Update app.py

app.py

@@ -17,21 +17,24 @@ api_hf_embeddings = HuggingFaceInferenceAPIEmbeddings(
 loader = PyPDFLoader("./new_papers/ReACT.pdf")
 documents = loader.load()
 print("-----------")
-print(documents)
+print(documents[0])
 print("-----------")
 
 # Load the document, split it into chunks, embed each chunk, and load it into the vector store.
-text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
+text_splitter = CharacterTextSplitter(chunk_size=100, chunk_overlap=0)
 vdocuments = text_splitter.split_documents(documents)
 
 # Add these lines before creating the Chroma vector store
 #print("Length of embeddings: %s", len(api_hf_embeddings))
 print("Length of documents: %s", len(documents))
 print("Length of vdocuments: %s", len(vdocuments))
-if vdocuments:
-    first_document_embeddings = vdocuments[0].embeddings
+# Add these lines before creating the Chroma vector store
+#logger.debug("Length of vdocuments: %s", len(vdocuments))
+if vdocuments and 'embeddings' in vdocuments[0]:
+    first_document_embeddings = vdocuments[0]['embeddings']
     print("Length of embeddings for the first document: %s", len(first_document_embeddings))
 
+
 # Create Chroma vector store for API embeddings
 api_db = Chroma.from_documents(vdocuments, api_hf_embeddings, collection_name="api-collection")