bugfixing in embeddings api
This commit is contained in:
overcuriousity
@@ -66,6 +66,11 @@ interface AnalysisContext {
|
||||
auditTrail: AuditEntry[];
|
||||
}
|
||||
|
||||
interface SimilarityResult extends EmbeddingData {
|
||||
similarity: number;
|
||||
}
|
||||
|
||||
|
||||
class ImprovedMicroTaskAIPipeline {
|
||||
private config: AIConfig;
|
||||
private maxSelectedItems: number;
|
||||
@@ -267,39 +272,62 @@ class ImprovedMicroTaskAIPipeline {
|
||||
userQuery,
|
||||
this.embeddingCandidates,
|
||||
this.similarityThreshold
|
||||
);
|
||||
) as SimilarityResult[]; // Type assertion for similarity property
|
||||
|
||||
const toolNames = new Set<string>();
|
||||
const conceptNames = new Set<string>();
|
||||
console.log(`[IMPROVED PIPELINE] Embeddings found ${similarItems.length} similar items`);
|
||||
|
||||
similarItems.forEach(item => {
|
||||
if (item.type === 'tool') toolNames.add(item.name);
|
||||
if (item.type === 'concept') conceptNames.add(item.name);
|
||||
});
|
||||
// FIXED: Create lookup maps for O(1) access while preserving original data
|
||||
const toolsMap = new Map<string, any>(toolsData.tools.map((tool: any) => [tool.name, tool]));
|
||||
const conceptsMap = new Map<string, any>(toolsData.concepts.map((concept: any) => [concept.name, concept]));
|
||||
|
||||
console.log(`[IMPROVED PIPELINE] Embeddings found: ${toolNames.size} tools, ${conceptNames.size} concepts`);
|
||||
// FIXED: Process in similarity order, preserving the ranking
|
||||
const similarTools = similarItems
|
||||
.filter((item): item is SimilarityResult => item.type === 'tool')
|
||||
.map(item => toolsMap.get(item.name))
|
||||
.filter((tool): tool is any => tool !== undefined); // Proper type guard
|
||||
|
||||
if (toolNames.size >= 15) {
|
||||
candidateTools = toolsData.tools.filter((tool: any) => toolNames.has(tool.name));
|
||||
candidateConcepts = toolsData.concepts.filter((concept: any) => conceptNames.has(concept.name));
|
||||
const similarConcepts = similarItems
|
||||
.filter((item): item is SimilarityResult => item.type === 'concept')
|
||||
.map(item => conceptsMap.get(item.name))
|
||||
.filter((concept): concept is any => concept !== undefined); // Proper type guard
|
||||
|
||||
console.log(`[IMPROVED PIPELINE] Similarity-ordered results: ${similarTools.length} tools, ${similarConcepts.length} concepts`);
|
||||
|
||||
// Log the first few tools to verify ordering is preserved
|
||||
if (similarTools.length > 0) {
|
||||
console.log(`[IMPROVED PIPELINE] Top similar tools (in similarity order):`);
|
||||
similarTools.slice(0, 5).forEach((tool, idx) => {
|
||||
const originalSimilarItem = similarItems.find(item => item.name === tool.name);
|
||||
console.log(` ${idx + 1}. ${tool.name} (similarity: ${originalSimilarItem?.similarity?.toFixed(4) || 'N/A'})`);
|
||||
});
|
||||
}
|
||||
|
||||
if (similarTools.length >= 15) {
|
||||
candidateTools = similarTools;
|
||||
candidateConcepts = similarConcepts;
|
||||
selectionMethod = 'embeddings_candidates';
|
||||
|
||||
console.log(`[IMPROVED PIPELINE] Using embeddings candidates: ${candidateTools.length} tools`);
|
||||
console.log(`[IMPROVED PIPELINE] Using embeddings candidates in similarity order: ${candidateTools.length} tools`);
|
||||
} else {
|
||||
console.log(`[IMPROVED PIPELINE] Embeddings insufficient (${toolNames.size} < 15), using full dataset`);
|
||||
console.log(`[IMPROVED PIPELINE] Embeddings insufficient (${similarTools.length} < 15), using full dataset`);
|
||||
candidateTools = toolsData.tools;
|
||||
candidateConcepts = toolsData.concepts;
|
||||
selectionMethod = 'full_dataset';
|
||||
}
|
||||
|
||||
// NEW: Add Audit Entry for Embeddings Search
|
||||
// NEW: Add Audit Entry for Embeddings Search with ordering verification
|
||||
if (this.auditConfig.enabled) {
|
||||
this.addAuditEntry(null, 'retrieval', 'embeddings-search',
|
||||
{ query: userQuery, threshold: this.similarityThreshold, candidates: this.embeddingCandidates },
|
||||
{ candidatesFound: similarItems.length, toolNames: Array.from(toolNames), conceptNames: Array.from(conceptNames) },
