Phase 3: Memory & Growth - Multi-file fusion, Entity alignment with embedding, Document import, Knowledge base panel
This commit is contained in:
OpenClaw Bot
389
backend/main.py
389
backend/main.py
@@ -1,7 +1,7 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
InsightFlow Backend - Phase 3 (Production Ready)
|
||||
Knowledge Growth: Multi-file fusion + Entity Alignment
|
||||
InsightFlow Backend - Phase 3 (Memory & Growth)
|
||||
Knowledge Growth: Multi-file fusion + Entity Alignment + Document Import
|
||||
ASR: 阿里云听悟 + OSS
|
||||
"""
|
||||
|
||||
@@ -9,6 +9,7 @@ import os
|
||||
import json
|
||||
import httpx
|
||||
import uuid
|
||||
import re
|
||||
from fastapi import FastAPI, File, UploadFile, HTTPException, Form
|
||||
from fastapi.middleware.cors import CORSMiddleware
|
||||
from fastapi.staticfiles import StaticFiles
|
||||
@@ -35,6 +36,18 @@ try:
|
||||
except ImportError:
|
||||
DB_AVAILABLE = False
|
||||
|
||||
try:
|
||||
from document_processor import DocumentProcessor
|
||||
DOC_PROCESSOR_AVAILABLE = True
|
||||
except ImportError:
|
||||
DOC_PROCESSOR_AVAILABLE = False
|
||||
|
||||
try:
|
||||
from entity_aligner import EntityAligner
|
||||
ALIGNER_AVAILABLE = True
|
||||
except ImportError:
|
||||
ALIGNER_AVAILABLE = False
|
||||
|
||||
app = FastAPI(title="InsightFlow", version="0.3.0")
|
||||
|
||||
app.add_middleware(
|
||||
@@ -90,9 +103,29 @@ class EntityMergeRequest(BaseModel):
|
||||
source_entity_id: str
|
||||
target_entity_id: str
|
||||
|
||||
class GlossaryTermCreate(BaseModel):
|
||||
term: str
|
||||
pronunciation: Optional[str] = ""
|
||||
|
||||
# API Keys
|
||||
KIMI_API_KEY = os.getenv("KIMI_API_KEY", "")
|
||||
KIMI_BASE_URL = "https://api.kimi.com/coding"
|
||||
KIMI_BASE_URL = os.getenv("KIMI_BASE_URL", "https://api.kimi.com/coding")
|
||||
|
||||
# Phase 3: Entity Aligner singleton
|
||||
_aligner = None
|
||||
def get_aligner():
|
||||
global _aligner
|
||||
if _aligner is None and ALIGNER_AVAILABLE:
|
||||
_aligner = EntityAligner()
|
||||
return _aligner
|
||||
|
||||
# Phase 3: Document Processor singleton
|
||||
_doc_processor = None
|
||||
def get_doc_processor():
|
||||
global _doc_processor
|
||||
if _doc_processor is None and DOC_PROCESSOR_AVAILABLE:
|
||||
_doc_processor = DocumentProcessor()
|
||||
return _doc_processor
|
||||
|
||||
# Phase 2: Entity Edit API
|
||||
@app.put("/api/v1/entities/{entity_id}")
|
||||
@@ -406,12 +439,21 @@ def extract_entities_with_llm(text: str) -> tuple[List[dict], List[dict]]:
|
||||
|
||||
return [], []
|
||||
|
||||
def align_entity(project_id: str, name: str, db) -> Optional[Entity]:
|
||||
"""实体对齐"""
|
||||
def align_entity(project_id: str, name: str, db, definition: str = "") -> Optional[Entity]:
|
||||
"""实体对齐 - Phase 3: 使用 embedding 对齐"""
|
||||
# 1. 首先尝试精确匹配
|
||||
existing = db.get_entity_by_name(project_id, name)
|
||||
if existing:
|
||||
return existing
|
||||
|
||||
# 2. 使用 embedding 对齐（如果可用）
|
||||
aligner = get_aligner()
|
||||
if aligner:
|
||||
similar = aligner.find_similar_entity(project_id, name, definition)
|
||||
if similar:
|
||||
return similar
|
||||
|
||||
# 3. 回退到简单相似度匹配
|
||||
similar = db.find_similar_entities(project_id, name)
