mirror of
https://github.com/logancyang/obsidian-copilot.git
synced 2026-07-22 07:50:24 +00:00
* Add LexicalEngine and related interfaces for enhanced search functionality - Implement LexicalEngine class utilizing FlexSearch for efficient document indexing and searching. - Create Hit, SearchResult, SearchOptions, and RetrieverEngine interfaces to standardize search operations. - Update package.json and package-lock.json to include new dependencies: flexsearch and p-queue. * Add QueryExpander class and tests for enhanced search query expansion * Add README for Tiered Note-Level Lexical Retrieval with multilingual support and enhanced search pipeline * Implement v3 tiered search with GrepScanner, FullTextEngine, and GraphExpander - Add GrepScanner for fast substring search (L0) - Implement FullTextEngine with ephemeral FlexSearch index (L1) - Add GraphExpander for link-based candidate expansion - Create MemoryManager with platform-aware limits - Implement weighted RRF fusion for result combination - Add SemanticReranker placeholder for future integration - Include comprehensive tests for core components - Simplify code based on review: use TextEncoder, extract methods, streamline RRF - Add clear logging for debugging search pipeline The architecture follows a tiered approach: 1. Grep scan for initial candidates 2. Graph expansion to increase recall 3. Full-text search on expanded set 4. Optional semantic reranking 5. RRF fusion to combine signals 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com> * Enhance tiered retrieval recall with both rewritten queries and the expanded salient terms - Added detailed example of end-to-end query processing in README.md - Updated TieredRetriever to log salient terms during query expansion - Modified FullTextEngine to index link basenames for improved searchability - Adjusted NoteDoc interface to clarify link handling and indexing * Refactor QueryExpander configuration and caching logic for improved clarity and performance; enhance GraphExpander documentation and testing; remove unused fields from NoteDoc interface. * Refactor search retrieval system to wire in TieredLexicalRetriever - Replaced HybridRetriever with TieredLexicalRetriever in ChainManager, VaultQAChainRunner, and main.ts for improved multi-stage retrieval. - Updated README.md to reflect new integration tasks and performance benchmarks. - Introduced TieredLexicalRetriever class to handle on-demand indexing and retrieval. - Enhanced GrepScanner to support inclusion/exclusion patterns for file indexing. - Modified TieredRetriever to combine expanded salient terms and improved logging for final results. - Removed legacy index management in favor of ephemeral indexing with TieredLexicalRetriever. - Updated interfaces and utility functions to support new retrieval logic. * feat: Implement first working TieredLexicalRetriever and refactor search scoring - Added comprehensive tests for TieredLexicalRetriever, covering folder boosting and result combination. - Refactored TieredLexicalRetriever to utilize SearchCore instead of TieredRetriever. - Enhanced FullTextEngine with improved scoring mechanisms, including field weighting and multi-field match bonuses. - Introduced FuzzyMatcher utility for fuzzy matching capabilities, including Levenshtein distance and variant generation. - Updated GrepScanner to prioritize path matching for faster search results. - Implemented normalized scoring in RRF for better ranking consistency. * feat: Update vault search result display to show snippet of content instead of full text * feat: Enhance FullTextEngine to index frontmatter property values and improve search scoring * feat: Improve scoring and logging * feat: Refactor TieredLexicalRetriever to support time-based queries and improve document retrieval logic * Remove TODO.md from tracking and add to .gitignore - TODO.md is now a local-only development session tracker - Prevents accidental commits of work-in-progress task lists - Each developer can maintain their own TODO.md without conflicts * feat: Update dependencies and enhance search functionality - Upgraded axios to version 1.11.0 and electron to version 27.3.11 for improved performance and security. - Refactored QueryExpander to limit