From 1d0376d6a926ef60d641af4406dacf5b8bbb430f Mon Sep 17 00:00:00 2001 From: zrguo <49157727+LarFii@users.noreply.github.com> Date: Mon, 14 Jul 2025 16:27:49 +0800 Subject: [PATCH] update from main --- README-zh.md | 2 +- README.md | 2 +- env.example | 8 +- lightrag/operate.py | 421 +++++++----------- lightrag_webui/src/api/lightrag.ts | 16 - .../components/retrieval/QuerySettings.tsx | 38 +- lightrag_webui/src/locales/ar.json | 10 +- lightrag_webui/src/locales/en.json | 10 +- lightrag_webui/src/locales/fr.json | 10 +- lightrag_webui/src/locales/zh.json | 10 +- lightrag_webui/src/locales/zh_TW.json | 10 +- 11 files changed, 205 insertions(+), 332 deletions(-) diff --git a/README-zh.md b/README-zh.md index d0b3ec70..02d7295c 100644 --- a/README-zh.md +++ b/README-zh.md @@ -250,7 +250,7 @@ if __name__ == "__main__": | **embedding_func_max_async** | `int` | 最大并发异步嵌入进程数 | `16` | | **llm_model_func** | `callable` | LLM生成的函数 | `gpt_4o_mini_complete` | | **llm_model_name** | `str` | 用于生成的LLM模型名称 | `meta-llama/Llama-3.2-1B-Instruct` | -| **llm_model_max_token_size** | `int` | 生成实体关系摘要时送给LLM的最大令牌数 | `32000`（默认值由环境变量MAX_TOKENS更改） | +| **llm_model_max_token_size** | `int` | LLM生成的最大令牌大小（影响实体关系摘要） | `32768`（默认值由环境变量MAX_TOKENS更改） | | **llm_model_max_async** | `int` | 最大并发异步LLM进程数 | `4`（默认值由环境变量MAX_ASYNC更改） | | **llm_model_kwargs** | `dict` | LLM生成的附加参数 | | | **vector_db_storage_cls_kwargs** | `dict` | 向量数据库的附加参数，如设置节点和关系检索的阈值 | cosine_better_than_threshold: 0.2（默认值由环境变量COSINE_THRESHOLD更改） | diff --git a/README.md b/README.md index 5be7389d..a04eb1d7 100644 --- a/README.md +++ b/README.md @@ -257,7 +257,7 @@ A full list of LightRAG init parameters: | **embedding_func_max_async** | `int` | Maximum number of concurrent asynchronous embedding processes | `16` | | **llm_model_func** | `callable` | Function for LLM generation | `gpt_4o_mini_complete` | | **llm_model_name** | `str` | LLM model name for generation | `meta-llama/Llama-3.2-1B-Instruct` | -| **llm_model_max_token_size** | `int` | Maximum tokens send to LLM to generate entity relation summaries | `32000`（default value changed by env var MAX_TOKENS) | +| **llm_model_max_token_size** | `int` | Maximum token size for LLM generation (affects entity relation summaries) | `32768`（default value changed by env var MAX_TOKENS) | | **llm_model_max_async** | `int` | Maximum number of concurrent asynchronous LLM processes | `4`（default value changed by env var MAX_ASYNC) | | **llm_model_kwargs** | `dict` | Additional parameters for LLM generation | | | **vector_db_storage_cls_kwargs** | `dict` | Additional parameters for vector database, like setting the threshold for nodes and relations retrieval | cosine_better_than_threshold: 0.2（default value changed by env var COSINE_THRESHOLD) | diff --git a/env.example b/env.example index 50b68c1f..ec5d0bad 100644 --- a/env.example +++ b/env.example @@ -46,6 +46,7 @@ OLLAMA_EMULATING_MODEL_TAG=latest ### Chunk size for document splitting, 500~1500 is recommended # CHUNK_SIZE=1200 # CHUNK_OVERLAP_SIZE=100 +# MAX_TOKEN_SUMMARY=500 ### RAG Query Configuration # HISTORY_TURNS=3 @@ -93,7 +94,8 @@ TEMPERATURE=0 ### Max concurrency requests of LLM MAX_ASYNC=4 ### MAX_TOKENS: max tokens send to LLM for entity relation summaries (less than context size of the model) -MAX_TOKENS=32000 +### MAX_TOKENS: set as num_ctx option for Ollama by API Server +MAX_TOKENS=32768 ### LLM Binding type: openai, ollama, lollms, azure_openai LLM_BINDING=openai LLM_MODEL=gpt-4o @@ -102,8 +104,6 @@ LLM_BINDING_API_KEY=your_api_key ### Optional for Azure # AZURE_OPENAI_API_VERSION=2024-08-01-preview # AZURE_OPENAI_DEPLOYMENT=gpt-4o -### set as num_ctx option for Ollama LLM -# OLLAMA_NUM_CTX=32768 ### Embedding Configuration ### Embedding Binding type: openai, ollama, lollms, azure_openai @@ -116,7 +116,7 @@ EMBEDDING_BINDING_HOST=http://localhost:11434 ### Num of chunks send to Embedding