Update app.py
Browse files
app.py
CHANGED
|
@@ -43,8 +43,13 @@ if "vector" not in st.session_state:
|
|
| 43 |
|
| 44 |
# st.session_state.loader = WebBaseLoader("https://paulgraham.com/greatwork.html") # ORIGINAL
|
| 45 |
# st.session_state.docs = st.session_state.loader.load() # ORIGINAL
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
pdf_file_path = "*.pdf" # JB
|
| 47 |
-
st.session_state.loader = PyPDFLoader(file_path=pdf_file_path).load()
|
|
|
|
| 48 |
# chunks = self.text_splitter.split_documents(docs)
|
| 49 |
# chunks = filter_complex_metadata(chunks)
|
| 50 |
|
|
|
|
| 43 |
|
| 44 |
# st.session_state.loader = WebBaseLoader("https://paulgraham.com/greatwork.html") # ORIGINAL
|
| 45 |
# st.session_state.docs = st.session_state.loader.load() # ORIGINAL
|
| 46 |
+
# https://api.python.langchain.com/en/latest/document_loaders/langchain_community.document_loaders.pdf.PyPDFLoader.html
|
| 47 |
+
# https://python.langchain.com/docs/integrations/document_loaders/merge_doc
|
| 48 |
+
# from langchain_community.document_loaders import PyPDFLoader
|
| 49 |
+
# loader_pdf = PyPDFLoader("../MachineLearning-Lecture01.pdf")
|
| 50 |
pdf_file_path = "*.pdf" # JB
|
| 51 |
+
# st.session_state.loader = PyPDFLoader(file_path=pdf_file_path).load() # JB
|
| 52 |
+
st.session_state.loader = PyPDFLoader(*.pdf).load() # JB
|
| 53 |
# chunks = self.text_splitter.split_documents(docs)
|
| 54 |
# chunks = filter_complex_metadata(chunks)
|
| 55 |
|