queries to the original for strict fallback tests. - Enhanced SearchCore to rank grep hits by evidence quality before fusion, improving retrieval accuracy. - Implemented a new method in SearchCore to rank grep hits based on evidence strength. - Updated TieredLexicalRetriever tests to ensure proper integration with mocked SearchCore. - Improved FuzzyMatcher to include plural/singular normalization for better fuzzy matching. * feat: Add tool call marker encoding/decoding - Introduced new utility functions for encoding and decoding tool call markers to ensure safe embedding in HTML comments. - Updated `updateChatMemory` to handle encoded tool call markers, preserving their integrity during memory storage. - Enhanced logging to decode tool marker results for better readability while maintaining encoded formats for storage. - Added comprehensive tests for tool call marker functionality to ensure correct encoding and decoding behavior. - Refactored related components to integrate the new encoding/decoding logic seamlessly. * feat: Enhance FullTextEngine search to support low-weight terms and improve scoring - Updated FullTextEngine to accept low-weight terms in the search method, allowing for better handling of salient terms. - Implemented downweighting for boolean and numeric tokens in the properties field to reduce noise in search results. - Added a new test case to validate the downweighting behavior for boolean and numeric queries in FullTextEngine. - Improved logging for full-text search results to provide clearer insights into the search process. * feat: Update GraphExpander to enhance search recall with adaptive hop logic - Implemented guardrails in GraphExpander to adjust hop depth based on the number of grep hits: allows +1 hop for small sets (<5) and limits to 1 hop for large sets (≥50). - Updated README.md to reflect new guardrail logic and scoring normalization in search results. - Enhanced test cases to validate the new behavior of skipping co-citations for large result sets and allowing additional hops for smaller sets. * feat: Filter out background tools during streaming to enhance user experience - Added logic to determine and filter out background tools, preventing their names from appearing in the tool call display during streaming. - Implemented a mechanism to include partial tool names only if they meet a specified length threshold, improving clarity in tool call presentations. * feat: Enhance search tools to support time-based queries and display modified time - Updated localSearchTool to ensure a healthy cap on max source chunks for time-based queries, improving recall. - Modified ToolResultFormatter to display actual modified time for time-filtered results, enhancing clarity in search results. - Adjusted output formatting to differentiate between recency and relevance scores based on query type. * feat: Introduce semantic search capabilities with Memory Index support - Added `enableSemanticSearchV3` setting to control the new semantic search feature. - Implemented `MemoryIndexManager` for managing in-memory vector indexing with JSONL persistence. - Enhanced `SearchCore` to utilize semantic retrieval based on the new memory index. - Introduced command to build the semantic memory index, improving search accuracy and retrieval efficiency. - Updated relevant components to integrate semantic search functionality seamlessly. * feat: Add unit tests for MemoryIndexManager to validate functionality - Introduced comprehensive tests for the MemoryIndexManager, covering scenarios such as loading from a file, building a vector store, and indexing vault contents. - Implemented a mock embeddings API to facilitate testing without external dependencies. - Added a utility function to reset the MemoryIndexManager state between tests, ensuring isolation and reliability of test outcomes. * feat: Enhance MemoryIndexManager and related components for improved semantic indexing - Introduced incremental indexing capabilities in MemoryIndexManager to update the JSONL index with new or modified files, enhancing efficiency. - Updated commands to utilize the new incremental indexing method, providing users with real-time updates to the semantic memory index. - Refactored existing indexing