We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent 28656b5 commit a06040dCopy full SHA for a06040d
ingest.py
@@ -20,9 +20,9 @@ def pageextract(texts):
20
PAGES=[]
21
id=0
22
while id<len(texts):
23
- if (texts[id].metadata['page']-7)==len(PAGES):
+ if (texts[id].metadata['page'])==len(PAGES):
24
temp=''
25
- while id<len(texts) and (texts[id].metadata['page']-7)==len(PAGES) :
+ while id<len(texts) and (texts[id].metadata['page'])==len(PAGES) :
26
temp=temp+texts[id].page_content
27
id=id+1
28
PAGES.append(copy.deepcopy(texts[0]))
@@ -41,4 +41,4 @@ def makedb(chunks,embeddings):
41
def INGESTER():
42
chunks=getdoctext("data")
43
embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
44
- makedb(chunks,embeddings)
+ makedb(chunks,embeddings)
0 commit comments