in single request # EMBEDDING_BATCH_NUM=10 ### Max concurrency requests for Embedding -# EMBEDDING_FUNC_MAX_ASYNC=8 +# EMBEDDING_FUNC_MAX_ASYNC=16 ### Maximum tokens sent to Embedding for each chunk (no longer in use?) # MAX_EMBED_TOKENS=8192 ### Optional for Azure diff --git a/lightrag/operate.py b/lightrag/operate.py index 3d009363..668d42a9 100644 --- a/lightrag/operate.py +++ b/lightrag/operate.py @@ -37,7 +37,6 @@ from .base import ( ) from .prompt import PROMPTS from .constants import GRAPH_FIELD_SEP -from .kg.shared_storage import get_storage_keyed_lock import time from dotenv import load_dotenv @@ -118,7 +117,7 @@ async def _handle_entity_relation_summary( tokenizer: Tokenizer = global_config["tokenizer"] llm_max_tokens = global_config["llm_model_max_token_size"] - # summary_max_tokens = global_config["summary_to_max_tokens"] + summary_max_tokens = global_config["summary_to_max_tokens"] language = global_config["addon_params"].get( "language", PROMPTS["DEFAULT_LANGUAGE"] @@ -145,7 +144,7 @@ async def _handle_entity_relation_summary( use_prompt, use_llm_func, llm_response_cache=llm_response_cache, - # max_tokens=summary_max_tokens, + max_tokens=summary_max_tokens, cache_type="extract", ) return summary @@ -275,26 +274,20 @@ async def _rebuild_knowledge_from_chunks( pipeline_status: dict | None = None, pipeline_status_lock=None, ) -> None: - """Rebuild entity and relationship descriptions from cached extraction results with parallel processing + """Rebuild entity and relationship descriptions from cached extraction results This method uses cached LLM extraction results instead of calling LLM again, - following the same approach as the insert process. Now with parallel processing - controlled by llm_model_max_async and using get_storage_keyed_lock for data consistency. + following the same approach as the insert process. Args: entities_to_rebuild: Dict mapping entity_name -> set of remaining chunk_ids relationships_to_rebuild: Dict mapping (src, tgt) -> set of remaining chunk_ids - knowledge_graph_inst: Knowledge graph storage - entities_vdb: Entity vector database - relationships_vdb: Relationship vector database - text_chunks_storage: Text chunks storage - llm_response_cache: LLM response cache - global_config: Global configuration containing llm_model_max_async - pipeline_status: Pipeline status dictionary - pipeline_status_lock: Lock for pipeline status + text_chunks_data: Pre-loaded chunk data dict {chunk_id: chunk_data} """ if not entities_to_rebuild and not relationships_to_rebuild: return + rebuilt_entities_count = 0 + rebuilt_relationships_count = 0 # Get all referenced chunk IDs all_referenced_chunk_ids = set() @@ -303,7 +296,7 @@ async def _rebuild_knowledge_from_chunks( for chunk_ids in relationships_to_rebuild.values(): all_referenced_chunk_ids.update(chunk_ids) - status_message = f"Rebuilding knowledge from {len(all_referenced_chunk_ids)} cached chunk extractions (parallel processing)" + status_message = f"Rebuilding knowledge from {len(all_referenced_chunk_ids)} cached chunk extractions" logger.info(status_message) if pipeline_status is not None and pipeline_status_lock is not None: async with pipeline_status_lock: @@ -373,116 +366,66 @@ async def _rebuild_knowledge_from_chunks( pipeline_status["history_messages"].append(status_message) continue - # Get max async tasks limit from global_config for semaphore control - graph_max_async = global_config.get("llm_model_max_async", 4) * 2 - semaphore = asyncio.Semaphore(graph_max_async) - - # Counters for tracking progress - rebuilt_entities_count = 0 - rebuilt_relationships_count = 0 - failed_entities_count = 0 - failed_relationships_count = 0 - - async def _locked_rebuild_entity(entity_name, chunk_ids): - nonlocal rebuilt_entities_count, failed_entities_count - async with semaphore: - workspace = global_config.get("workspace", "") - namespace = f"{workspace}:GraphDB" if