From 6307adfba1048c01a9954723f8d16b02fe984470 Mon Sep 17 00:00:00 2001
From: "Timothy J. Baek" <timothyjrbeck@gmail.com>
Date: Mon, 25 Mar 2024 23:47:08 -0700
Subject: [PATCH] feat: better error handling

---
 backend/apps/rag/main.py | 93 +++++++++++++++++++++++-----------------
 backend/constants.py     |  2 +
 2 files changed, 55 insertions(+), 40 deletions(-)

diff --git a/backend/apps/rag/main.py b/backend/apps/rag/main.py
index 1e50ef20b..d87f7bc73 100644
--- a/backend/apps/rag/main.py
+++ b/backend/apps/rag/main.py
@@ -115,6 +115,7 @@ class CollectionNameForm(BaseModel):
 class StoreWebForm(CollectionNameForm):
     url: str
 
+
 @app.get("/")
 async def get_status():
     return {
@@ -297,13 +298,18 @@ def store_web(form_data: StoreWebForm, user=Depends(get_current_user)):
 
 
 def store_data_in_vector_db(data, collection_name, overwrite: bool = False) -> bool:
+
     text_splitter = RecursiveCharacterTextSplitter(
         chunk_size=app.state.CHUNK_SIZE,
         chunk_overlap=app.state.CHUNK_OVERLAP,
         add_start_index=True,
     )
     docs = text_splitter.split_documents(data)
-    return store_docs_in_vector_db(docs, collection_name, overwrite)
+
+    if len(docs) > 0:
+        return store_docs_in_vector_db(docs, collection_name, overwrite), None
+    else:
+        raise ValueError(ERROR_MESSAGES.EMPTY_CONTENT)
 
 
 def store_text_in_vector_db(
@@ -319,6 +325,7 @@ def store_text_in_vector_db(
 
 
 def store_docs_in_vector_db(docs, collection_name, overwrite: bool = False) -> bool:
+
     texts = [doc.page_content for doc in docs]
     metadatas = [doc.metadata for doc in docs]
 
@@ -455,19 +462,21 @@ def store_doc(
 
         loader, known_type = get_loader(file.filename, file.content_type, file_path)
         data = loader.load()
-        result = store_data_in_vector_db(data, collection_name)
 
-        if result:
-            return {
-                "status": True,
-                "collection_name": collection_name,
-                "filename": filename,
-                "known_type": known_type,
-            }
-        else:
+        try:
+            result = store_data_in_vector_db(data, collection_name)
+
+            if result:
+                return {
+                    "status": True,
+                    "collection_name": collection_name,
+                    "filename": filename,
+                    "known_type": known_type,
+                }
+        except Exception as e:
             raise HTTPException(
                 status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
-                detail=ERROR_MESSAGES.DEFAULT(),
+                detail=e,
             )
     except Exception as e:
         log.exception(e)
@@ -532,38 +541,42 @@ def scan_docs_dir(user=Depends(get_admin_user)):
                 )
                 data = loader.load()
 
-                result = store_data_in_vector_db(data, collection_name)
+                try:
+                    result = store_data_in_vector_db(data, collection_name)
 
-                if result:
-                    sanitized_filename = sanitize_filename(filename)
-                    doc = Documents.get_doc_by_name(sanitized_filename)
+                    if result:
+                        sanitized_filename = sanitize_filename(filename)
+                        doc = Documents.get_doc_by_name(sanitized_filename)
 
-                    if doc == None:
-                        doc = Documents.insert_new_doc(
-                            user.id,
-                            DocumentForm(
-                                **{
-                                    "name": sanitized_filename,
-                                    "title": filename,
-                                    "collection_name": collection_name,
-                                    "filename": filename,
-                                    "content": (
-                                        json.dumps(
-                                            {
-                                                "tags": list(
-                                                    map(
-                                                        lambda name: {"name": name},
-                                                        tags,
+                        if doc == None:
+                            doc = Documents.insert_new_doc(
+                                user.id,
+                                DocumentForm(
+                                    **{
+                                        "name": sanitized_filename,
+                                        "title": filename,
+                                        "collection_name": collection_name,
+                                        "filename": filename,
+                                        "content": (
+                                            json.dumps(
+                                                {
+                                                    "tags": list(
+                                                        map(
+                                                            lambda name: {"name": name},
+                                                            tags,
+                                                        )
                                                     )
-                                                )
-                                            }
-                                        )
-                                        if len(tags)
-                                        else "{}"
-                                    ),
-                                }
-                            ),
-                        )
+                                                }
+                                            )
+                                            if len(tags)
+                                            else "{}"
+                                        ),
+                                    }
+                                ),
+                            )
+                except Exception as e:
+                    print(e)
+                    pass
 
         except Exception as e:
             log.exception(e)
diff --git a/backend/constants.py b/backend/constants.py
index 42c5c85eb..8bcdd0789 100644
--- a/backend/constants.py
+++ b/backend/constants.py
@@ -60,3 +60,5 @@ class ERROR_MESSAGES(str, Enum):
     MODEL_NOT_FOUND = lambda name="": f"Model '{name}' was not found"
     OPENAI_NOT_FOUND = lambda name="": f"OpenAI API was not found"
     OLLAMA_NOT_FOUND = "WebUI could not connect to Ollama"
+
+    EMPTY_CONTENT = "The content provided is empty. Please ensure that there is text or data present before proceeding."