logic to support partitioned writes, improving performance and manageability of large datasets. - Enhanced user notifications during indexing processes to provide better feedback on progress and status. - Added a setting to enable semantic search, allowing users to blend semantic similarity into search results seamlessly. * feat: Refine scoring display and enhance search result handling - Updated SourcesModal to display relevance scores with four decimal places for consistency with SearchCore logs. - Enhanced TieredLexicalRetriever to include a new `rerank_score` field for better score management and consistency across search results. - Modified the combineResults method to ensure that title matches retain their original score while incorporating a fused score as `rerank_score`. - Adjusted formatting in SearchTools to ensure both `score` and `rerank_score` reflect the same final score when present. - Updated ToolResultFormatter to display scores with four decimal places, improving clarity in search result presentations. * refactor: Simplify relevant notes retrieval by removing VectorStoreManager dependency - Removed the use of VectorStoreManager in the relevant notes fetching logic, streamlining the process. - Integrated MemoryIndexManager for improved handling of in-memory indexing and note retrieval. - Enhanced error handling to ensure relevant notes are only fetched when the embedding index is available. - Updated related functions to utilize the new memory index approach, improving performance and reliability. * refactor: Remove VectorStoreManager dependency and streamline indexing logic - Eliminated the VectorStoreManager from various components, transitioning to MemoryIndexManager for indexing and retrieval. - Updated project and chain managers to remove unnecessary dependencies, enhancing code clarity and maintainability. - Improved error handling and indexing conditions, particularly for mobile users, ensuring a more robust initialization process. - Refactored settings components to utilize the new memory indexing approach, simplifying the user experience and reducing legacy code. * chore: Mark legacy components as deprecated in preparation for v3 transition - Annotated various files including DebugSearchModal, OramaSearchModal, chunkedStorage, dbOperations, hybridRetriever, and vectorStoreManager as deprecated, indicating they are obsolete in v3. - Updated README.md to reflect the current implementation status and migration notes, emphasizing the removal of Orama-based modules and the transition to MemoryIndexManager for indexing and retrieval. * feat: Implement file tracking and reindexing for modified files - Introduced a new FileTrackingState interface to manage the last active file and its modification time. - Enhanced the CopilotPlugin to opportunistically reindex the previous active file if it was modified while active, contingent on semantic search settings. - Updated MemoryIndexManager to support reindexing of single modified files, improving efficiency in handling changes. - Added unit tests for reindexSingleFileIfModified to ensure correct functionality and performance. * feat: Add graph hops setting for enhanced search result expansion - Introduced a new `graphHops` setting in `CopilotSettings` to control the number of hops for graph expansion during search, with a default value of 1 and a range of 1-3. - Updated the `sanitizeSettings` function to validate the `graphHops` value. - Enhanced the `SearchCore` and `TieredLexicalRetriever` classes to utilize the `graphHops` setting for improved search result relevance. - Updated documentation in `README.md` to reflect the new feature and its security optimizations. * refactor: Improve error handling and indexing logic in MemoryIndexManager and related components - Replaced console error logging with structured logging using logError and logWarn for better error tracking. - Enhanced the refresh and reindexing functions to ensure proper user notifications and error handling. - Updated the logic for managing indexed files, including handling exclusions and ensuring accurate reporting of indexed and unindexed files. - Implemented rate limiting in the MemoryIndexManager to optimize embedding requests and prevent