workspace else "GraphDB" - async with get_storage_keyed_lock( - [entity_name], namespace=namespace, enable_logging=False - ): - try: - await _rebuild_single_entity( - knowledge_graph_inst=knowledge_graph_inst, - entities_vdb=entities_vdb, - entity_name=entity_name, - chunk_ids=chunk_ids, - chunk_entities=chunk_entities, - llm_response_cache=llm_response_cache, - global_config=global_config, - ) - rebuilt_entities_count += 1 - status_message = ( - f"Rebuilt entity: {entity_name} from {len(chunk_ids)} chunks" - ) - logger.info(status_message) - if pipeline_status is not None and pipeline_status_lock is not None: - async with pipeline_status_lock: - pipeline_status["latest_message"] = status_message - pipeline_status["history_messages"].append(status_message) - except Exception as e: - failed_entities_count += 1 - status_message = f"Failed to rebuild entity {entity_name}: {e}" - logger.info(status_message) # Per requirement, change to info - if pipeline_status is not None and pipeline_status_lock is not None: - async with pipeline_status_lock: - pipeline_status["latest_message"] = status_message - pipeline_status["history_messages"].append(status_message) - - async def _locked_rebuild_relationship(src, tgt, chunk_ids): - nonlocal rebuilt_relationships_count, failed_relationships_count - async with semaphore: - workspace = global_config.get("workspace", "") - namespace = f"{workspace}:GraphDB" if workspace else "GraphDB" - async with get_storage_keyed_lock( - f"{src}-{tgt}", namespace=namespace, enable_logging=False - ): - try: - await _rebuild_single_relationship( - knowledge_graph_inst=knowledge_graph_inst, - relationships_vdb=relationships_vdb, - src=src, - tgt=tgt, - chunk_ids=chunk_ids, - chunk_relationships=chunk_relationships, - llm_response_cache=llm_response_cache, - global_config=global_config, - ) - rebuilt_relationships_count += 1 - status_message = f"Rebuilt relationship: {src}->{tgt} from {len(chunk_ids)} chunks" - logger.info(status_message) - if pipeline_status is not None and pipeline_status_lock is not None: - async with pipeline_status_lock: - pipeline_status["latest_message"] = status_message - pipeline_status["history_messages"].append(status_message) - except Exception as e: - failed_relationships_count += 1 - status_message = f"Failed to rebuild relationship {src}->{tgt}: {e}" - logger.info(status_message) # Per requirement, change to info - if pipeline_status is not None and pipeline_status_lock is not None: - async with pipeline_status_lock: - pipeline_status["latest_message"] = status_message - pipeline_status["history_messages"].append(status_message) - - # Create tasks for parallel processing - tasks = [] - - # Add entity rebuilding tasks + # Rebuild entities for entity_name, chunk_ids in entities_to_rebuild.items(): - task = asyncio.create_task(_locked_rebuild_entity(entity_name, chunk_ids)) - tasks.append(task) + try: + await _rebuild_single_entity( + knowledge_graph_inst=knowledge_graph_inst, + entities_vdb=entities_vdb, + entity_name=entity_name, + chunk_ids=chunk_ids, + chunk_entities=chunk_entities, + llm_response_cache=llm_response_cache, + global_config=global_config, + ) + rebuilt_entities_count += 1 + status_message = ( + f"Rebuilt entity: {entity_name} from {len(chunk_ids)} chunks" + ) + logger.info(status_message) + if pipeline_status is not None and pipeline_status_lock is not None: + async with pipeline_status_lock: + pipeline_status["latest_message"] = status_message + pipeline_status["history_messages"].append(status_message) + except Exception as e: + status_message = f"Failed to rebuild entity {entity_name}: {e}" + logger.info(status_message) # Per requirement, change to info + if pipeline_status is not None and pipeline_status_lock is not None: + async with pipeline_status_lock: + pipeline_status["latest_message"] = status_message + pipeline_status["history_messages"].append(status_message) - # Add