mirror of
https://github.com/TriliumNext/Notes.git
synced 2025-07-29 19:12:27 +08:00
try using a new ProviderOptions approach
This commit is contained in:
perf3ct
parent
4f812cd2ce
commit
1dfbabc1d1
@ -2,6 +2,9 @@ import options from '../../options.js';
|
||||
import { BaseAIService } from '../base_ai_service.js';
|
||||
import type { ChatCompletionOptions, ChatResponse, Message } from '../ai_interface.js';
|
||||
import { PROVIDER_CONSTANTS } from '../constants/provider_constants.js';
|
||||
import type { AnthropicOptions } from './provider_options.js';
|
||||
import { getAnthropicOptions } from './providers.js';
|
||||
import log from '../../log.js';
|
||||
|
||||
interface AnthropicMessage {
|
||||
role: string;
|
||||
@ -22,42 +25,67 @@ export class AnthropicService extends BaseAIService {
|
||||
throw new Error('Anthropic service is not available. Check API key and AI settings.');
|
||||
}
|
||||
|
||||
const apiKey = options.getOption('anthropicApiKey');
|
||||
const baseUrl = options.getOption('anthropicBaseUrl') || PROVIDER_CONSTANTS.ANTHROPIC.BASE_URL;
|
||||
const model = opts.model || options.getOption('anthropicDefaultModel') || PROVIDER_CONSTANTS.ANTHROPIC.DEFAULT_MODEL;
|
||||
// Get provider-specific options from the central provider manager
|
||||
const providerOptions = getAnthropicOptions(opts);
|
||||
|
||||
const temperature = opts.temperature !== undefined
|
||||
? opts.temperature
|
||||
: parseFloat(options.getOption('aiTemperature') || '0.7');
|
||||
// Log provider metadata if available
|
||||
if (providerOptions.providerMetadata) {
|
||||
log.info(`Using model ${providerOptions.model} from provider ${providerOptions.providerMetadata.provider}`);
|
||||
|
||||
const systemPrompt = this.getSystemPrompt(opts.systemPrompt || options.getOption('aiSystemPrompt'));
|
||||
// Log capabilities if available
|
||||
const capabilities = providerOptions.providerMetadata.capabilities;
|
||||
if (capabilities) {
|
||||
log.info(`Model capabilities: ${JSON.stringify(capabilities)}`);
|
||||
}
|
||||
}
|
||||
|
||||
const systemPrompt = this.getSystemPrompt(providerOptions.systemPrompt || options.getOption('aiSystemPrompt'));
|
||||
|
||||
// Format for Anthropic's API
|
||||
const formattedMessages = this.formatMessages(messages, systemPrompt);
|
||||
|
||||
// Store the formatted messages in the provider options for future reference
|
||||
providerOptions.formattedMessages = formattedMessages;
|
||||
|
||||
try {
|
||||
// Ensure base URL doesn't already include '/v1' and build the complete endpoint
|
||||
const cleanBaseUrl = baseUrl.replace(/\/+$/, '').replace(/\/v1$/, '');
|
||||
const cleanBaseUrl = providerOptions.baseUrl.replace(/\/+$/, '').replace(/\/v1$/, '');
|
||||
const endpoint = `${cleanBaseUrl}/v1/messages`;
|
||||
|
||||
console.log(`Anthropic API endpoint: ${endpoint}`);
|
||||
console.log(`Using model: ${model}`);
|
||||
console.log(`Using model: ${providerOptions.model}`);
|
||||
|
||||
// Create request body directly from provider options
|
||||
const requestBody: any = {
|
||||
model: providerOptions.model,
|
||||
messages: formattedMessages.messages,
|
||||
system: formattedMessages.system,
|
||||
};
|
||||
|
||||
// Extract API parameters from provider options
|
||||
const apiParams = {
|
||||
temperature: providerOptions.temperature,
|
||||
max_tokens: providerOptions.max_tokens,
|
||||
stream: providerOptions.stream,
|
||||
top_p: providerOptions.top_p
|
||||
};
|
||||
|
||||
// Merge API parameters, filtering out undefined values
|
||||
Object.entries(apiParams).forEach(([key, value]) => {
|
||||
if (value !== undefined) {
|
||||
requestBody[key] = value;
|
||||
}
|
||||
});
|
||||
|
||||
const response = await fetch(endpoint, {
|
||||
method: 'POST',
|
||||
headers: {
|
||||
'Content-Type': 'application/json',
|
||||
'X-Api-Key': apiKey,
|
||||
'anthropic-version': PROVIDER_CONSTANTS.ANTHROPIC.API_VERSION,
|
||||
'anthropic-beta': PROVIDER_CONSTANTS.ANTHROPIC.BETA_VERSION
|
||||
'X-Api-Key': providerOptions.apiKey,
|
||||
