI / Assemble and push default build (push) Blocked by required conditions
CI / AMD64 Build (push) Waiting to run
CI / ARM Build (push) Waiting to run
CI / Jetson Jetpack 6 (push) Waiting to run
CI / AMD64 Extra Build (push) Blocked by required conditions
* Strip model name before training * Handle options file for go2rtc option * Make reviewed optional and add null to API call * Send reviewed for dashboard * Allow setting context size for openai compatible endpoints * push empty go2rtc config to avoid homekit error in log * Add option to set runtime options for LLM providers * Docs --------- Co-authored-by: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>
89 lines
2.8 KiB
Python
89 lines
2.8 KiB
Python
"""Ollama Provider for Frigate AI."""
|
|
|
|
import logging
|
|
from typing import Any, Optional
|
|
|
|
from httpx import RemoteProtocolError, TimeoutException
|
|
from ollama import Client as ApiClient
|
|
from ollama import ResponseError
|
|
|
|
from frigate.config import GenAIProviderEnum
|
|
from frigate.genai import GenAIClient, register_genai_provider
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
@register_genai_provider(GenAIProviderEnum.ollama)
|
|
class OllamaClient(GenAIClient):
|
|
"""Generative AI client for Frigate using Ollama."""
|
|
|
|
LOCAL_OPTIMIZED_OPTIONS = {
|
|
"options": {
|
|
"temperature": 0.5,
|
|
"repeat_penalty": 1.05,
|
|
"presence_penalty": 0.3,
|
|
},
|
|
}
|
|
|
|
provider: ApiClient
|
|
provider_options: dict[str, Any]
|
|
|
|
def _init_provider(self):
|
|
"""Initialize the client."""
|
|
self.provider_options = {
|
|
**self.LOCAL_OPTIMIZED_OPTIONS,
|
|
**self.genai_config.provider_options,
|
|
}
|
|
|
|
try:
|
|
client = ApiClient(host=self.genai_config.base_url, timeout=self.timeout)
|
|
# ensure the model is available locally
|
|
response = client.show(self.genai_config.model)
|
|
if response.get("error"):
|
|
logger.error(
|
|
"Ollama error: %s",
|
|
response["error"],
|
|
)
|
|
return None
|
|
return client
|
|
except Exception as e:
|
|
logger.warning("Error initializing Ollama: %s", str(e))
|
|
return None
|
|
|
|
def _send(self, prompt: str, images: list[bytes]) -> Optional[str]:
|
|
"""Submit a request to Ollama"""
|
|
if self.provider is None:
|
|
logger.warning(
|
|
"Ollama provider has not been initialized, a description will not be generated. Check your Ollama configuration."
|
|
)
|
|
return None
|
|
try:
|
|
ollama_options = {
|
|
**self.provider_options,
|
|
**self.genai_config.runtime_options,
|
|
}
|
|
result = self.provider.generate(
|
|
self.genai_config.model,
|
|
prompt,
|
|
images=images if images else None,
|
|
**ollama_options,
|
|
)
|
|
logger.debug(
|
|
f"Ollama tokens used: eval_count={result.get('eval_count')}, prompt_eval_count={result.get('prompt_eval_count')}"
|
|
)
|
|
return result["response"].strip()
|
|
except (
|
|
TimeoutException,
|
|
ResponseError,
|
|
RemoteProtocolError,
|
|
ConnectionError,
|
|
) as e:
|
|
logger.warning("Ollama returned an error: %s", str(e))
|
|
return None
|
|
|
|
def get_context_size(self) -> int:
|
|
"""Get the context window size for Ollama."""
|
|
return self.genai_config.provider_options.get("options", {}).get(
|
|
"num_ctx", 4096
|
|
)
|