relationship rebuilding tasks + # Rebuild relationships for (src, tgt), chunk_ids in relationships_to_rebuild.items(): - task = asyncio.create_task(_locked_rebuild_relationship(src, tgt, chunk_ids)) - tasks.append(task) - - # Log parallel processing start - status_message = f"Starting parallel rebuild of {len(entities_to_rebuild)} entities and {len(relationships_to_rebuild)} relationships (async: {graph_max_async})" - logger.info(status_message) - if pipeline_status is not None and pipeline_status_lock is not None: - async with pipeline_status_lock: - pipeline_status["latest_message"] = status_message - pipeline_status["history_messages"].append(status_message) - - # Execute all tasks in parallel with semaphore control - await asyncio.gather(*tasks) - - # Final status report - status_message = f"KG rebuild completed: {rebuilt_entities_count} entities and {rebuilt_relationships_count} relationships rebuilt successfully." - if failed_entities_count > 0 or failed_relationships_count > 0: - status_message += f" Failed: {failed_entities_count} entities, {failed_relationships_count} relationships." + try: + await _rebuild_single_relationship( + knowledge_graph_inst=knowledge_graph_inst, + relationships_vdb=relationships_vdb, + src=src, + tgt=tgt, + chunk_ids=chunk_ids, + chunk_relationships=chunk_relationships, + llm_response_cache=llm_response_cache, + global_config=global_config, + ) + rebuilt_relationships_count += 1 + status_message = ( + f"Rebuilt relationship: {src}->{tgt} from {len(chunk_ids)} chunks" + ) + logger.info(status_message) + if pipeline_status is not None and pipeline_status_lock is not None: + async with pipeline_status_lock: + pipeline_status["latest_message"] = status_message + pipeline_status["history_messages"].append(status_message) + except Exception as e: + status_message = f"Failed to rebuild relationship {src}->{tgt}: {e}" + logger.info(status_message) + if pipeline_status is not None and pipeline_status_lock is not None: + async with pipeline_status_lock: + pipeline_status["latest_message"] = status_message + pipeline_status["history_messages"].append(status_message) + status_message = f"KG rebuild completed: {rebuilt_entities_count} entities and {rebuilt_relationships_count} relationships." logger.info(status_message) if pipeline_status is not None and pipeline_status_lock is not None: async with pipeline_status_lock: @@ -687,10 +630,7 @@ async def _rebuild_single_entity( # Helper function to generate final description with optional LLM summary async def _generate_final_description(combined_description: str) -> str: - force_llm_summary_on_merge = global_config["force_llm_summary_on_merge"] - num_fragment = combined_description.count(GRAPH_FIELD_SEP) + 1 - - if num_fragment >= force_llm_summary_on_merge: + if len(combined_description) > global_config["summary_to_max_tokens"]: return await _handle_entity_relation_summary( entity_name, combined_description, @@ -785,11 +725,7 @@ async def _rebuild_single_relationship( llm_response_cache: BaseKVStorage, global_config: dict[str, str], ) -> None: - """Rebuild a single relationship from cached extraction results - - Note: This function assumes the caller has already acquired the appropriate - keyed lock for the relationship pair to ensure thread safety. - """ + """Rebuild a single relationship from cached extraction results""" # Get current relationship data current_relationship = await knowledge_graph_inst.get_edge(src, tgt) @@ -845,11 +781,8 @@ async def _rebuild_single_relationship( # ) weight = sum(weights) if weights else current_relationship.get("weight", 1.0) - # Use summary if description has too many fragments - force_llm_summary_on_merge = global_config["force_llm_summary_on_merge"] - num_fragment = combined_description.count(GRAPH_FIELD_SEP) + 1 - - if num_fragment >= force_llm_summary_on_merge: + # Use summary if description is