'anthropic-version': providerOptions.apiVersion || PROVIDER_CONSTANTS.ANTHROPIC.API_VERSION,
|
||||
'anthropic-beta': providerOptions.betaVersion || PROVIDER_CONSTANTS.ANTHROPIC.BETA_VERSION
|
||||
},
|
||||
body: JSON.stringify({
|
||||
model,
|
||||
messages: formattedMessages.messages,
|
||||
system: formattedMessages.system,
|
||||
temperature,
|
||||
max_tokens: opts.maxTokens || 4000,
|
||||
})
|
||||
body: JSON.stringify(requestBody)
|
||||
});
|
||||
|
||||
if (!response.ok) {
|
||||
|
||||
@ -6,6 +6,8 @@ import { OllamaMessageFormatter } from '../formatters/ollama_formatter.js';
|
||||
import log from '../../log.js';
|
||||
import type { ToolCall } from '../tools/tool_interfaces.js';
|
||||
import toolRegistry from '../tools/tool_registry.js';
|
||||
import type { OllamaOptions } from './provider_options.js';
|
||||
import { getOllamaOptions } from './providers.js';
|
||||
|
||||
interface OllamaFunctionArguments {
|
||||
[key: string]: any;
|
||||
@ -65,32 +67,33 @@ export class OllamaService extends BaseAIService {
|
||||
throw new Error('Ollama service is not available. Check API URL in settings.');
|
||||
}
|
||||
|
||||
const apiBase = options.getOption('ollamaBaseUrl');
|
||||
// Get provider-specific options from the central provider manager
|
||||
const providerOptions = await getOllamaOptions(opts);
|
||||
|
||||
// Get the model name and strip the "ollama:" prefix if it exists
|
||||
let model = opts.model || options.getOption('ollamaDefaultModel') || 'llama3';
|
||||
if (model.startsWith('ollama:')) {
|
||||
model = model.substring(7); // Remove the "ollama:" prefix
|
||||
log.info(`Stripped 'ollama:' prefix from model name, using: ${model}`);
|
||||
// Log provider metadata if available
|
||||
if (providerOptions.providerMetadata) {
|
||||
log.info(`Using model ${providerOptions.model} from provider ${providerOptions.providerMetadata.provider}`);
|
||||
|
||||
// Log capabilities if available
|
||||
const capabilities = providerOptions.providerMetadata.capabilities;
|
||||
if (capabilities) {
|
||||
log.info(`Model capabilities: ${JSON.stringify(capabilities)}`);
|
||||
}
|
||||
}
|
||||
|
||||
const temperature = opts.temperature !== undefined
|
||||
? opts.temperature
|
||||
: parseFloat(options.getOption('aiTemperature') || '0.7');
|
||||
|
||||
const systemPrompt = this.getSystemPrompt(opts.systemPrompt || options.getOption('aiSystemPrompt'));
|
||||
const systemPrompt = this.getSystemPrompt(providerOptions.systemPrompt || options.getOption('aiSystemPrompt'));
|
||||
|
||||
try {
|
||||
// Check if we should add tool execution feedback
|
||||
if (opts.toolExecutionStatus && Array.isArray(opts.toolExecutionStatus) && opts.toolExecutionStatus.length > 0) {
|
||||
if (providerOptions.toolExecutionStatus && Array.isArray(providerOptions.toolExecutionStatus) && providerOptions.toolExecutionStatus.length > 0) {
|
||||
log.info(`Adding tool execution feedback to messages`);
|
||||
messages = this.addToolExecutionFeedback(messages, opts.toolExecutionStatus);
|
||||
messages = this.addToolExecutionFeedback(messages, providerOptions.toolExecutionStatus);
|
||||
}
|
||||
|
||||
// Determine whether to use the formatter or send messages directly
|
||||
let messagesToSend: Message[];
|
||||
|
||||
if (opts.bypassFormatter) {
|
||||
if (providerOptions.bypassFormatter) {
|
||||
// Bypass the formatter entirely - use messages as is
|
||||
messagesToSend = [...messages];
|
||||
log.info(`Bypassing formatter for Ollama request with ${messages.length} messages`);
|
||||
@ -100,69 +103,58 @@ export class OllamaService extends BaseAIService {
|
||||
messages,
|
||||
systemPrompt,
|
||||
undefined, // context
|
||||
opts.preserveSystemPrompt
|
||||
providerOptions.preserveSystemPrompt
|
||||
);
|
||||
log.info(`Sending to Ollama with formatted messages: ${messagesToSend.length}`);
|
||||
}
|
||||
|
||||
// Check if this is a request that expects JSON response
|
||||
const expectsJsonResponse = opts.expectsJsonResponse || false;
|
||||
|
||||
// Build request body
|
||||
// Build request body base
