Files
myAi/Apis/cv-matcher-api-models/Responses/JobMatchResponse.cs
T
claude b78ede23cf feat(job-search): extract keywords from LLM match call instead of heuristics
Piggybacks keyword extraction onto the existing CV-to-job LLM call —
no extra API calls. The system prompt now instructs the model to return
8-12 English job-search terms (job titles, technologies, skills, domains)
in a new `keywords` field alongside the existing score/summary fields.

Keywords flow: LLM JSON → JobMatchResponse.Keywords → CreateJobSearchTokenRequest →
JobSearchTokenEntity.Keywords (stored comma-separated) → JobSearchSessionEntity.Keywords
(copied at session-creation time, no RAG call needed).

Changes:
- Add Keywords to JobMatchResponse, CreateJobSearchTokenRequest, JobSearchTokenEntity
- IJobTokenService.CreateTokenAsync now accepts IReadOnlyList<string> keywords
- JobTokenService: store keywords on token; TriggerStartAsync reads token.Keywords
  instead of fetching CV text from RAG — removes IRagApiClient dependency
- Remove heuristic ExtractKeywords method
- Migration AddKeywordsToJobSearchTokens: adds Keywords column to cvSearch.JobSearchTokens
- Migration UpdateCvMatchSystemPromptKeywords: updates ai.cv-match.system-prompt seed
  to include keywords in the JSON shape

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-29 12:44:13 +03:00

17 lines
621 B
C#

namespace CvMatcher.Models.Responses
{
public sealed class JobMatchResponse
{
public int Score { get; set; }
public string Summary { get; set; } = string.Empty;
public List<string> Strengths { get; set; } = [];
public List<string> Gaps { get; set; } = [];
public List<string> Recommendations { get; set; } = [];
public List<string> Evidence { get; set; } = [];
public List<string> Keywords { get; set; } = [];
public bool Cached { get; set; }
public string? JobDocumentId { get; set; }
public string? JobUrl { get; set; }
}
}