|
||||
if similar:
|
||||
return similar[0]
|
||||
@@ -443,7 +485,7 @@ async def list_projects():
|
||||
|
||||
@app.post("/api/v1/projects/{project_id}/upload", response_model=AnalysisResult)
|
||||
async def upload_audio(project_id: str, file: UploadFile = File(...)):
|
||||
"""上传音频到指定项目"""
|
||||
"""上传音频到指定项目 - Phase 3: 支持多文件融合"""
|
||||
if not DB_AVAILABLE:
|
||||
raise HTTPException(status_code=500, detail="Database not available")
|
||||
|
||||
@@ -471,12 +513,12 @@ async def upload_audio(project_id: str, file: UploadFile = File(...)):
|
||||
full_text=tw_result["full_text"]
|
||||
)
|
||||
|
||||
# 实体对齐并保存
|
||||
# 实体对齐并保存 - Phase 3: 使用增强对齐
|
||||
aligned_entities = []
|
||||
entity_name_to_id = {} # 用于关系映射
|
||||
|
||||
for raw_ent in raw_entities:
|
||||
existing = align_entity(project_id, raw_ent["name"], db)
|
||||
existing = align_entity(project_id, raw_ent["name"], db, raw_ent.get("definition", ""))
|
||||
|
||||
if existing:
|
||||
ent_model = EntityModel(
|
||||
@@ -551,6 +593,302 @@ async def upload_audio(project_id: str, file: UploadFile = File(...)):
|
||||
created_at=datetime.now().isoformat()
|
||||
)
|
||||
|
||||
# Phase 3: Document Upload API
|
||||
@app.post("/api/v1/projects/{project_id}/upload-document")
|
||||
async def upload_document(project_id: str, file: UploadFile = File(...)):
|
||||
"""上传 PDF/DOCX 文档到指定项目"""
|
||||
if not DB_AVAILABLE:
|
||||
raise HTTPException(status_code=500, detail="Database not available")
|
||||
|
||||
if not DOC_PROCESSOR_AVAILABLE:
|
||||
raise HTTPException(status_code=500, detail="Document processor not available")
|
||||
|
||||
db = get_db_manager()
|
||||
project = db.get_project(project_id)
|
||||
if not project:
|
||||
raise HTTPException(status_code=404, detail="Project not found")
|
||||
|
||||
content = await file.read()
|
||||
|
||||
# 处理文档
|
||||
processor = get_doc_processor()
|
||||
try:
|
||||
result = processor.process(content, file.filename)
|
||||
except Exception as e:
|
||||
raise HTTPException(status_code=400, detail=f"Document processing failed: {str(e)}")
|
||||
|
||||
# 保存文档转录记录
|
||||
transcript_id = str(uuid.uuid4())[:8]
|
||||
db.save_transcript(
|
||||
transcript_id=transcript_id,
|
||||
project_id=project_id,
|
||||
filename=file.filename,
|
||||
full_text=result["text"],
|
||||
transcript_type="document"
|
||||
)
|
||||
|
||||
# 提取实体和关系
|
||||
raw_entities, raw_relations = extract_entities_with_llm(result["text"])
|
||||
|
||||
# 实体对齐并保存
|
||||
aligned_entities = []
|
||||
entity_name_to_id = {}
|
||||
|
||||
for raw_ent in raw_entities:
|
||||
existing = align_entity(project_id, raw_ent["name"], db, raw_ent.get("definition", ""))
|
||||
|
||||
if existing:
|
||||
entity_name_to_id[raw_ent["name"]] = existing.id
|
||||
aligned_entities.append(EntityModel(
|
||||
id=existing.id,
|
||||
name=existing.name,
|
||||
type=existing.type,
|
||||
definition=existing.definition,
|
||||
aliases=existing.aliases
|
||||
))
|
||||
else:
|
||||
new_ent = db.create_entity(Entity(
|
||||
id=str(uuid.uuid4())[:8],
|
||||
project_id=project_id,
|
||||
name=raw_ent["name"],
|
||||
type=raw_ent.get("type", "OTHER"),
|
||||
definition=raw_ent.get("definition", "")