|
||||
const requestBody: any = {
|
||||
model,
|
||||
messages: messagesToSend,
|
||||
options: {
|
||||
temperature,
|
||||
// Add num_ctx parameter based on model capabilities
|
||||
num_ctx: await this.getModelContextWindowTokens(model),
|
||||
// Add response_format for requests that expect JSON
|
||||
...(expectsJsonResponse ? { response_format: { type: "json_object" } } : {})
|
||||
},
|
||||
stream: false
|
||||
model: providerOptions.model,
|
||||
messages: messagesToSend
|
||||
};
|
||||
|
||||
// Add tools if enabled - put them at the top level for Ollama
|
||||
if (opts.enableTools !== false) {
|
||||
// Get tools from registry if not provided in options
|
||||
if (!opts.tools || opts.tools.length === 0) {
|
||||
try {
|
||||
// Get tool definitions from registry
|
||||
const tools = toolRegistry.getAllToolDefinitions();
|
||||
requestBody.tools = tools;
|
||||
log.info(`Adding ${tools.length} tools to request`);
|
||||
|
||||
// If no tools found, reinitialize
|
||||
if (tools.length === 0) {
|
||||
log.info('No tools found in registry, re-initializing...');
|
||||
log.info(`Stream: ${providerOptions.stream}`);
|
||||
// Stream is a top-level option
|
||||
if (providerOptions.stream !== undefined) {
|
||||
requestBody.stream = providerOptions.stream;
|
||||
}
|
||||
|
||||
// Add options object if provided
|
||||
if (providerOptions.options) {
|
||||
requestBody.options = { ...providerOptions.options };
|
||||
}
|
||||
|
||||
// Add tools if enabled
|
||||
if (providerOptions.enableTools !== false) {
|
||||
// Use provided tools or get from registry
|
||||
try {
|
||||
requestBody.tools = providerOptions.tools && providerOptions.tools.length > 0
|
||||
? providerOptions.tools
|
||||
: toolRegistry.getAllToolDefinitions();
|
||||
|
||||
// Handle empty tools array
|
||||
if (requestBody.tools.length === 0) {
|
||||
log.info('No tools found, attempting to initialize tools...');
|
||||
const toolInitializer = await import('../tools/tool_initializer.js');
|
||||
await toolInitializer.default.initializeTools();
|
||||
|
||||
// Try again
|
||||
requestBody.tools = toolRegistry.getAllToolDefinitions();
|
||||
log.info(`After re-initialization: ${requestBody.tools.length} tools available`);
|
||||
} catch (err: any) {
|
||||
log.error(`Failed to re-initialize tools: ${err.message}`);
|
||||
}
|
||||
log.info(`After initialization: ${requestBody.tools.length} tools available`);
|
||||
}
|
||||
} catch (error: any) {
|
||||
log.error(`Error getting tools: ${error.message || String(error)}`);
|
||||
// Create default empty tools array if we couldn't load the tools
|
||||
requestBody.tools = [];
|
||||
log.error(`Error preparing tools: ${error.message || String(error)}`);
|
||||
requestBody.tools = []; // Empty fallback
|
||||
}
|
||||
} else {
|
||||
requestBody.tools = opts.tools;
|
||||
}
|
||||
log.info(`Adding ${requestBody.tools.length} tools to Ollama request`);
|
||||
} else {
|
||||
log.info('Tools are explicitly disabled for this request');
|
||||
}
|
||||
|
||||
// Log key request details
|
||||
// Log request details
|
||||
log.info(`========== OLLAMA API REQUEST ==========`);
|
||||
log.info(`Model: ${requestBody.model}, Messages: ${requestBody.messages.length}, Tools: ${requestBody.tools ? requestBody.tools.length : 0}`);
|
||||
log.info(`Temperature: ${temperature}, Stream: ${requestBody.stream}, JSON response expected: ${expectsJsonResponse}`);
|
||||
log.info(`Stream: ${requestBody.stream || false}, JSON response expected: ${providerOptions.expectsJsonResponse}`);
|
||||
if (requestBody.options) {
|
||||
log.info(`Options: ${JSON.stringify(requestBody.options)}`);
|
||||
}
|
||||
|
||||
// Check message structure and log detailed information about each message
|
||||
requestBody.messages.forEach((msg: any, index: number) => {
|
||||
@ -222,26 +214,13 @@ export class OllamaService extends BaseAIService {
|
||||
log.info(`========== FULL OLLAMA REQUEST ==========`);
|
||||
|
||||
// Log request in manageable chunks
|
||||
const maxChunkSize = 4000;
|
||||
