Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -15,17 +15,16 @@ os.getenv("GOOGLE_API_KEY")
|
|
| 15 |
genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
|
| 16 |
|
| 17 |
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
|
| 22 |
def get_pdf_text(pdf_docs):
|
| 23 |
-
text=""
|
| 24 |
for pdf in pdf_docs:
|
| 25 |
-
pdf_reader= PdfReader(pdf)
|
| 26 |
for page in pdf_reader.pages:
|
| 27 |
-
|
| 28 |
-
|
|
|
|
|
|
|
|
|
|
| 29 |
|
| 30 |
|
| 31 |
|
|
@@ -36,7 +35,10 @@ def get_text_chunks(text):
|
|
| 36 |
|
| 37 |
|
| 38 |
def get_vector_store(text_chunks):
|
| 39 |
-
|
|
|
|
|
|
|
|
|
|
| 40 |
vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
|
| 41 |
vector_store.save_local("faiss_index")
|
| 42 |
|
|
|
|
| 15 |
genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
|
| 16 |
|
| 17 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
def get_pdf_text(pdf_docs):
|
| 19 |
+
text = ""
|
| 20 |
for pdf in pdf_docs:
|
| 21 |
+
pdf_reader = PdfReader(pdf)
|
| 22 |
for page in pdf_reader.pages:
|
| 23 |
+
page_text = page.extract_text()
|
| 24 |
+
if page_text:
|
| 25 |
+
text += page_text
|
| 26 |
+
return text
|
| 27 |
+
|
| 28 |
|
| 29 |
|
| 30 |
|
|
|
|
| 35 |
|
| 36 |
|
| 37 |
def get_vector_store(text_chunks):
|
| 38 |
+
if not text_chunks:
|
| 39 |
+
raise ValueError("No text chunks generated from PDF. Please check the uploaded file.")
|
| 40 |
+
|
| 41 |
+
embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
|
| 42 |
vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
|
| 43 |
vector_store.save_local("faiss_index")
|
| 44 |
|