|
||||
similarItems.length >= 15 ? 85 : 60, // Confidence based on result quality
|
||||
{
|
||||
candidatesFound: similarItems.length,
|
||||
toolsInOrder: similarTools.slice(0, 3).map((t: any) => t.name),
|
||||
conceptsInOrder: similarConcepts.slice(0, 3).map((c: any) => c.name),
|
||||
orderingPreserved: true
|
||||
},
|
||||
similarTools.length >= 15 ? 85 : 60,
|
||||
embeddingsStart,
|
||||
{ selectionMethod, embeddingsEnabled: true }
|
||||
{ selectionMethod, embeddingsEnabled: true, orderingFixed: true }
|
||||
);
|
||||
}
|
||||
} else {
|
||||
@@ -309,7 +337,7 @@ class ImprovedMicroTaskAIPipeline {
|
||||
selectionMethod = 'full_dataset';
|
||||
}
|
||||
|
||||
console.log(`[IMPROVED PIPELINE] AI will analyze FULL DATA of ${candidateTools.length} candidate tools`);
|
||||
console.log(`[IMPROVED PIPELINE] AI will analyze ${candidateTools.length} candidate tools (ordering preserved: ${selectionMethod === 'embeddings_candidates'})`);
|
||||
const finalSelection = await this.aiSelectionWithFullData(userQuery, candidateTools, candidateConcepts, mode, selectionMethod);
|
||||
|
||||
return {
|
||||
@@ -735,33 +763,59 @@ ${JSON.stringify(conceptsWithFullData.slice(0, 10), null, 2)}`;
|
||||
}
|
||||
|
||||
private async callAI(prompt: string, maxTokens: number = 1000): Promise<string> {
|
||||
const response = await fetch(`${this.config.endpoint}/v1/chat/completions`, {
|
||||
method: 'POST',
|
||||
headers: {
|
||||
'Content-Type': 'application/json',
|
||||
'Authorization': `Bearer ${this.config.apiKey}`
|
||||
},
|
||||
body: JSON.stringify({
|
||||
model: this.config.model,
|
||||
messages: [{ role: 'user', content: prompt }],
|
||||
max_tokens: maxTokens,
|
||||
temperature: 0.3
|
||||
})
|
||||
});
|
||||
|
||||
if (!response.ok) {
|
||||
const errorText = await response.text();
|
||||
throw new Error(`AI API error: ${response.status} - ${errorText}`);
|
||||
}
|
||||
|
||||
const data = await response.json();
|
||||
const content = data.choices?.[0]?.message?.content;
|
||||
const endpoint = this.config.endpoint;
|
||||
const apiKey = this.config.apiKey;
|
||||
const model = this.config.model;
|
||||
|
||||
if (!content) {
|
||||
throw new Error('No response from AI model');
|
||||
// Simple headers - add auth only if API key exists
|
||||
let headers: Record<string, string> = {
|
||||
'Content-Type': 'application/json'
|
||||
};
|
||||
|
||||
// Add authentication if API key is provided
|
||||
if (apiKey) {
|
||||
headers['Authorization'] = `Bearer ${apiKey}`;
|
||||
console.log('[AI PIPELINE] Using API key authentication');
|
||||
} else {
|
||||
console.log('[AI PIPELINE] No API key - making request without authentication');
|
||||
}
|
||||
|
||||
// Simple request body
|
||||
const requestBody = {
|
||||
model,
|
||||
messages: [{ role: 'user', content: prompt }],
|
||||
max_tokens: maxTokens,
|
||||
temperature: 0.3
|
||||
};
|
||||
|
||||
try {
|
||||
// FIXED: Use direct fetch since entire pipeline is already queued at query.ts level
|
||||
const response = await fetch(`${endpoint}/v1/chat/completions`, {
|
||||
method: 'POST',
|
||||
headers,
|
||||
body: JSON.stringify(requestBody)
|
||||
});
|
||||
|
||||
return content;
|
||||
if (!response.ok) {
|
||||
const errorText = await response.text();
|
||||
console.error(`[AI PIPELINE] AI API Error ${response.status}:`, errorText);
|
||||
throw new Error(`AI API error: ${response.status} - ${errorText}`);
|
||||
}
|
||||
|
||||
const data = await response.json();
|
||||
const content = data.choices?.[0]?.message?.content;
|
||||
|
||||
if (!content) {
|
||||
console.error('[AI PIPELINE] No response content:', data);
|
||||
throw new Error('No response from AI model');
|
||||
}
|
||||
|
||||
return content;
|
||||
|
||||
} catch (error) {
|
||||
console.error('[AI PIPELINE] AI service call failed:', error.message);
|
||||
throw error;
|
||||
}
|
||||
}
|
||||
|
||||
async processQuery(userQuery: string, mode: string): Promise<AnalysisResult> {
|
||||
|
||||
Reference in New Issue
Block a user