AI/myAi
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects 1 Releases Wiki Activity
191 Commits 12 Branches 0 Tags
b78ede23cfaa3ab27c34700671b6bcccdd2a9f5d
Commit Graph

4 Commits

Author SHA1 Message Date
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
claude 487924e345 Move RAG repository from rag-api to rag-data — consolidate data layer ownership 
- Move IRagRepository, EfRagRepository, and VectorSerializer from rag-api/Data to rag-data/Repositories
- Add rag-api-models ProjectReference to rag-data.csproj for model type availability
- Delete rag-api/Data folder (no longer needed; all data access is now in rag-data)
- This aligns RAG with email-api and other services: all data code in the data project

Pattern: rag-api (API logic) → rag-data (repository, EF entities, migrations)

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
 2026-05-29 09:38:25 +03:00
claude a1c145e861 feat(cv-matcher): add AiPrompts table; remove MyAiDbContext dependency 
cv-matcher-data:
- Add AiPromptEntity (Key, Language, Value, Description, UpdatedAt)
- Add AiPrompts DbSet to CvMatcherDbContext with composite PK
- Migration AddAiPrompts: create cvMatcher.AiPrompts table and seed
  ai.cv-match.system-prompt (language "*") with the current prompt value

cv-matcher-api:
- Add IAiPromptsRepository / EfAiPromptsRepository under Data/Repositories/
- CvMatcherService: inject IAiPromptsRepository; replace _templates.Render(...)
  with async DB lookup + simple string replacement
- Program.cs: register IAiPromptsRepository (scoped); remove MyAiDbContext,
  ITemplateService/DbTemplateService registrations and MyAiDbContext migration call
- Remove myai-data ProjectReference

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-05-28 08:48:39 +03:00
claude e95ed36647 refactor: restructure solution into -models/-data/-api project taxonomy 
Phases 1-10 of the planned refactoring:

Phase 1: rename shared-models -> common
  - namespace Shared.Models -> Common throughout
  - remove stale AspNetCore.Http.Features 5.0 reference

Phase 2: create shared-data with abstract BaseEntity
  - BaseEntity: required string Id { get; init; } + DateTime CreatedAt { get; init; }

Phase 3: rename myai-models -> myai-data
  - namespace MyAi.Models -> MyAi.Data
  - MigrationsAssembly("myai-data")

Phase 4: rename cv-search-models -> cv-search-data
  - namespace CvSearch.Models -> CvSearch.Data
  - move JobSearchSettings to cv-matcher-api-models
  - JobSearch*Entity now inherits BaseEntity

Phase 5: extract rag-data from rag-api
  - new project: Apis/rag-data with RagDbContext + entities + migrations
  - RagDocumentEntity inherits BaseEntity; cache entities use CacheKey PK
  - fix duplicate AddHttpClient<RagAiClient>/AddScoped registrations in rag-api
  - MigrationsAssembly("rag-data")

Phase 6: extract cv-matcher-data from cv-matcher-api
  - new project: Apis/cv-matcher-data with CvMatcherDbContext + entities + migrations
  - CvMatchResultEntity inherits BaseEntity; CvMatcherChatCacheEntity uses CacheKey PK
  - MigrationsAssembly("cv-matcher-data")

Phase 7: create empty cv-cleanup-job-models and cv-search-job-models

Phase 8: update all 5 Dockerfiles for renamed/new projects

Phase 9: reorganise .sln virtual folders (Apis/Jobs/Models/Data/Helpers)
  - update root CLAUDE.md with new project taxonomy and migration commands
  - update cv-matcher-api/CLAUDE.md and cv-search-job/CLAUDE.md

Phase 10: add Directory.Packages.props for centralised NuGet versions
  - remove Version= from all PackageReference elements in active .csproj files

No database changes. No runtime behaviour changes.
All MigrationId strings in __EFMigrationsHistory are unaffected.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-05-27 15:26:03 +03:00