overloading the service. - Refactored chunk processing to improve efficiency and clarity in the indexing workflow. * chore: Update README.md to reflect final session completion and key fixes - Expanded the final session summary with a date and detailed list of completed features and fixes, including UI enhancements and improved logging practices. - Clarified the status of deferred features and provided migration notes for better user guidance. - Ensured documentation aligns with the latest implementation changes and optimizations. * chore: Update memory limits in README.md and MemoryManager.ts for improved performance - Adjusted memory limits for mobile and desktop platforms in both README.md and MemoryManager.ts to reflect increased capacity (20MB mobile, 100MB desktop). - Ensured documentation aligns with the latest implementation changes for better clarity on resource management. * feat: Integrate HyDE document generation into SearchCore for enhanced semantic search - Implemented a new method to generate hypothetical documents (HyDE) to improve semantic search capabilities. - Added timeout handling for HyDE generation to ensure graceful error management. - Updated SearchCore to utilize HyDE documents in search queries, enhancing the relevance of results when semantic search is enabled. - Introduced unit tests to validate the integration and functionality of HyDE generation within the search process. * refactor: Enhance MemoryIndexManager with public methods for better indexing management - Introduced public methods in MemoryIndexManager to streamline access to indexed file paths, check if a file is indexed, retrieve embeddings, and clear the index. - Updated related components to utilize these new methods, improving code clarity and reducing direct access to internal properties. - Enhanced error handling and user notifications during memory index operations. * feat: Implement indexing notification and progress management - Introduced the IndexingNotificationManager to handle UI notifications during indexing operations, allowing users to pause or stop the process. - Added the IndexingProgressTracker to track progress across multiple files, enhancing user feedback during indexing. - Developed the IndexingPipeline to manage the chunking and processing of files into embeddings, improving the overall indexing workflow. - Created the IndexPersistenceManager for managing the persistence of indexed data, ensuring efficient storage and retrieval of index records. - Refactored MemoryIndexManager to utilize the new components, streamlining the indexing process and improving code organization. --------- Co-authored-by: Claude <noreply@anthropic.com>
363 lines
12 KiB
TypeScript
363 lines
12 KiB
TypeScript
import {
|
|
getChainType,
|
|
getCurrentProject,
|
|
getModelKey,
|
|
SetChainOptions,
|
|
setChainType,
|
|
} from "@/aiParams";
|
|
import ChainFactory, { ChainType, Document } from "@/chainFactory";
|
|
import { BUILTIN_CHAT_MODELS, USER_SENDER } from "@/constants";
|
|
import {
|
|
AutonomousAgentChainRunner,
|
|
ChainRunner,
|
|
CopilotPlusChainRunner,
|
|
LLMChainRunner,
|
|
ProjectChainRunner,
|
|
VaultQAChainRunner,
|
|
} from "@/LLMProviders/chainRunner/index";
|
|
import { logError, logInfo } from "@/logger";
|
|
import { TieredLexicalRetriever } from "@/search/v3/TieredLexicalRetriever";
|
|
import { getSettings, getSystemPrompt, subscribeToSettingsChange } from "@/settings/model";
|
|
import { ChatMessage } from "@/types/message";
|
|
import { findCustomModel, isOSeriesModel, isSupportedChain } from "@/utils";
|
|
import {
|
|
ChatPromptTemplate,
|
|
HumanMessagePromptTemplate,
|
|
MessagesPlaceholder,
|
|
} from "@langchain/core/prompts";
|
|
import { RunnableSequence } from "@langchain/core/runnables";
|
|
import { App, Notice } from "obsidian";
|
|
import ChatModelManager from "./chatModelManager";
|
|
import MemoryManager from "./memoryManager";
|
|
import PromptManager from "./promptManager";
|
|
|
|
export default class ChainManager {
|
|
// TODO: These chains are deprecated since we now use direct chat model calls in chain runners
|
|
// Consider removing after verifying no dependencies remain
|
|
private chain: RunnableSequence;
|
|
private retrievalChain: RunnableSequence;