if (requestStr.length > maxChunkSize) {
|
||||
let i = 0;
|
||||
while (i < requestStr.length) {
|
||||
const chunk = requestStr.substring(i, i + maxChunkSize);
|
||||
log.info(`Request part ${Math.floor(i/maxChunkSize) + 1}/${Math.ceil(requestStr.length/maxChunkSize)}: ${chunk}`);
|
||||
i += maxChunkSize;
|
||||
}
|
||||
} else {
|
||||
log.info(`Full request: ${requestStr}`);
|
||||
}
|
||||
log.info(`========== END FULL OLLAMA REQUEST ==========`);
|
||||
log.info(`========== END OLLAMA REQUEST ==========`);
|
||||
|
||||
// Make API request
|
||||
const response = await fetch(`${apiBase}/api/chat`, {
|
||||
// Send the request
|
||||
const response = await fetch(`${providerOptions.baseUrl}/api/chat`, {
|
||||
method: 'POST',
|
||||
headers: {
|
||||
'Content-Type': 'application/json'
|
||||
},
|
||||
headers: { 'Content-Type': 'application/json' },
|
||||
body: JSON.stringify(requestBody)
|
||||
});
|
||||
|
||||
|
||||
@ -2,6 +2,8 @@ import options from '../../options.js';
|
||||
import { BaseAIService } from '../base_ai_service.js';
|
||||
import type { ChatCompletionOptions, ChatResponse, Message } from '../ai_interface.js';
|
||||
import { PROVIDER_CONSTANTS } from '../constants/provider_constants.js';
|
||||
import type { OpenAIOptions } from './provider_options.js';
|
||||
import { getOpenAIOptions } from './providers.js';
|
||||
|
||||
export class OpenAIService extends BaseAIService {
|
||||
constructor() {
|
||||
@ -17,14 +19,10 @@ export class OpenAIService extends BaseAIService {
|
||||
throw new Error('OpenAI service is not available. Check API key and AI settings.');
|
||||
}
|
||||
|
||||
const apiKey = options.getOption('openaiApiKey');
|
||||
const baseUrl = options.getOption('openaiBaseUrl') || PROVIDER_CONSTANTS.OPENAI.BASE_URL;
|
||||
const model = opts.model || options.getOption('openaiDefaultModel') || PROVIDER_CONSTANTS.OPENAI.DEFAULT_MODEL;
|
||||
const temperature = opts.temperature !== undefined
|
||||
? opts.temperature
|
||||
: parseFloat(options.getOption('aiTemperature') || '0.7');
|
||||
// Get provider-specific options from the central provider manager
|
||||
const providerOptions = getOpenAIOptions(opts);
|
||||
|
||||
const systemPrompt = this.getSystemPrompt(opts.systemPrompt || options.getOption('aiSystemPrompt'));
|
||||
const systemPrompt = this.getSystemPrompt(providerOptions.systemPrompt || options.getOption('aiSystemPrompt'));
|
||||
|
||||
// Ensure we have a system message
|
||||
const systemMessageExists = messages.some(m => m.role === 'system');
|
||||
@ -34,23 +32,52 @@ export class OpenAIService extends BaseAIService {
|
||||
|
||||
try {
|
||||
// Fix endpoint construction - ensure we don't double up on /v1
|
||||
const normalizedBaseUrl = baseUrl.replace(/\/+$/, '');
|
||||
const normalizedBaseUrl = providerOptions.baseUrl.replace(/\/+$/, '');
|
||||
const endpoint = normalizedBaseUrl.includes('/v1')
|
||||
? `${normalizedBaseUrl}/chat/completions`
|
||||
: `${normalizedBaseUrl}/v1/chat/completions`;
|
||||
|
||||
// Create request body directly from provider options
|
||||
const requestBody: any = {
|
||||
model: providerOptions.model,
|
||||
messages: messagesWithSystem,
|
||||
};
|
||||
|
||||
// Extract API parameters from provider options
|
||||
const apiParams = {
|
||||
temperature: providerOptions.temperature,
|
||||
max_tokens: providerOptions.max_tokens,
|
||||
stream: providerOptions.stream,
|
||||
top_p: providerOptions.top_p,
|
||||
frequency_penalty: providerOptions.frequency_penalty,
|
||||
presence_penalty: providerOptions.presence_penalty
|
||||
};
|
||||
|
||||
|
||||
|
||||
// Merge API parameters, filtering out undefined values
|
||||
Object.entries(apiParams).forEach(([key, value]) => {
|
||||
if (value !== undefined) {
|
||||
requestBody[key] = value;
|
||||
}
|
||||
});
|
||||
|
||||
// Add tools if enabled
|
||||
if (providerOptions.enableTools && providerOptions.tools && providerOptions.tools.length > 0) {
|
||||
requestBody.tools = providerOptions.tools;
|
||||
}
|
||||
|
||||
if (providerOptions.tool_choice) {
