Bumping versions (#44)

app/requirements.txt

@@ -11,24 +11,24 @@
 ### pip3 install -r app/requirements.txt
 
 ## Top-Level brings in the required dependencies, if adding modules, try to find the minimum required
-bokeh==3.6.0
+bokeh==3.6.1
 evaluate==0.4.3
 faiss-cpu==1.9.0
-giskard==2.15.3
+giskard==2.15.5
 IPython==8.29.0
 langchain-cohere==0.3.1
-langchain-community==0.3.5
+langchain-community==0.3.7
 langchain-huggingface==0.1.2
 langchain-ollama==0.2.0
-langchain-openai==0.2.6
-langgraph==0.2.45
-llama_index==0.11.22
+langchain-openai==0.2.8
+langgraph==0.2.48
+llama_index==0.11.23
 lxml==5.3.0
 matplotlib==3.9.2
 oci>=2.0.0
 oracledb>=2.0.0
 plotly==5.24.1
-streamlit==1.39.0
+streamlit==1.40.1
 umap-learn==0.5.7
 
 ## For Licensing Purposes; ensures no GPU modules are installed

app/src/modules/split.py

@@ -150,7 +150,7 @@ def load_and_split_documents(
     If output_dir, a list of written json files
     """
     split_files = []
-    split_docos = []
+    all_split_docos = []
     for file in src_files:
         name = os.path.basename(file)
         stat = os.stat(file)
@@ -175,13 +175,15 @@ def load_and_split_documents(
         split_doc = split_document(model, chunk_size, chunk_overlap, loaded_doc, extension)
 
         # Add IDs to metadata
+        split_docos = []
         for idx, chunk in enumerate(split_doc, start=1):
             split_doc_with_mdata = process_metadata(idx, chunk)
             split_docos += split_doc_with_mdata
-
+            
         if write_json and output_dir:
             split_files.append(doc_to_json(split_docos, file, output_dir))
-    logger.info("Total Number of Chunks: %i", len(split_docos))
+        all_split_docos += split_docos
+    logger.info("Total Number of Chunks: %i", len(all_split_docos))
 
     return split_docos, split_files