|
|
private retrievedDocuments: Document[] = [];
|
|
|
|
public getRetrievedDocuments(): Document[] {
|
|
return this.retrievedDocuments;
|
|
}
|
|
|
|
public app: App;
|
|
public chatModelManager: ChatModelManager;
|
|
public memoryManager: MemoryManager;
|
|
public promptManager: PromptManager;
|
|
|
|
constructor(app: App) {
|
|
// Instantiate singletons
|
|
this.app = app;
|
|
this.memoryManager = MemoryManager.getInstance();
|
|
this.chatModelManager = ChatModelManager.getInstance();
|
|
this.promptManager = PromptManager.getInstance();
|
|
|
|
// Initialize async operations
|
|
this.initialize();
|
|
|
|
subscribeToSettingsChange(async () => {
|
|
await this.createChainWithNewModel();
|
|
});
|
|
}
|
|
|
|
private async initialize() {
|
|
await this.createChainWithNewModel();
|
|
}
|
|
|
|
// TODO: These methods are deprecated - chain runners now use direct chat model calls
|
|
// Remove after confirming no usage remains
|
|
public getChain(): RunnableSequence {
|
|
return this.chain;
|
|
}
|
|
|
|
public getRetrievalChain(): RunnableSequence {
|
|
return this.retrievalChain;
|
|
}
|
|
|
|
private validateChainType(chainType: ChainType): void {
|
|
if (chainType === undefined || chainType === null) throw new Error("No chain type set");
|
|
}
|
|
|
|
private validateChatModel() {
|
|
if (!this.chatModelManager.validateChatModel(this.chatModelManager.getChatModel())) {
|
|
const errorMsg =
|
|
"Chat model is not initialized properly, check your API key in Copilot setting and make sure you have API access.";
|
|
new Notice(errorMsg);
|
|
throw new Error(errorMsg);
|
|
}
|
|
}
|
|
|
|
// TODO: This method is deprecated - chain validation no longer needed
|
|
// Remove after confirming no dependencies
|
|
private validateChainInitialization() {
|
|
if (!this.chain || !isSupportedChain(this.chain)) {
|
|
console.error("Chain is not initialized properly, re-initializing chain: ", getChainType());
|
|
this.createChainWithNewModel({}, false);
|
|
// this.setChain(getChainType());
|
|
}
|
|
}
|
|
|
|
public storeRetrieverDocuments(documents: Document[]) {
|
|
this.retrievedDocuments = documents;
|
|
}
|
|
|
|
/**
|
|
* Update the active model and create a new chain with the specified model
|
|
* name.
|
|
*/
|
|
async createChainWithNewModel(
|
|
options: SetChainOptions = {},
|
|
neededReInitChatMode: boolean = true
|
|
): Promise<void> {
|
|
const chainType = getChainType();
|
|
const currentProject = getCurrentProject();
|
|
|
|
if (chainType === ChainType.PROJECT_CHAIN && !currentProject) {
|
|
return;
|
|
}
|
|
|
|
let newModelKey =
|
|
chainType === ChainType.PROJECT_CHAIN ? currentProject?.projectModelKey : getModelKey();
|
|
|
|
if (!newModelKey) {
|
|
new Notice("No model key found");
|
|
throw new Error("No model key found");
|
|
}
|
|
|
|
try {
|
|
if (neededReInitChatMode) {
|
|
let customModel = findCustomModel(newModelKey, getSettings().activeModels);
|
|
if (!customModel) {
|
|
// Reset default model if no model is found
|
|
console.error("Resetting default model. No model configuration found for: ", newModelKey);
|
|
customModel = BUILTIN_CHAT_MODELS[0];
|
|
newModelKey = customModel.name + "|" + customModel.provider;
|
|
}
|
|
|
|
// Add validation for project mode
|
|
if (chainType === ChainType.PROJECT_CHAIN && !customModel.projectEnabled) {
|
|
// If the model is not project-enabled, find the first project-enabled model
|
|
const projectEnabledModel = getSettings().activeModels.find(
|
|
(m) => m.enabled && m.projectEnabled
|
|
);
|
|
if (projectEnabledModel) {
|
|
customModel = projectEnabledModel;
|
|
newModelKey = projectEnabledModel.name + "|" + projectEnabledModel.provider;
|
|
new Notice(
|
|
`Model ${customModel.name} is not available in project mode. Switching to ${projectEnabledModel.name}.`
|
|
);
|
|
} else {
|
|
throw new Error(
|
|
"No project-enabled models available. Please enable a model for project mode in settings."
|
|
);
|
|
}
|
|
}
|
|
|
|
const mergedModel = {
|
|
...customModel,
|
|
...currentProject?.modelConfigs,
|
|
};
|
|
await this.chatModelManager.setChatModel(mergedModel);
|
|
}
|
|
|
|
// Must update the chatModel for chain because ChainFactory always
|
|
// retrieves the old chain without the chatModel change if it exists!