|
||||
requestBody.tool_choice = providerOptions.tool_choice;
|
||||
}
|
||||
|
||||
const response = await fetch(endpoint, {
|
||||
method: 'POST',
|
||||
headers: {
|
||||
'Content-Type': 'application/json',
|
||||
'Authorization': `Bearer ${apiKey}`
|
||||
'Authorization': `Bearer ${providerOptions.apiKey}`
|
||||
},
|
||||
body: JSON.stringify({
|
||||
model,
|
||||
messages: messagesWithSystem,
|
||||
temperature,
|
||||
max_tokens: opts.maxTokens,
|
||||
})
|
||||
body: JSON.stringify(requestBody)
|
||||
});
|
||||
|
||||
if (!response.ok) {
|
||||
@ -68,7 +95,8 @@ export class OpenAIService extends BaseAIService {
|
||||
promptTokens: data.usage?.prompt_tokens,
|
||||
completionTokens: data.usage?.completion_tokens,
|
||||
totalTokens: data.usage?.total_tokens
|
||||
}
|
||||
},
|
||||
tool_calls: data.choices[0].message.tool_calls
|
||||
};
|
||||
} catch (error) {
|
||||
console.error('OpenAI service error:', error);
|
||||
|
||||
202
src/services/llm/providers/provider_options.ts
Normal file
202
src/services/llm/providers/provider_options.ts
Normal file
@ -0,0 +1,202 @@
|
||||
import type { Message, ChatCompletionOptions } from '../ai_interface.js';
|
||||
import type { ToolCall } from '../tools/tool_interfaces.js';
|
||||
|
||||
/**
|
||||
* Model metadata interface to track provider information
|
||||
*/
|
||||
export interface ModelMetadata {
|
||||
// The provider that supports this model
|
||||
provider: 'openai' | 'anthropic' | 'ollama' | 'local';
|
||||
// The actual model identifier used by the provider's API
|
||||
modelId: string;
|
||||
// Display name for UI (optional)
|
||||
displayName?: string;
|
||||
// Model capabilities
|
||||
capabilities?: {
|
||||
contextWindow?: number;
|
||||
supportsTools?: boolean;
|
||||
supportsVision?: boolean;
|
||||
supportsStreaming?: boolean;
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* Base provider configuration that's common to all providers
|
||||
* but not necessarily sent directly to APIs
|
||||
*/
|
||||
export interface ProviderConfig {
|
||||
// Internal configuration
|
||||
systemPrompt?: string;
|
||||
// Provider metadata for model routing
|
||||
providerMetadata?: ModelMetadata;
|
||||
}
|
||||
|
||||
/**
|
||||
* OpenAI-specific options, structured to match the OpenAI API
|
||||
*/
|
||||
export interface OpenAIOptions extends ProviderConfig {
|
||||
// Connection settings (not sent to API)
|
||||
apiKey: string;
|
||||
baseUrl: string;
|
||||
|
||||
// Direct API parameters as they appear in requests
|
||||
model: string;
|
||||
messages?: Message[];
|
||||
temperature?: number;
|
||||
max_tokens?: number;
|
||||
stream?: boolean;
|
||||
top_p?: number;
|
||||
frequency_penalty?: number;
|
||||
presence_penalty?: number;
|
||||
tools?: any[];
|
||||
tool_choice?: string | object;
|
||||
|
||||
// Internal control flags (not sent directly to API)
|
||||
enableTools?: boolean;
|
||||
}
|
||||
|
||||
/**
|
||||
* Anthropic-specific options, structured to match the Anthropic API
|
||||
*/
|
||||
export interface AnthropicOptions extends ProviderConfig {
|
||||
// Connection settings (not sent to API)
|
||||
apiKey: string;
|
||||
baseUrl: string;
|
||||
apiVersion?: string;
|
||||
betaVersion?: string;
|
||||
|
||||
// Direct API parameters as they appear in requests
|
||||
model: string;
|
||||
messages?: any[];
|
||||
system?: string;
|
||||
temperature?: number;
|
||||
max_tokens?: number;
|
||||
stream?: boolean;
|
||||
top_p?: number;
|
||||
|
||||
// Internal parameters (not sent directly to API)
|
||||
formattedMessages?: { messages: any[], system: string };
|
||||
}
|
||||
|
||||
/**
|
||||
* Ollama-specific options, structured to match the Ollama API
|
||||
*/
|
||||
export interface OllamaOptions extends ProviderConfig {
|
||||
// Connection settings (not sent to API)
|
||||
baseUrl: string;
|
||||
|
||||
// Direct API parameters as they appear in requests
|
||||
model: string;
|
||||
messages?: Message[];
|
||||
stream?: boolean;
|
||||
options?: {
|
||||
temperature?: number;
|
||||
