fix

microsoft · Dec 5, 2024 · d666a16 · d666a16
1 parent bf8170e
commit d666a16
Show file tree

Hide file tree

Showing 3 changed files with 11 additions and 15 deletions.
diff --git a/app/util/ui_components.py b/app/util/ui_components.py
@@ -804,7 +804,7 @@ def build_validation_ui(
 
 def check_ai_configuration(enforce_structured_output=False):
     ai_configuration = UIOpenAIConfiguration().get_configuration()
-    if ai_configuration.api_key == "":
+    if ai_configuration.api_key == "" and ai_configuration.api_type == "Open AI":
         st.warning("Please set your OpenAI API key in the Settings page.")
     if ai_configuration.model == "":
         st.warning("Please set your OpenAI model in the Settings page.")

diff --git a/app/workflows/query_text_data/workflow.py b/app/workflows/query_text_data/workflow.py
@@ -64,11 +64,7 @@ async def create(sv: SessionVariables, workflow=None):
     with uploader_tab:
         st.markdown("##### Upload data for processing")
 
-        upload_type = st.radio(
-            "Upload type",
-            options=["Raw files", "Processed data"],
-            key=f"{workflow}_data_source",
-        )
+        upload_type = "Raw files"
         files = None
         file_chunks = None
         if upload_type == "Raw files":
@@ -135,14 +131,14 @@ async def create(sv: SessionVariables, workflow=None):
             message = message.replace("**1** periods", "**1** period")
             st.success(message)
 
-        if qtd.label_to_chunks and upload_type == "Raw files":
-            st.download_button(
-                label="Download chunk data",
-                help="Export chunk data as CSV",
-                data=qtd.get_chunks_as_df().to_csv(),
-                file_name=f"processed_data_{len(qtd.label_to_chunks)}_query_text.csv",
-                mime="text/csv",
-            )
+        # if qtd.label_to_chunks and upload_type == "Raw files":
+        #     st.download_button(
+        #         label="Download chunk data",
+        #         help="Export chunk data as CSV",
+        #         data=qtd.get_chunks_as_df().to_csv(),
+        #         file_name=f"processed_data_{len(qtd.label_to_chunks)}_query_text.csv",
+        #         mime="text/csv",
+        #     )
 
     with graph_tab:
         if qtd.stage.value < QueryTextDataStage.CHUNKS_PROCESSED.value:

diff --git a/intelligence_toolkit/AI/base_embedder.py b/intelligence_toolkit/AI/base_embedder.py
@@ -144,7 +144,7 @@ async def embed_store_many(
                 hash_all_texts = [hash_text(item["text"]) for item in batch_data]
                 existing = self.vector_store.search_by_column(hash_all_texts, "hash")
 
-                if len(existing.get("vector")) > 0 and cache_data:
+                if len(existing.get("vector")) > 0:
                     existing_texts = existing.sort_values("text")
                     for item in existing_texts.to_numpy():
                         all_data.append(