Quellcode durchsuchen

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 vor 1 Jahr
Ursprung
Commit
c103dd2746
Es ist kein Account mit der E-Mail-Adresse des Committers verbunden
3 geänderte Dateien mit 21 neuen und 13 gelöschten Zeilen
  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 Datei anzeigen

@@ -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 Datei anzeigen

@@ -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 Datei anzeigen

@@ -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")

Laden…
Abbrechen
Speichern