too long + if len(combined_description) > global_config["summary_to_max_tokens"]: final_description = await _handle_entity_relation_summary( f"{src}-{tgt}", combined_description, @@ -1082,23 +1015,28 @@ async def _merge_edges_then_upsert( ) for need_insert_id in [src_id, tgt_id]: - workspace = global_config.get("workspace", "") - namespace = f"{workspace}:GraphDB" if workspace else "GraphDB" - async with get_storage_keyed_lock( - [need_insert_id], namespace=namespace, enable_logging=False - ): - if not (await knowledge_graph_inst.has_node(need_insert_id)): - await knowledge_graph_inst.upsert_node( - need_insert_id, - node_data={ - "entity_id": need_insert_id, - "source_id": source_id, - "description": description, - "entity_type": "UNKNOWN", - "file_path": file_path, - "created_at": int(time.time()), - }, - ) + if not (await knowledge_graph_inst.has_node(need_insert_id)): + # # Discard this edge if the node does not exist + # if need_insert_id == src_id: + # logger.warning( + # f"Discard edge: {src_id} - {tgt_id} | Source node missing" + # ) + # else: + # logger.warning( + # f"Discard edge: {src_id} - {tgt_id} | Target node missing" + # ) + # return None + await knowledge_graph_inst.upsert_node( + need_insert_id, + node_data={ + "entity_id": need_insert_id, + "source_id": source_id, + "description": description, + "entity_type": "UNKNOWN", + "file_path": file_path, + "created_at": int(time.time()), + }, + ) force_llm_summary_on_merge = global_config["force_llm_summary_on_merge"] @@ -1180,6 +1118,8 @@ async def merge_nodes_and_edges( pipeline_status_lock: Lock for pipeline status llm_response_cache: LLM response cache """ + # Get lock manager from shared storage + from .kg.shared_storage import get_graph_db_lock # Collect all nodes and edges from all chunks all_nodes = defaultdict(list) @@ -1196,109 +1136,94 @@ async def merge_nodes_and_edges( all_edges[sorted_edge_key].extend(edges) # Centralized processing of all nodes and edges - total_entities_count = len(all_nodes) - total_relations_count = len(all_edges) + entities_data = [] + relationships_data = [] # Merge nodes and edges - log_message = f"Merging stage {current_file_number}/{total_files}: {file_path}" - logger.info(log_message) - async with pipeline_status_lock: - pipeline_status["latest_message"] = log_message - pipeline_status["history_messages"].append(log_message) + # Use graph database lock to ensure atomic merges and updates + graph_db_lock = get_graph_db_lock(enable_logging=False) + async with graph_db_lock: + async with pipeline_status_lock: + log_message = ( + f"Merging stage {current_file_number}/{total_files}: {file_path}" + ) + logger.info(log_message) + pipeline_status["latest_message"] = log_message + pipeline_status["history_messages"].append(log_message) - # Get max async tasks limit from global_config for semaphore control - graph_max_async = global_config.get("llm_model_max_async", 4) * 2 - semaphore = asyncio.Semaphore(graph_max_async) + # Process and update all entities at once + for entity_name, entities in all_nodes.items(): + entity_data = await _merge_nodes_then_upsert( + entity_name, + entities, + knowledge_graph_inst, + global_config, + pipeline_status, + pipeline_status_lock, + llm_response_cache, + ) + entities_data.append(entity_data) - # Process and update all entities and relationships in parallel - log_message = f"Processing: {total_entities_count} entities and {total_relations_count} relations (async: {graph_max_async})" - logger.info(log_message) - async with pipeline_status_lock: - pipeline_status["latest_message"] = log_message - pipeline_status["history_messages"].append(log_message) + # Process and update all relationships at once + for edge_key, edges in all_edges.items(): + edge_data = await _merge_edges_then_upsert( + edge_key[0], + edge_key[1], + edges, + knowledge_graph_inst, + global_config, + pipeline_status, + pipeline_status_lock, + llm_response_cache, + ) + if