|
||||
))
|
||||
entity_name_to_id[raw_ent["name"]] = new_ent.id
|
||||
aligned_entities.append(EntityModel(
|
||||
id=new_ent.id,
|
||||
name=new_ent.name,
|
||||
type=new_ent.type,
|
||||
definition=new_ent.definition
|
||||
))
|
||||
|
||||
# 保存实体提及位置
|
||||
full_text = result["text"]
|
||||
name = raw_ent["name"]
|
||||
start_pos = 0
|
||||
while True:
|
||||
pos = full_text.find(name, start_pos)
|
||||
if pos == -1:
|
||||
break
|
||||
mention = EntityMention(
|
||||
id=str(uuid.uuid4())[:8],
|
||||
entity_id=entity_name_to_id[name],
|
||||
transcript_id=transcript_id,
|
||||
start_pos=pos,
|
||||
end_pos=pos + len(name),
|
||||
text_snippet=full_text[max(0, pos-20):min(len(full_text), pos+len(name)+20)],
|
||||
confidence=1.0
|
||||
)
|
||||
db.add_mention(mention)
|
||||
start_pos = pos + 1
|
||||
|
||||
# 保存关系
|
||||
for rel in raw_relations:
|
||||
source_id = entity_name_to_id.get(rel.get("source", ""))
|
||||
target_id = entity_name_to_id.get(rel.get("target", ""))
|
||||
if source_id and target_id:
|
||||
db.create_relation(
|
||||
project_id=project_id,
|
||||
source_entity_id=source_id,
|
||||
target_entity_id=target_id,
|
||||
relation_type=rel.get("type", "related"),
|
||||
evidence=result["text"][:200],
|
||||
transcript_id=transcript_id
|
||||
)
|
||||
|
||||
return {
|
||||
"transcript_id": transcript_id,
|
||||
"project_id": project_id,
|
||||
"filename": file.filename,
|
||||
"text_length": len(result["text"]),
|
||||
"entities": [e.dict() for e in aligned_entities],
|
||||
"created_at": datetime.now().isoformat()
|
||||
}
|
||||
|
||||
# Phase 3: Knowledge Base API
|
||||
@app.get("/api/v1/projects/{project_id}/knowledge-base")
|
||||
async def get_knowledge_base(project_id: str):
|
||||
"""获取项目知识库 - 包含所有实体、关系、术语表"""
|
||||
if not DB_AVAILABLE:
|
||||
raise HTTPException(status_code=500, detail="Database not available")
|
||||
|
||||
db = get_db_manager()
|
||||
project = db.get_project(project_id)
|
||||
if not project:
|
||||
raise HTTPException(status_code=404, detail="Project not found")
|
||||
|
||||
# 获取所有实体
|
||||
entities = db.list_project_entities(project_id)
|
||||
|
||||
# 获取所有关系
|
||||
relations = db.list_project_relations(project_id)
|
||||
|
||||
# 获取所有转录
|
||||
transcripts = db.list_project_transcripts(project_id)
|
||||
|
||||
# 获取术语表
|
||||
glossary = db.list_glossary(project_id)
|
||||
|
||||
# 构建实体统计
|
||||
entity_stats = {}
|
||||
for ent in entities:
|
||||
mentions = db.get_entity_mentions(ent.id)
|
||||
entity_stats[ent.id] = {
|
||||
"mention_count": len(mentions),
|
||||
"transcript_ids": list(set([m.transcript_id for m in mentions]))
|
||||
}
|
||||
|
||||
# 构建实体名称映射
|
||||
entity_map = {e.id: e.name for e in entities}
|
||||
|
||||
return {
|
||||
"project": {
|
||||
"id": project.id,
|
||||
"name": project.name,
|
||||
"description": project.description
|
||||
},
|
||||
"stats": {
|
||||
"entity_count": len(entities),
|
||||
"relation_count": len(relations),
|
||||
"transcript_count": len(transcripts),
|
||||
"glossary_count": len(glossary)
|
||||
},
|
||||
"entities": [
|
||||
{
|
||||
"id": e.id,
|
||||
"name": e.name,
|
||||
"type": e.type,
|
||||
"definition": e.definition,
|
