refactor: Update GenerateEmbeddingsForm to support batch processing

refactor: Update embedding batch size handling in RAG configuration

refactor: add query_doc query caching

refactor: update logging statements in generate_chat_completion function

change embedding_batch_size to Optional

backend/open_webui/apps/retrieval/main.py

@@ -63,7 +63,7 @@ from open_webui.config import (
     RAG_EMBEDDING_MODEL,
     RAG_EMBEDDING_MODEL_AUTO_UPDATE,
     RAG_EMBEDDING_MODEL_TRUST_REMOTE_CODE,
-    RAG_EMBEDDING_OPENAI_BATCH_SIZE,
+    RAG_EMBEDDING_BATCH_SIZE,
     RAG_FILE_MAX_COUNT,
     RAG_FILE_MAX_SIZE,
     RAG_OPENAI_API_BASE_URL,
@@ -134,7 +134,7 @@ app.state.config.CHUNK_OVERLAP = CHUNK_OVERLAP
 
 app.state.config.RAG_EMBEDDING_ENGINE = RAG_EMBEDDING_ENGINE
 app.state.config.RAG_EMBEDDING_MODEL = RAG_EMBEDDING_MODEL
-app.state.config.RAG_EMBEDDING_OPENAI_BATCH_SIZE = RAG_EMBEDDING_OPENAI_BATCH_SIZE
+app.state.config.RAG_EMBEDDING_BATCH_SIZE = RAG_EMBEDDING_BATCH_SIZE
 app.state.config.RAG_RERANKING_MODEL = RAG_RERANKING_MODEL
 app.state.config.RAG_TEMPLATE = RAG_TEMPLATE
 
@@ -233,7 +233,7 @@ app.state.EMBEDDING_FUNCTION = get_embedding_function(
     app.state.sentence_transformer_ef,
     app.state.config.OPENAI_API_KEY,
     app.state.config.OPENAI_API_BASE_URL,
-    app.state.config.RAG_EMBEDDING_OPENAI_BATCH_SIZE,
+    app.state.config.RAG_EMBEDDING_BATCH_SIZE,
 )
 
 app.add_middleware(
@@ -267,7 +267,7 @@ async def get_status():
         "embedding_engine": app.state.config.RAG_EMBEDDING_ENGINE,
         "embedding_model": app.state.config.RAG_EMBEDDING_MODEL,
         "reranking_model": app.state.config.RAG_RERANKING_MODEL,
-        "openai_batch_size": app.state.config.RAG_EMBEDDING_OPENAI_BATCH_SIZE,
+        "embedding_batch_size": app.state.config.RAG_EMBEDDING_BATCH_SIZE,
     }
 
 
@@ -277,10 +277,10 @@ async def get_embedding_config(user=Depends(get_admin_user)):
         "status": True,
         "embedding_engine": app.state.config.RAG_EMBEDDING_ENGINE,
         "embedding_model": app.state.config.RAG_EMBEDDING_MODEL,
+        "embedding_batch_size": app.state.config.RAG_EMBEDDING_BATCH_SIZE,
         "openai_config": {
             "url": app.state.config.OPENAI_API_BASE_URL,
             "key": app.state.config.OPENAI_API_KEY,
-            "batch_size": app.state.config.RAG_EMBEDDING_OPENAI_BATCH_SIZE,
         },
     }
 
@@ -296,13 +296,13 @@ async def get_reraanking_config(user=Depends(get_admin_user)):
 class OpenAIConfigForm(BaseModel):
     url: str
     key: str
-    batch_size: Optional[int] = None
 
 
 class EmbeddingModelUpdateForm(BaseModel):
     openai_config: Optional[OpenAIConfigForm] = None
     embedding_engine: str
     embedding_model: str
+    embedding_batch_size: Optional[int] = 1
 
 
 @app.post("/embedding/update")
@@ -320,11 +320,7 @@ async def update_embedding_config(
             if form_data.openai_config is not None:
                 app.state.config.OPENAI_API_BASE_URL = form_data.openai_config.url
                 app.state.config.OPENAI_API_KEY = form_data.openai_config.key
-                app.state.config.RAG_EMBEDDING_OPENAI_BATCH_SIZE = (
-                    form_data.openai_config.batch_size
-                    if form_data.openai_config.batch_size
-                    else 1
-                )
+            app.state.config.RAG_EMBEDDING_BATCH_SIZE = form_data.embedding_batch_size
 
         update_embedding_model(app.state.config.RAG_EMBEDDING_MODEL)
 
@@ -334,17 +330,17 @@ async def update_embedding_config(
             app.state.sentence_transformer_ef,
             app.state.config.OPENAI_API_KEY,
             app.state.config.OPENAI_API_BASE_URL,
-            app.state.config.RAG_EMBEDDING_OPENAI_BATCH_SIZE,
+            app.state.config.RAG_EMBEDDING_BATCH_SIZE,
         )
 
         return {
             "status": True,
             "embedding_engine": app.state.config.RAG_EMBEDDING_ENGINE,
             "embedding_model": app.state.config.RAG_EMBEDDING_MODEL,
+            "embedding_batch_size": app.state.config.RAG_EMBEDDING_BATCH_SIZE,
             "openai_config": {
                 "url": app.state.config.OPENAI_API_BASE_URL,
                 "key": app.state.config.OPENAI_API_KEY,
-                "batch_size": app.state.config.RAG_EMBEDDING_OPENAI_BATCH_SIZE,
             },
         }
     except Exception as e:
@@ -690,7 +686,7 @@ def save_docs_to_vector_db(
             app.state.sentence_transformer_ef,
             app.state.config.OPENAI_API_KEY,
             app.state.config.OPENAI_API_BASE_URL,
-            app.state.config.RAG_EMBEDDING_OPENAI_BATCH_SIZE,
+            app.state.config.RAG_EMBEDDING_BATCH_SIZE,
         )
 
         embeddings = embedding_function(