Tools/Notes
1
0
Fork 0
mirror of https://github.com/TriliumNext/Notes.git synced 2025-08-31 11:49:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

increase context window size

Browse Source
This commit is contained in:
perf3ct 2025-04-09 01:24:43 +00:00
parent c95b9f798c
commit 208267edb8
No known key found for this signature in database
GPG Key ID: 569C4EEC436F5232
4 changed files with 31 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
src/services/llm/constants/provider_constants.ts
View File

@ -19,37 +19,37 @@ export const PROVIDER_CONSTANTS = {
id: 'claude-3-7-sonnet-20240620',
name: 'Claude 3.7 Sonnet',
description: 'Most intelligent model with hybrid reasoning capabilities',
maxTokens: 4096
maxTokens: 8192
},
{
id: 'claude-3-5-haiku-20240307',
name: 'Claude 3.5 Haiku',
description: 'Improved version of Haiku with better performance',
maxTokens: 4096
maxTokens: 8192
},
{
id: 'claude-3-opus-20240229',
name: 'Claude 3 Opus',
description: 'Most capable model for highly complex tasks',
maxTokens: 4096
maxTokens: 8192
},
{
id: 'claude-3-sonnet-20240229',
name: 'Claude 3 Sonnet',
description: 'Ideal balance of intelligence and speed',
maxTokens: 4096
maxTokens: 8192
},
{
id: 'claude-3-haiku-20240307',
name: 'Claude 3 Haiku',
description: 'Fastest and most compact model',
maxTokens: 4096
maxTokens: 8192
},
{
id: 'claude-2.1',
name: 'Claude 2.1',
description: 'Previous generation model',
maxTokens: 4096
maxTokens: 8192
}
]
},
@ -86,7 +86,7 @@ export const PROVIDER_CONSTANTS = {
id: 'gpt-3.5-turbo',
name: 'GPT-3.5 Turbo',
description: 'Fast and efficient model for most tasks',
maxTokens: 4096
maxTokens: 8192
}
]
},
@ -100,14 +100,14 @@ export const PROVIDER_CONSTANTS = {
OVERLAP: 200
},
MODEL_DIMENSIONS: {
default: 4096,
llama2: 4096,
mixtral: 4096,
'mistral': 4096
default: 8192,
llama2: 8192,
mixtral: 8192,
'mistral': 8192
},
MODEL_CONTEXT_WINDOWS: {
default: 8192,
llama2: 4096,
llama2: 8192,
mixtral: 8192,
'mistral': 8192
}
@ -147,9 +147,9 @@ export const LLM_CONSTANTS = {
// Model-specific embedding dimensions for Ollama models
OLLAMA_MODEL_DIMENSIONS: {
"llama3": 4096,
"llama3.1": 4096,
"mistral": 4096,
"llama3": 8192,
"llama3.1": 8192,
"mistral": 8192,
"nomic": 768,
"mxbai": 1024,
"nomic-embed-text": 768,
@ -167,7 +167,7 @@ export const LLM_CONSTANTS = {
"mxbai": 32768,
"nomic-embed-text": 32768,
"mxbai-embed-large": 32768,
"default": 4096
"default": 8192
},
// Batch size configuration