|
|
// Create a new chain with the new chatModel
|
|
this.setChain(chainType, options);
|
|
logInfo(`Setting model to ${newModelKey}`);
|
|
} catch (error) {
|
|
logError(`createChainWithNewModel failed: ${error}`);
|
|
logInfo(`modelKey: ${newModelKey}`);
|
|
}
|
|
}
|
|
|
|
// TODO: This method is deprecated - chain runners now handle chain logic directly
|
|
// Remove after confirming no usage remains
|
|
async setChain(chainType: ChainType, options: SetChainOptions = {}): Promise<void> {
|
|
if (!this.chatModelManager.validateChatModel(this.chatModelManager.getChatModel())) {
|
|
console.error("setChain failed: No chat model set.");
|
|
return;
|
|
}
|
|
|
|
this.validateChainType(chainType);
|
|
|
|
// Get chatModel, memory, prompt, and embeddingAPI from respective managers
|
|
const chatModel = this.chatModelManager.getChatModel();
|
|
const memory = this.memoryManager.getMemory();
|
|
const chatPrompt = this.promptManager.getChatPrompt();
|
|
|
|
switch (chainType) {
|
|
case ChainType.LLM_CHAIN: {
|
|
// TODO: LLMChainRunner now handles this directly without chains
|
|
this.chain = ChainFactory.createNewLLMChain({
|
|
llm: chatModel,
|
|
memory: memory,
|
|
prompt: options.prompt || chatPrompt,
|
|
abortController: options.abortController,
|
|
}) as RunnableSequence;
|
|
|
|
setChainType(ChainType.LLM_CHAIN);
|
|
break;
|
|
}
|
|
|
|
case ChainType.VAULT_QA_CHAIN: {
|
|
// TODO: VaultQAChainRunner now handles this directly without chains
|
|
await this.initializeQAChain(options);
|
|
|
|
const retriever = new TieredLexicalRetriever(app, {
|
|
minSimilarityScore: 0.01,
|
|
maxK: getSettings().maxSourceChunks,
|
|
salientTerms: [],
|
|
});
|
|
|
|
// Create new conversational retrieval chain
|
|
this.retrievalChain = ChainFactory.createConversationalRetrievalChain(
|
|
{
|
|
llm: chatModel,
|
|
retriever: retriever,
|
|
systemMessage: getSystemPrompt(),
|
|
},
|
|
this.storeRetrieverDocuments.bind(this),
|
|
getSettings().debug
|
|
);
|
|
|
|
setChainType(ChainType.VAULT_QA_CHAIN);
|
|
if (getSettings().debug) {
|
|
console.log("New Vault QA chain with hybrid retriever created for entire vault");
|
|
console.log("Set chain:", ChainType.VAULT_QA_CHAIN);
|
|
}
|
|
break;
|
|
}
|
|
|
|
case ChainType.COPILOT_PLUS_CHAIN: {
|
|
// For initial load of the plugin
|
|
await this.initializeQAChain(options);
|
|
this.chain = ChainFactory.createNewLLMChain({
|
|
llm: chatModel,
|
|
memory: memory,
|
|
prompt: options.prompt || chatPrompt,
|
|
abortController: options.abortController,
|
|
}) as RunnableSequence;
|
|
|
|
setChainType(ChainType.COPILOT_PLUS_CHAIN);
|
|
break;
|
|
}
|
|
|
|
case ChainType.PROJECT_CHAIN: {
|
|
// For initial load of the plugin
|
|
await this.initializeQAChain(options);
|
|
this.chain = ChainFactory.createNewLLMChain({
|
|
llm: chatModel,
|
|
memory: memory,
|
|
prompt: options.prompt || chatPrompt,
|
|
abortController: options.abortController,
|
|
}) as RunnableSequence;
|
|
setChainType(ChainType.PROJECT_CHAIN);
|
|
break;
|
|
}
|
|
|
|
default:
|
|
this.validateChainType(chainType);
|
|
break;
|
|
}
|
|
}
|
|
|
|
