mirror of
https://github.com/ItzCrazyKns/Perplexica.git
synced 2025-06-21 17:28:43 +00:00
5a603a7fd4
the reasoning models using ReasoningChatModel Custom Class.
1. Added the STREAM_DELAY parameter to the sample.config.toml file:
[MODELS.DEEPSEEK]
API_KEY = ""
STREAM_DELAY = 20 # Milliseconds between token emissions for reasoning models (higher = slower, 0 = no delay)
2. Updated the Config interface in src/config.ts to include the new parameter:
DEEPSEEK: {
API_KEY: string;
STREAM_DELAY: number;
};
3. Added a getter function in src/config.ts to retrieve the configured value:
export const getDeepseekStreamDelay = () =>
loadConfig().MODELS.DEEPSEEK.STREAM_DELAY || 20; // Default to 20ms if not specified
Updated the deepseek.ts provider to use the configured stream delay:
const streamDelay = getDeepseekStreamDelay();
logger.debug(`Using stream delay of ${streamDelay}ms for ${model.id}`);
// Then using it in the model configuration
model: new ReasoningChatModel({
// ...other params
streamDelay
}),
4. This implementation provides several benefits:
-User-Configurable: Users can now adjust the stream delay without modifying code
-Descriptive Naming: The parameter name "STREAM_DELAY" clearly indicates its purpose
-Documented: The comment in the config file explains what the parameter does
-Fallback Default: If not specified, it defaults to 20ms
-Logging: Added debug logging to show the configured value when loading models
To adjust the stream delay, users can simply modify the STREAM_DELAY value in
their config.toml file. Higher values will slow down token generation
(making it easier to read in real-time), while lower values will speed it up.
Setting it to 0 will disable the delay entirely.
35 lines
772 B
TOML
35 lines
772 B
TOML
[GENERAL]
|
|
PORT = 3001 # Port to run the server on
|
|
SIMILARITY_MEASURE = "cosine" # "cosine" or "dot"
|
|
KEEP_ALIVE = "5m" # How long to keep Ollama models loaded into memory. (Instead of using -1 use "-1m")
|
|
|
|
[MODELS.OPENAI]
|
|
API_KEY = ""
|
|
|
|
[MODELS.GROQ]
|
|
API_KEY = ""
|
|
|
|
[MODELS.ANTHROPIC]
|
|
API_KEY = ""
|
|
|
|
[MODELS.GEMINI]
|
|
API_KEY = ""
|
|
|
|
[MODELS.DEEPSEEK]
|
|
API_KEY = ""
|
|
STREAM_DELAY = 5 # Milliseconds between token emissions for reasoning models (higher = slower, 0 = no delay)
|
|
|
|
[MODELS.OLLAMA]
|
|
API_URL = "" # Ollama API URL - http://host.docker.internal:11434
|
|
|
|
[MODELS.LMSTUDIO]
|
|
API_URL = "" # LM STUDIO API URL - http://host.docker.internal:1234
|
|
|
|
[MODELS.CUSTOM_OPENAI]
|
|
API_KEY = ""
|
|
API_URL = ""
|
|
MODEL_NAME = ""
|
|
|
|
[API_ENDPOINTS]
|
|
SEARXNG = "http://localhost:32768" # SearxNG API URL
|