num_ctx?: number;
|
||||
top_p?: number;
|
||||
top_k?: number;
|
||||
num_predict?: number; // equivalent to max_tokens
|
||||
response_format?: { type: string };
|
||||
};
|
||||
tools?: any[];
|
||||
|
||||
// Internal control flags (not sent directly to API)
|
||||
enableTools?: boolean;
|
||||
bypassFormatter?: boolean;
|
||||
preserveSystemPrompt?: boolean;
|
||||
expectsJsonResponse?: boolean;
|
||||
toolExecutionStatus?: any[];
|
||||
}
|
||||
|
||||
/**
|
||||
* Create OpenAI options from generic options and config
|
||||
*/
|
||||
export function createOpenAIOptions(
|
||||
opts: ChatCompletionOptions = {},
|
||||
apiKey: string,
|
||||
baseUrl: string,
|
||||
defaultModel: string
|
||||
): OpenAIOptions {
|
||||
return {
|
||||
// Connection settings
|
||||
apiKey,
|
||||
baseUrl,
|
||||
|
||||
// API parameters
|
||||
model: opts.model || defaultModel,
|
||||
temperature: opts.temperature,
|
||||
max_tokens: opts.maxTokens,
|
||||
stream: opts.stream,
|
||||
top_p: opts.topP,
|
||||
frequency_penalty: opts.frequencyPenalty,
|
||||
presence_penalty: opts.presencePenalty,
|
||||
tools: opts.tools,
|
||||
|
||||
// Internal configuration
|
||||
systemPrompt: opts.systemPrompt,
|
||||
enableTools: opts.enableTools,
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* Create Anthropic options from generic options and config
|
||||
*/
|
||||
export function createAnthropicOptions(
|
||||
opts: ChatCompletionOptions = {},
|
||||
apiKey: string,
|
||||
baseUrl: string,
|
||||
defaultModel: string,
|
||||
apiVersion: string,
|
||||
betaVersion: string
|
||||
): AnthropicOptions {
|
||||
return {
|
||||
// Connection settings
|
||||
apiKey,
|
||||
baseUrl,
|
||||
apiVersion,
|
||||
betaVersion,
|
||||
|
||||
// API parameters
|
||||
model: opts.model || defaultModel,
|
||||
temperature: opts.temperature,
|
||||
max_tokens: opts.maxTokens,
|
||||
stream: opts.stream,
|
||||
top_p: opts.topP,
|
||||
|
||||
// Internal configuration
|
||||
systemPrompt: opts.systemPrompt,
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* Create Ollama options from generic options and config
|
||||
*/
|
||||
export function createOllamaOptions(
|
||||
opts: ChatCompletionOptions = {},
|
||||
baseUrl: string,
|
||||
defaultModel: string,
|
||||
contextWindow: number
|
||||
): OllamaOptions {
|
||||
return {
|
||||
// Connection settings
|
||||
baseUrl,
|
||||
|
||||
// API parameters
|
||||
model: opts.model || defaultModel,
|
||||
stream: opts.stream,
|
||||
options: {
|
||||
temperature: opts.temperature,
|
||||
num_ctx: contextWindow,
|
||||
num_predict: opts.maxTokens,
|
||||
response_format: opts.expectsJsonResponse ? { type: "json_object" } : undefined
|
||||
},
|
||||
tools: opts.tools,
|
||||
|
||||
// Internal configuration
|
||||
systemPrompt: opts.systemPrompt,
|
||||
enableTools: opts.enableTools,
|
||||
bypassFormatter: opts.bypassFormatter,
|
||||
preserveSystemPrompt: opts.preserveSystemPrompt,
|
||||
expectsJsonResponse: opts.expectsJsonResponse,
|
||||
toolExecutionStatus: opts.toolExecutionStatus,
|
||||
};
|
||||
}
|
||||
@ -9,6 +9,14 @@ import { OpenAIEmbeddingProvider } from "../embeddings/providers/openai.js";
|
||||
import { OllamaEmbeddingProvider } from "../embeddings/providers/ollama.js";
|
||||
import { VoyageEmbeddingProvider } from "../embeddings/providers/voyage.js";
|
||||
import type { OptionDefinitions } from "../../options_interface.js";
|
||||
import type { ChatCompletionOptions } from '../ai_interface.js';
|
||||
import type { OpenAIOptions, AnthropicOptions, OllamaOptions, ModelMetadata } from './provider_options.js';
|
||||
import {
|
||||
createOpenAIOptions,
|
||||
createAnthropicOptions,
|
||||
createOllamaOptions
|
||||
} from './provider_options.js';
|
||||
import { PROVIDER_CONSTANTS } from '../constants/provider_constants.js';
|
||||
|
||||
/**
|
||||
* Simple local embedding provider implementation
|
||||
@ -362,3 +370,238 @@ export default {
|
||||
getEmbeddingProviderConfigs,
|
||||
initializeDefaultProviders
|
||||
};
|
||||
|
||||
/**
|
||||