private getChainRunner(): ChainRunner {
|
|
const chainType = getChainType();
|
|
const settings = getSettings();
|
|
|
|
switch (chainType) {
|
|
case ChainType.LLM_CHAIN:
|
|
return new LLMChainRunner(this);
|
|
case ChainType.VAULT_QA_CHAIN:
|
|
return new VaultQAChainRunner(this);
|
|
case ChainType.COPILOT_PLUS_CHAIN:
|
|
// Use AutonomousAgentChainRunner if the setting is enabled
|
|
if (settings.enableAutonomousAgent) {
|
|
return new AutonomousAgentChainRunner(this);
|
|
}
|
|
return new CopilotPlusChainRunner(this);
|
|
case ChainType.PROJECT_CHAIN:
|
|
return new ProjectChainRunner(this);
|
|
default:
|
|
throw new Error(`Unsupported chain type: ${chainType}`);
|
|
}
|
|
}
|
|
|
|
private async initializeQAChain(options: SetChainOptions) {
|
|
// Handle index refresh if needed
|
|
if (options.refreshIndex) {
|
|
// New semantic index auto-refresh path
|
|
const { MemoryIndexManager } = await import("@/search/v3/MemoryIndexManager");
|
|
await MemoryIndexManager.getInstance(this.app).indexVaultIncremental();
|
|
await MemoryIndexManager.getInstance(this.app).ensureLoaded();
|
|
}
|
|
}
|
|
|
|
async runChain(
|
|
userMessage: ChatMessage,
|
|
abortController: AbortController,
|
|
updateCurrentAiMessage: (message: string) => void,
|
|
addMessage: (message: ChatMessage) => void,
|
|
options: {
|
|
debug?: boolean;
|
|
ignoreSystemMessage?: boolean;
|
|
updateLoading?: (loading: boolean) => void;
|
|
} = {}
|
|
) {
|
|
const { debug = false, ignoreSystemMessage = false } = options;
|
|
|
|
if (debug) console.log("==== Step 0: Initial user message ====\n", userMessage);
|
|
|
|
this.validateChatModel();
|
|
this.validateChainInitialization();
|
|
|
|
const chatModel = this.chatModelManager.getChatModel();
|
|
|
|
// Handle ignoreSystemMessage
|
|
if (ignoreSystemMessage || isOSeriesModel(chatModel)) {
|
|
let effectivePrompt = ChatPromptTemplate.fromMessages([
|
|
new MessagesPlaceholder("history"),
|
|
HumanMessagePromptTemplate.fromTemplate("{input}"),
|
|
]);
|
|
|
|
// TODO: hack for o-series models, to be removed when langchainjs supports system prompt
|
|
// https://github.com/langchain-ai/langchain/issues/28895
|
|
if (isOSeriesModel(chatModel)) {
|
|
effectivePrompt = ChatPromptTemplate.fromMessages([
|
|
[USER_SENDER, getSystemPrompt() || ""],
|
|
effectivePrompt,
|
|
]);
|
|
}
|
|
|
|
this.createChainWithNewModel({ prompt: effectivePrompt }, false);
|
|
/*this.setChain(getChainType(), {
|
|
prompt: effectivePrompt,
|
|
});*/
|
|
}
|
|
|
|
const chainRunner = this.getChainRunner();
|
|
return await chainRunner.run(
|
|
userMessage,
|
|
abortController,
|
|
updateCurrentAiMessage,
|
|
addMessage,
|
|
options
|
|
);
|
|
}
|
|
|
|
async updateMemoryWithLoadedMessages(messages: ChatMessage[]) {
|
|
await this.memoryManager.clearChatMemory();
|
|
for (let i = 0; i < messages.length; i += 2) {
|
|
const userMsg = messages[i];
|
|
const aiMsg = messages[i + 1];
|
|
if (userMsg && aiMsg && userMsg.sender === USER_SENDER) {
|
|
await this.memoryManager
|
|
.getMemory()
|
|
.saveContext({ input: userMsg.message }, { output: aiMsg.message });
|
|
}
|
|
}
|
|
}
|
|
}
|