16
src/services/llm/embeddings/providers/ollama.ts
View File

@ -42,7 +42,7 @@ export class OllamaEmbeddingProvider extends BaseEmbeddingProvider {
// First try the /api/show endpoint which has detailed model information
const url = new URL(`${this.baseUrl}/api/show`);
url.searchParams.append('name', modelName);
const showResponse = await fetch(url, {
method: 'GET',
headers: { "Content-Type": "application/json" },
@ -52,9 +52,9 @@ export class OllamaEmbeddingProvider extends BaseEmbeddingProvider {
if (!showResponse.ok) {
throw new Error(`HTTP error! status: ${showResponse.status}`);
}
const data = await showResponse.json();
if (data && data.parameters) {
const params = data.parameters;
// Extract context length from parameters (different models might use different parameter names)
@ -175,9 +175,9 @@ export class OllamaEmbeddingProvider extends BaseEmbeddingProvider {
if (!testResponse.ok) {
throw new Error(`HTTP error! status: ${testResponse.status}`);
}
const data = await testResponse.json();
if (data && Array.isArray(data.embedding)) {
return data.embedding.length;
} else {
@ -215,7 +215,7 @@ export class OllamaEmbeddingProvider extends BaseEmbeddingProvider {
// Trim text if it might exceed context window (rough character estimate)
// This is a simplistic approach - ideally we'd count tokens properly
const charLimit = (modelInfo.contextWidth || 4096) * 4; // Rough estimate: avg 4 chars per token
const charLimit = (modelInfo.contextWidth || 8192) * 4; // Rough estimate: avg 4 chars per token
const trimmedText = text.length > charLimit ? text.substring(0, charLimit) : text;
const response = await fetch(`${this.baseUrl}/api/embeddings`, {
@ -232,9 +232,9 @@ export class OllamaEmbeddingProvider extends BaseEmbeddingProvider {
if (!response.ok) {
throw new Error(`HTTP error! status: ${response.status}`);
}
const data = await response.json();
if (data && Array.isArray(data.embedding)) {
// Success! Return the embedding
return new Float32Array(data.embedding);

8
src/services/llm/embeddings/providers/voyage.ts
View File

@ -118,14 +118,14 @@ export class VoyageEmbeddingProvider extends BaseEmbeddingProvider {
if (modelName.includes('voyage-2')) {
return {
dimension: dimension || 1024,
contextWidth: 4096,
contextWidth: 8192,
name: modelName,
type: 'float32'
};
} else if (modelName.includes('voyage-lite-02')) {
return {
dimension: dimension || 768,
contextWidth: 4096,
contextWidth: 8192,
name: modelName,
type: 'float32'
};
@ -133,7 +133,7 @@ export class VoyageEmbeddingProvider extends BaseEmbeddingProvider {
// Default for other Voyage models
return {
dimension: dimension || 1024,
contextWidth: 4096,
contextWidth: 8192,
name: modelName,
type: 'float32'
};
@ -170,7 +170,7 @@ export class VoyageEmbeddingProvider extends BaseEmbeddingProvider {
const modelInfo = await this.getModelInfo(modelName);
// Trim text if it might exceed context window (rough character estimate)
const charLimit = (modelInfo.contextWidth || 4096) * 4; // Rough estimate: avg 4 chars per token
const charLimit = (modelInfo.contextWidth || 8192) * 4; // Rough estimate: avg 4 chars per token
const trimmedText = text.length > charLimit ? text.substring(0, charLimit) : text;
const response = await fetch(`${this.baseUrl}/embeddings`, {

6
src/services/llm/interfaces/model_capabilities.ts
View File

@ -17,7 +17,7 @@ export interface ModelCapabilities {
* Default model capabilities for unknown models
*/
export const DEFAULT_MODEL_CAPABILITIES: ModelCapabilities = {
contextWindowTokens: 4096,
contextWindowTokens: 8192,
contextWindowChars: 16000, // ~4 chars per token estimate
maxCompletionTokens: 1024,
hasFunctionCalling: false,
@ -32,7 +32,7 @@ export const DEFAULT_MODEL_CAPABILITIES: ModelCapabilities = {
export const MODEL_CAPABILITIES: Record<string, Partial<ModelCapabilities>> = {
// OpenAI models
'gpt-3.5-turbo': {
contextWindowTokens: 4096,
contextWindowTokens: 8192,
contextWindowChars: 16000,
hasFunctionCalling: true
},
@ -95,7 +95,7 @@ export const MODEL_CAPABILITIES: Record<string, Partial<ModelCapabilities>> = {
contextWindowChars: 32000
},
'llama2': {
contextWindowTokens: 4096,
contextWindowTokens: 8192,
contextWindowChars: 16000
}
};