* Get OpenAI provider options from chat options and configuration
|
||||
* Updated to use provider metadata approach
|
||||
*/
|
||||
export function getOpenAIOptions(
|
||||
opts: ChatCompletionOptions = {}
|
||||
): OpenAIOptions {
|
||||
try {
|
||||
const apiKey = options.getOption('openaiApiKey');
|
||||
if (!apiKey) {
|
||||
throw new Error('OpenAI API key is not configured');
|
||||
}
|
||||
|
||||
const baseUrl = options.getOption('openaiBaseUrl') || PROVIDER_CONSTANTS.OPENAI.BASE_URL;
|
||||
const modelName = opts.model || options.getOption('openaiDefaultModel') || PROVIDER_CONSTANTS.OPENAI.DEFAULT_MODEL;
|
||||
|
||||
// Create provider metadata
|
||||
const providerMetadata: ModelMetadata = {
|
||||
provider: 'openai',
|
||||
modelId: modelName,
|
||||
displayName: modelName,
|
||||
capabilities: {
|
||||
supportsTools: modelName.includes('gpt-4') || modelName.includes('gpt-3.5-turbo'),
|
||||
supportsVision: modelName.includes('vision') || modelName.includes('gpt-4-turbo') || modelName.includes('gpt-4o'),
|
||||
supportsStreaming: true
|
||||
}
|
||||
};
|
||||
|
||||
// Get temperature from options or global setting
|
||||
const temperature = opts.temperature !== undefined
|
||||
? opts.temperature
|
||||
: parseFloat(options.getOption('aiTemperature') || '0.7');
|
||||
|
||||
return {
|
||||
// Connection settings
|
||||
apiKey,
|
||||
baseUrl,
|
||||
|
||||
// Provider metadata
|
||||
providerMetadata,
|
||||
|
||||
// API parameters
|
||||
model: modelName,
|
||||
temperature,
|
||||
max_tokens: opts.maxTokens,
|
||||
stream: opts.stream,
|
||||
top_p: opts.topP,
|
||||
frequency_penalty: opts.frequencyPenalty,
|
||||
presence_penalty: opts.presencePenalty,
|
||||
tools: opts.tools,
|
||||
|
||||
// Internal configuration
|
||||
systemPrompt: opts.systemPrompt,
|
||||
enableTools: opts.enableTools,
|
||||
};
|
||||
} catch (error) {
|
||||
log.error(`Error creating OpenAI provider options: ${error}`);
|
||||
throw error;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Get Anthropic provider options from chat options and configuration
|
||||
* Updated to use provider metadata approach
|
||||
*/
|
||||
export function getAnthropicOptions(
|
||||
opts: ChatCompletionOptions = {}
|
||||
): AnthropicOptions {
|
||||
try {
|
||||
const apiKey = options.getOption('anthropicApiKey');
|
||||
if (!apiKey) {
|
||||
throw new Error('Anthropic API key is not configured');
|
||||
}
|
||||
|
||||
const baseUrl = options.getOption('anthropicBaseUrl') || PROVIDER_CONSTANTS.ANTHROPIC.BASE_URL;
|
||||
const modelName = opts.model || options.getOption('anthropicDefaultModel') || PROVIDER_CONSTANTS.ANTHROPIC.DEFAULT_MODEL;
|
||||
|
||||
// Create provider metadata
|
||||
const providerMetadata: ModelMetadata = {
|
||||
provider: 'anthropic',
|
||||
modelId: modelName,
|
||||
displayName: modelName,
|
||||
capabilities: {
|
||||
supportsTools: modelName.includes('claude-3') || modelName.includes('claude-3.5'),
|
||||
supportsVision: modelName.includes('claude-3') || modelName.includes('claude-3.5'),
|
||||
supportsStreaming: true,
|
||||
// Anthropic models typically have large context windows
|
||||
contextWindow: modelName.includes('claude-3-opus') ? 200000 :
|
||||
modelName.includes('claude-3-sonnet') ? 180000 :
|
||||
modelName.includes('claude-3.5-sonnet') ? 200000 : 100000
|
||||
}
|
||||
};
|
||||
|
||||
// Get temperature from options or global setting
|
||||
const temperature = opts.temperature !== undefined
|
||||
? opts.temperature
|
||||
: parseFloat(options.getOption('aiTemperature') || '0.7');
|
||||
|
||||
return {
|
||||
// Connection settings
|
||||
apiKey,
|
||||
baseUrl,
|
||||
apiVersion: PROVIDER_CONSTANTS.ANTHROPIC.API_VERSION,
|
||||
betaVersion: PROVIDER_CONSTANTS.ANTHROPIC.BETA_VERSION,
|
||||
|
||||
// Provider metadata
|
||||
providerMetadata,
|
||||
|
||||
// API parameters
|
||||
model: modelName,
|
||||
temperature,
|
||||
max_tokens: opts.maxTokens,
|
||||
stream: opts.stream,
|
||||
top_p: opts.topP,
|
||||
|
||||
// Internal configuration
|
||||