||||
"aliases": e.aliases,
|
||||
"mention_count": entity_stats.get(e.id, {}).get("mention_count", 0),
|
||||
"appears_in": entity_stats.get(e.id, {}).get("transcript_ids", [])
|
||||
}
|
||||
for e in entities
|
||||
],
|
||||
"relations": [
|
||||
{
|
||||
"id": r["id"],
|
||||
"source_id": r["source_entity_id"],
|
||||
"source_name": entity_map.get(r["source_entity_id"], "Unknown"),
|
||||
"target_id": r["target_entity_id"],
|
||||
"target_name": entity_map.get(r["target_entity_id"], "Unknown"),
|
||||
"type": r["relation_type"],
|
||||
"evidence": r["evidence"]
|
||||
}
|
||||
for r in relations
|
||||
],
|
||||
"glossary": [
|
||||
{
|
||||
"id": g["id"],
|
||||
"term": g["term"],
|
||||
"pronunciation": g["pronunciation"],
|
||||
"frequency": g["frequency"]
|
||||
}
|
||||
for g in glossary
|
||||
],
|
||||
"transcripts": [
|
||||
{
|
||||
"id": t["id"],
|
||||
"filename": t["filename"],
|
||||
"type": t.get("type", "audio"),
|
||||
"created_at": t["created_at"]
|
||||
}
|
||||
for t in transcripts
|
||||
]
|
||||
}
|
||||
|
||||
# Phase 3: Glossary API
|
||||
@app.post("/api/v1/projects/{project_id}/glossary")
|
||||
async def add_glossary_term(project_id: str, term: GlossaryTermCreate):
|
||||
"""添加术语到项目术语表"""
|
||||
if not DB_AVAILABLE:
|
||||
raise HTTPException(status_code=500, detail="Database not available")
|
||||
|
||||
db = get_db_manager()
|
||||
project = db.get_project(project_id)
|
||||
if not project:
|
||||
raise HTTPException(status_code=404, detail="Project not found")
|
||||
|
||||
term_id = db.add_glossary_term(
|
||||
project_id=project_id,
|
||||
term=term.term,
|
||||
pronunciation=term.pronunciation
|
||||
)
|
||||
|
||||
return {
|
||||
"id": term_id,
|
||||
"term": term.term,
|
||||
"pronunciation": term.pronunciation,
|
||||
"success": True
|
||||
}
|
||||
|
||||
@app.get("/api/v1/projects/{project_id}/glossary")
|
||||
async def get_glossary(project_id: str):
|
||||
"""获取项目术语表"""
|
||||
if not DB_AVAILABLE:
|
||||
raise HTTPException(status_code=500, detail="Database not available")
|
||||
|
||||
db = get_db_manager()
|
||||
glossary = db.list_glossary(project_id)
|
||||
return glossary
|
||||
|
||||
@app.delete("/api/v1/glossary/{term_id}")
|
||||
async def delete_glossary_term(term_id: str):
|
||||
"""删除术语"""
|
||||
if not DB_AVAILABLE:
|
||||
raise HTTPException(status_code=500, detail="Database not available")
|
||||
|
||||
db = get_db_manager()
|
||||
db.delete_glossary_term(term_id)
|
||||
return {"success": True}
|
||||
|
||||
# Phase 3: Entity Alignment API
|
||||
@app.post("/api/v1/projects/{project_id}/align-entities")
|
||||
async def align_project_entities(project_id: str, threshold: float = 0.85):
|
||||
"""运行实体对齐算法，合并相似实体"""
|
||||
if not DB_AVAILABLE:
|
||||
raise HTTPException(status_code=500, detail="Database not available")
|
||||
|
||||
aligner = get_aligner()
|
||||
if not aligner:
|
||||
raise HTTPException(status_code=500, detail="Entity aligner not available")
|
||||
|
||||
db = get_db_manager()
|
||||
entities = db.list_project_entities(project_id)
|
||||
|
||||
merged_count = 0
|
||||
merged_pairs = []
|
||||
|
||||
# 使用 embedding 对齐
|
||||
for i, entity in enumerate(entities):
