pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 20:42:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

refine code (#595)

Browse Source 
### What problem does this PR solve?

### Type of change

- [x] Refactoring
This commit is contained in:
KevinHuSh
2024-04-28 19:13:33 +08:00
committed by GitHub
parent aee8b48d2f
commit 8c07992b6c
24 changed files with 538 additions and 116 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
api/apps/chunk_app.py
View File

@ -20,7 +20,7 @@ from flask_login import login_required, current_user
from elasticsearch_dsl import Q
from rag.app.qa import rmPrefix, beAdoc
from rag.nlp import search, huqie
from rag.nlp import search, rag_tokenizer
from rag.utils.es_conn import ELASTICSEARCH
from rag.utils import rmSpace
from api.db import LLMType, ParserType
@ -125,10 +125,10 @@ def set():
d = {
"id": req["chunk_id"],
"content_with_weight": req["content_with_weight"]}
d["content_ltks"] = huqie.qie(req["content_with_weight"])
d["content_sm_ltks"] = huqie.qieqie(d["content_ltks"])
d["content_ltks"] = rag_tokenizer.tokenize(req["content_with_weight"])
d["content_sm_ltks"] = rag_tokenizer.fine_grained_tokenize(d["content_ltks"])
d["important_kwd"] = req["important_kwd"]
d["important_tks"] = huqie.qie(" ".join(req["important_kwd"]))
d["important_tks"] = rag_tokenizer.tokenize(" ".join(req["important_kwd"]))
if "available_int" in req:
d["available_int"] = req["available_int"]
@ -152,7 +152,7 @@ def set():
retmsg="Q&A must be separated by TAB/ENTER key.")
q, a = rmPrefix(arr[0]), rmPrefix[arr[1]]
d = beAdoc(d, arr[0], arr[1], not any(
[huqie.is_chinese(t) for t in q + a]))
[rag_tokenizer.is_chinese(t) for t in q + a]))
v, c = embd_mdl.encode([doc.name, req["content_with_weight"]])
v = 0.1 * v[0] + 0.9 * v[1] if doc.parser_id != ParserType.QA else v[1]
@ -202,11 +202,11 @@ def create():
md5 = hashlib.md5()
md5.update((req["content_with_weight"] + req["doc_id"]).encode("utf-8"))
chunck_id = md5.hexdigest()
d = {"id": chunck_id, "content_ltks": huqie.qie(req["content_with_weight"]),
d = {"id": chunck_id, "content_ltks": rag_tokenizer.tokenize(req["content_with_weight"]),
"content_with_weight": req["content_with_weight"]}
d["content_sm_ltks"] = huqie.qieqie(d["content_ltks"])
d["content_sm_ltks"] = rag_tokenizer.fine_grained_tokenize(d["content_ltks"])
d["important_kwd"] = req.get("important_kwd", [])
d["important_tks"] = huqie.qie(" ".join(req.get("important_kwd", [])))
d["important_tks"] = rag_tokenizer.tokenize(" ".join(req.get("important_kwd", [])))
d["create_time"] = str(datetime.datetime.now()).replace("T", " ")[:19]
d["create_timestamp_flt"] = datetime.datetime.now().timestamp()

5
api/db/services/task_service.py
View File

@ -78,14 +78,13 @@ class TaskService(CommonService):
docs = cls.model.select(*[Document.id, Document.kb_id, Document.location, File.parent_id]) \
.join(Document, on=(cls.model.doc_id == Document.id)) \
.join(File2Document, on=(File2Document.document_id == Document.id), join_type=JOIN.LEFT_OUTER) \
.join(File, on=(File2Document.file_id == File.id)) \
.join(File, on=(File2Document.file_id == File.id), join_type=JOIN.LEFT_OUTER) \
.where(
Document.status == StatusEnum.VALID.value,
Document.run == TaskStatus.RUNNING.value,
~(Document.type == FileType.VIRTUAL.value),
cls.model.progress >= 0,
cls.model.progress < 1,
cls.model.create_time >= current_timestamp() - 180000
cls.model.create_time >= current_timestamp() - 1000 * 600
)
docs = list(docs.dicts())
if not docs: return []