baraba/Baradb
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
255 Commits 1 Branch 2 Tags
e28c1f48968ecad092471f04c6ac4c6d89ef0a7a
Commit Graph
3 Commits
Author SHA1 Message Date
dimgigov 1e38e29f25 fix(security): SQL injection in Python/JS clients + bare except + session leak
CI / test (push) Has been cancelled
Details
CI / verify (push) Has been cancelled
Details
Clients CI / build-server (push) Has been cancelled
Details
Clients CI / test-python (push) Has been cancelled
Details
Clients CI / test-javascript (push) Has been cancelled
Details
Clients CI / test-nim (push) Has been cancelled
Details
Clients CI / test-rust (push) Has been cancelled
Details 
- Fix SQL injection vulnerabilities in chat_history.py, langchain_store.py,
  rag_pipeline.py, baradb_langchain.js by switching to parameterized queries
- Replace dangerous bare except: with except CatchableError:/ValueError:
  in llm.nim, embed.nim, cypher.nim, mcp/server.nim, executor.nim
- Fix session variable leak in MCP handleVectorSearch/handleSchemaInspect
- Build: 0 errors, all tests pass
 2026-05-17 16:58:05 +03:00
dimgigov e23b1d61d2 feat: Session 12 AI Agents & NL->SQL 
- src/barabadb/ai/llm.nim: LLM client for NL->SQL generation
  - Supports OpenAI-compatible and Ollama APIs
  - Configurable via BARADB_LLM_ENDPOINT, BARADB_LLM_MODEL, BARADB_LLM_API_KEY
  - extractSQL() parses SQL from LLM responses (handles markdown blocks)
  - Temperature 0.1 for deterministic SQL generation

- nl_to_sql() SQL function: natural language -> SQL
  - Schema-aware prompt with table column definitions + indexes + RLS
  - Query validation layer: wraps generated SQL in LIMIT 0 subquery
  - Self-correction loop: on error, feeds error back to LLM for fix
  - Tenant-aware: respects current session variables

- schema_prompt() SQL function: generates DDL + sample data + indexes
  - Returns full CREATE TABLE statement with column types and constraints
  - Includes up to 5 sample rows for context
  - Lists indexes, RLS policies, foreign keys
  - Perfect for feeding into LLM context

- All 340+ existing tests pass
 2026-05-17 15:38:14 +03:00
dimgigov 13bc17cfa8 feat: 10.1.4 Chunking + embedding pipeline 
- New modules: src/barabadb/ai/chunk.nim (text chunking) and embed.nim (HTTP embedding client)
- chunk() SQL function: returns JSON array of chunks with configurable size/overlap
- embed_text() SQL function: calls external embedding API (OpenAI/Ollama compatible)
- Auto-embedding on INSERT: when VECTOR column is null but TEXT column is populated,
  generates embeddings via configured embedder
- Configurable via env vars: BARADB_EMBED_ENDPOINT, BARADB_EMBED_MODEL, BARADB_EMBED_API_KEY
- All 340+ existing tests pass
 2026-05-17 15:26:24 +03:00