|
||||
# 跳过已合并的实体
|
||||
existing = db.get_entity(entity.id)
|
||||
if not existing:
|
||||
continue
|
||||
|
||||
similar = aligner.find_similar_entity(
|
||||
project_id,
|
||||
entity.name,
|
||||
entity.definition,
|
||||
exclude_id=entity.id,
|
||||
threshold=threshold
|
||||
)
|
||||
|
||||
if similar:
|
||||
# 合并实体
|
||||
db.merge_entities(similar.id, entity.id)
|
||||
merged_count += 1
|
||||
merged_pairs.append({
|
||||
"source": entity.name,
|
||||
"target": similar.name
|
||||
})
|
||||
|
||||
return {
|
||||
"success": True,
|
||||
"merged_count": merged_count,
|
||||
"merged_pairs": merged_pairs
|
||||
}
|
||||
|
||||
@app.get("/api/v1/projects/{project_id}/entities")
|
||||
async def get_project_entities(project_id: str):
|
||||
"""获取项目的全局实体列表"""
|
||||
@@ -559,7 +897,7 @@ async def get_project_entities(project_id: str):
|
||||
|
||||
db = get_db_manager()
|
||||
entities = db.list_project_entities(project_id)
|
||||
return [{"id": e.id, "name": e.name, "type": e.type, "definition": e.definition} for e in entities]
|
||||
return [{"id": e.id, "name": e.name, "type": e.type, "definition": e.definition, "aliases": e.aliases} for e in entities]
|
||||
|
||||
|
||||
@app.get("/api/v1/projects/{project_id}/relations")
|
||||
@@ -597,6 +935,7 @@ async def get_project_transcripts(project_id: str):
|
||||
return [{
|
||||
"id": t["id"],
|
||||
"filename": t["filename"],
|
||||
"type": t.get("type", "audio"),
|
||||
"created_at": t["created_at"],
|
||||
"preview": t["full_text"][:100] + "..." if len(t["full_text"]) > 100 else t["full_text"]
|
||||
} for t in transcripts]
|
||||
@@ -619,42 +958,18 @@ async def get_entity_mentions(entity_id: str):
|
||||
"confidence": m.confidence
|
||||
} for m in mentions]
|
||||
|
||||
@app.post("/api/v1/entities/{entity_id}/merge")
|
||||
async def merge_entities_endpoint(entity_id: str, merge_req: EntityMergeRequest):
|
||||
"""合并两个实体"""
|
||||
if not DB_AVAILABLE:
|
||||
raise HTTPException(status_code=500, detail="Database not available")
|
||||
|
||||
db = get_db_manager()
|
||||
|
||||
# 验证两个实体都存在
|
||||
source = db.get_entity(merge_req.source_entity_id)
|
||||
target = db.get_entity(merge_req.target_entity_id)
|
||||
|
||||
if not source or not target:
|
||||
raise HTTPException(status_code=404, detail="Entity not found")
|
||||
|
||||
result = db.merge_entities(merge_req.target_entity_id, merge_req.source_entity_id)
|
||||
return {
|
||||
"success": True,
|
||||
"merged_entity": {
|
||||
"id": result.id,
|
||||
"name": result.name,
|
||||
"type": result.type,
|
||||
"definition": result.definition,
|
||||
"aliases": result.aliases
|
||||
}
|
||||
}
|
||||
|
||||
# Health check
|
||||
@app.get("/health")
|
||||
async def health_check():
|
||||
return {
|
||||
"status": "ok",
|
||||
"version": "0.3.0",
|
||||
"phase": "Phase 3 - Memory & Growth",
|
||||
"oss_available": OSS_AVAILABLE,
|
||||
"tingwu_available": TINGWU_AVAILABLE,
|
||||
"db_available": DB_AVAILABLE
|
||||
"db_available": DB_AVAILABLE,
|
||||
"doc_processor_available": DOC_PROCESSOR_AVAILABLE,
|
||||
"aligner_available": ALIGNER_AVAILABLE
|
||||
}
|
||||
|
||||
# Serve frontend
|
||||
|
||||
Reference in New Issue
Block a user