feat(ai-services): add Vietnamese NLP pipeline for property description analysis

Implement auto-tagging (amenities, location features, condition/legal),
content quality scoring with moderation integration, and FastAPI endpoints
for single and batch text analysis. Uses underthesea for Vietnamese
tokenization/POS when available, with regex fallback.

Co-Authored-By: Paperclip <noreply@paperclip.ing>

libs/ai-services/app/models/nlp.py

@@ -0,0 +1,48 @@
+from pydantic import BaseModel, Field
+
+
+class NLPAnalyzeRequest(BaseModel):
+    text: str = Field(..., min_length=1, description="Vietnamese property description text")
+    include_moderation: bool = Field(
+        True, description="Whether to include moderation quality score"
+    )
+
+
+class PropertyTag(BaseModel):
+    category: str = Field(..., description="Tag category: amenity, location, condition, legal")
+    tag: str = Field(..., description="Normalized tag name")
+    matched_text: str = Field(..., description="Original text that matched")
+    confidence: float = Field(..., ge=0, le=1, description="Match confidence")
+
+
+class QualityScore(BaseModel):
+    overall: float = Field(..., ge=0, le=1, description="Overall content quality 0-1")
+    completeness: float = Field(
+        ..., ge=0, le=1, description="How complete the listing info is"
+    )
+    readability: float = Field(..., ge=0, le=1, description="Text readability score")
+    information_density: float = Field(
+        ..., ge=0, le=1, description="Ratio of useful info to total text"
+    )
+    moderation_score: float | None = Field(
+        None, ge=0, le=1, description="Moderation risk score (0=safe, 1=risky)"
+    )
+
+
+class NLPAnalyzeResponse(BaseModel):
+    tags: list[PropertyTag] = Field(default_factory=list)
+    quality: QualityScore
+    tokens: list[str] = Field(default_factory=list, description="Word-segmented tokens")
+    sentences: list[str] = Field(default_factory=list, description="Sentence-split results")
+    keyword_phrases: list[str] = Field(
+        default_factory=list, description="Key noun phrases extracted"
+    )
+
+
+class BatchAnalyzeRequest(BaseModel):
+    texts: list[str] = Field(..., min_length=1, max_length=50, description="Batch of texts")
+    include_moderation: bool = Field(True)
+
+
+class BatchAnalyzeResponse(BaseModel):
+    results: list[NLPAnalyzeResponse]