systemPrompt: opts.systemPrompt
|
||||
};
|
||||
} catch (error) {
|
||||
log.error(`Error creating Anthropic provider options: ${error}`);
|
||||
throw error;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Get Ollama provider options from chat options and configuration
|
||||
* This implementation cleanly separates provider information from model names
|
||||
*/
|
||||
export async function getOllamaOptions(
|
||||
opts: ChatCompletionOptions = {},
|
||||
contextWindow?: number
|
||||
): Promise<OllamaOptions> {
|
||||
try {
|
||||
const baseUrl = options.getOption('ollamaBaseUrl');
|
||||
if (!baseUrl) {
|
||||
throw new Error('Ollama API URL is not configured');
|
||||
}
|
||||
|
||||
// Get the model name - no prefix handling needed now
|
||||
let modelName = opts.model || options.getOption('ollamaDefaultModel') || 'llama3';
|
||||
|
||||
// Create provider metadata
|
||||
const providerMetadata: ModelMetadata = {
|
||||
provider: 'ollama',
|
||||
modelId: modelName,
|
||||
capabilities: {
|
||||
supportsTools: true,
|
||||
supportsStreaming: true
|
||||
}
|
||||
};
|
||||
|
||||
// Get temperature from options or global setting
|
||||
const temperature = opts.temperature !== undefined
|
||||
? opts.temperature
|
||||
: parseFloat(options.getOption('aiTemperature') || '0.7');
|
||||
|
||||
// Use provided context window or get from model if not specified
|
||||
const modelContextWindow = contextWindow || await getOllamaModelContextWindow(modelName);
|
||||
|
||||
// Update capabilities with context window information
|
||||
providerMetadata.capabilities!.contextWindow = modelContextWindow;
|
||||
|
||||
return {
|
||||
// Connection settings
|
||||
baseUrl,
|
||||
|
||||
// Provider metadata
|
||||
providerMetadata,
|
||||
|
||||
// API parameters
|
||||
model: modelName, // Clean model name without provider prefix
|
||||
stream: opts.stream,
|
||||
options: {
|
||||
temperature: opts.temperature,
|
||||
num_ctx: modelContextWindow,
|
||||
num_predict: opts.maxTokens,
|
||||
response_format: opts.expectsJsonResponse ? { type: "json_object" } : undefined
|
||||
},
|
||||
tools: opts.tools,
|
||||
|
||||
// Internal configuration
|
||||
systemPrompt: opts.systemPrompt,
|
||||
enableTools: opts.enableTools,
|
||||
bypassFormatter: opts.bypassFormatter,
|
||||
preserveSystemPrompt: opts.preserveSystemPrompt,
|
||||
expectsJsonResponse: opts.expectsJsonResponse,
|
||||
toolExecutionStatus: opts.toolExecutionStatus,
|
||||
};
|
||||
} catch (error) {
|
||||
log.error(`Error creating Ollama provider options: ${error}`);
|
||||
throw error;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Get context window size for Ollama model
|
||||
*/
|
||||
async function getOllamaModelContextWindow(modelName: string): Promise<number> {
|
||||
try {
|
||||
const baseUrl = options.getOption('ollamaBaseUrl');
|
||||
|
||||
// Try to get model information from Ollama API
|
||||
const response = await fetch(`${baseUrl}/api/show`, {
|
||||
method: 'POST',
|
||||
headers: { 'Content-Type': 'application/json' },
|
||||
body: JSON.stringify({ name: modelName })
|
||||
});
|
||||
|
||||
if (response.ok) {
|
||||
const data = await response.json();
|
||||
// Get context window from model parameters
|
||||
if (data && data.parameters && data.parameters.num_ctx) {
|
||||
return data.parameters.num_ctx;
|
||||
}
|
||||
}
|
||||
|
||||
// Default context sizes by model family if we couldn't get specific info
|
||||
if (modelName.includes('llama3')) {
|
||||
return 8192;
|
||||
} else if (modelName.includes('llama2')) {
|
||||
return 4096;
|
||||
} else if (modelName.includes('mistral') || modelName.includes('mixtral')) {
|
||||
return 8192;
|
||||
} else if (modelName.includes('gemma')) {
|
||||
return 8192;
|
||||
}
|
||||
|
||||
// Return a reasonable default
|
||||
return 4096;
|
||||
} catch (error) {
|
||||
log.info(`Error getting context window for model ${modelName}: ${error}`);
|
||||
return 4096; // Default fallback
|
||||
}
|
||||
}
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user