소스 검색

change chunk.status to chunk.available (#2646)

### What problem does this PR solve?

#1102

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
tags/v0.12.0
JobSmithManipulation 1 년 전
부모
커밋
c103dd2746
No account linked to committer's email address
3개의 변경된 파일21개의 추가작업 그리고 13개의 파일을 삭제
  1. 2
    2
      api/apps/sdk/doc.py
  2. 2
    2
      sdk/python/ragflow/modules/chunk.py
  3. 17
    9
      sdk/python/test/t_document.py

+ 2
- 2
api/apps/sdk/doc.py 파일 보기

@@ -609,8 +609,8 @@ def set(tenant_id):
d["content_sm_ltks"] = rag_tokenizer.fine_grained_tokenize(d["content_ltks"])
d["important_kwd"] = req["important_keywords"]
d["important_tks"] = rag_tokenizer.tokenize(" ".join(req["important_keywords"]))
if "available_int" in req:
d["available_int"] = req["available_int"]
if "available" in req:
d["available_int"] = req["available"]

try:
tenant_id = DocumentService.get_tenant_id(req["document_id"])

+ 2
- 2
sdk/python/ragflow/modules/chunk.py 파일 보기

@@ -11,7 +11,7 @@ class Chunk(Base):
self.knowledgebase_id = None
self.document_name = ""
self.document_id = ""
self.status = "1"
self.available = 1
for k in list(res_dict.keys()):
if k not in self.__dict__:
res_dict.pop(k)
@@ -39,7 +39,7 @@ class Chunk(Base):
"content": self.content,
"important_keywords": self.important_keywords,
"document_id": self.document_id,
"status": self.status,
"available": self.available,
})
res = res.json()
if res.get("retmsg") == "success":

+ 17
- 9
sdk/python/test/t_document.py 파일 보기

@@ -151,14 +151,12 @@ class TestDocument(TestSdk):
name3 = 'westworld.pdf'
path = 'test_data/westworld.pdf'


# Create a document in the dataset using the file path
rag.create_document(ds, name=name3, blob=open(path, "rb").read())

# Retrieve the document by name
doc = rag.get_document(name="westworld.pdf")


# Initiate asynchronous parsing
doc.async_parse()

@@ -231,7 +229,7 @@ class TestDocument(TestSdk):
def test_parse_document_and_chunk_list(self):
rag = RAGFlow(API_KEY, HOST_ADDRESS)
ds = rag.create_dataset(name="God7")
name='story.txt'
name = 'story.txt'
path = 'test_data/story.txt'
# name = "Test Document rag.txt"
# blob = " Sample document content for rag test66. rag wonderful apple os documents apps. Sample document content for rag test66. rag wonderful apple os documents apps.Sample document content for rag test66. rag wonderful apple os documents apps.Sample document content for rag test66. rag wonderful apple os documents apps. Sample document content for rag test66. rag wonderful apple os documents apps. Sample document content for rag test66. rag wonderful apple os documents apps. Sample document content for rag test66. rag wonderful apple os documents apps. Sample document content for rag test66. rag wonderful apple os documents apps. Sample document content for rag test66. rag wonderful apple os documents apps. Sample document content for rag test66. rag wonderful apple os documents apps. Sample document content for rag test66. rag wonderful apple os documents apps. Sample document content for rag test66. rag wonderful apple os documents apps."
@@ -266,11 +264,11 @@ class TestDocument(TestSdk):
assert chunk is not None, "Chunk is None"
assert isinstance(chunk, Chunk), "Chunk was not added to chunk list"
doc = rag.get_document(name='story.txt')
chunk_count_before=doc.chunk_count
chunk_count_before = doc.chunk_count
chunk.delete()
doc = rag.get_document(name='story.txt')
assert doc.chunk_count == chunk_count_before-1, "Chunk was not deleted"
assert doc.chunk_count == chunk_count_before - 1, "Chunk was not deleted"
def test_update_chunk_content(self):
rag = RAGFlow(API_KEY, HOST_ADDRESS)
doc = rag.get_document(name='story.txt')
@@ -278,9 +276,19 @@ class TestDocument(TestSdk):
assert chunk is not None, "Chunk is None"
assert isinstance(chunk, Chunk), "Chunk was not added to chunk list"
chunk.content = "ragflow123"
res=chunk.save()
assert res is True, f"Failed to update chunk, error: {res}"
res = chunk.save()
assert res is True, f"Failed to update chunk content, error: {res}"

def test_update_chunk_available(self):
rag = RAGFlow(API_KEY, HOST_ADDRESS)
doc = rag.get_document(name='story.txt')
chunk = doc.add_chunk(content="ragflow")
assert chunk is not None, "Chunk is None"
assert isinstance(chunk, Chunk), "Chunk was not added to chunk list"
chunk.available = 0
res = chunk.save()
assert res is True, f"Failed to update chunk status, error: {res}"

def test_retrieval_chunks(self):
rag = RAGFlow(API_KEY, HOST_ADDRESS)
ds = rag.create_dataset(name="God8")

Loading…
취소
저장