edge_data is not None: + relationships_data.append(edge_data) - async def _locked_process_entity_name(entity_name, entities): - async with semaphore: - workspace = global_config.get("workspace", "") - namespace = f"{workspace}:GraphDB" if workspace else "GraphDB" - async with get_storage_keyed_lock( - [entity_name], namespace=namespace, enable_logging=False - ): - entity_data = await _merge_nodes_then_upsert( - entity_name, - entities, - knowledge_graph_inst, - global_config, - pipeline_status, - pipeline_status_lock, - llm_response_cache, - ) - if entity_vdb is not None: - data_for_vdb = { - compute_mdhash_id(entity_data["entity_name"], prefix="ent-"): { - "entity_name": entity_data["entity_name"], - "entity_type": entity_data["entity_type"], - "content": f"{entity_data['entity_name']}\n{entity_data['description']}", - "source_id": entity_data["source_id"], - "file_path": entity_data.get("file_path", "unknown_source"), - } - } - await entity_vdb.upsert(data_for_vdb) - return entity_data + # Update total counts + total_entities_count = len(entities_data) + total_relations_count = len(relationships_data) - async def _locked_process_edges(edge_key, edges): - async with semaphore: - workspace = global_config.get("workspace", "") - namespace = f"{workspace}:GraphDB" if workspace else "GraphDB" - async with get_storage_keyed_lock( - f"{edge_key[0]}-{edge_key[1]}", - namespace=namespace, - enable_logging=False, - ): - edge_data = await _merge_edges_then_upsert( - edge_key[0], - edge_key[1], - edges, - knowledge_graph_inst, - global_config, - pipeline_status, - pipeline_status_lock, - llm_response_cache, - ) - if edge_data is None: - return None + log_message = f"Updating {total_entities_count} entities {current_file_number}/{total_files}: {file_path}" + logger.info(log_message) + if pipeline_status is not None: + async with pipeline_status_lock: + pipeline_status["latest_message"] = log_message + pipeline_status["history_messages"].append(log_message) - if relationships_vdb is not None: - data_for_vdb = { - compute_mdhash_id( - edge_data["src_id"] + edge_data["tgt_id"], prefix="rel-" - ): { - "src_id": edge_data["src_id"], - "tgt_id": edge_data["tgt_id"], - "keywords": edge_data["keywords"], - "content": f"{edge_data['src_id']}\t{edge_data['tgt_id']}\n{edge_data['keywords']}\n{edge_data['description']}", - "source_id": edge_data["source_id"], - "file_path": edge_data.get("file_path", "unknown_source"), - } - } - await relationships_vdb.upsert(data_for_vdb) - return edge_data + # Update vector databases with all collected data + if entity_vdb is not None and entities_data: + data_for_vdb = { + compute_mdhash_id(dp["entity_name"], prefix="ent-"): { + "entity_name": dp["entity_name"], + "entity_type": dp["entity_type"], + "content": f"{dp['entity_name']}\n{dp['description']}", + "source_id": dp["source_id"], + "file_path": dp.get("file_path", "unknown_source"), + } + for dp in entities_data + } + await entity_vdb.upsert(data_for_vdb) - # Create a single task queue for both entities and edges - tasks = [] + log_message = f"Updating {total_relations_count} relations {current_file_number}/{total_files}: {file_path}" + logger.info(log_message) + if pipeline_status is not None: + async with pipeline_status_lock: + pipeline_status["latest_message"] = log_message + pipeline_status["history_messages"].append(log_message) - # Add entity processing tasks - for entity_name, entities in all_nodes.items(): - tasks.append( - asyncio.create_task(_locked_process_entity_name(entity_name, entities)) - ) - - # Add edge processing tasks - for edge_key, edges in all_edges.items(): - tasks.append(asyncio.create_task(_locked_process_edges(edge_key, edges))) - - # Execute all tasks in parallel with semaphore control - await asyncio.gather(*tasks) + if relationships_vdb is not None and relationships_data: + data_for_vdb = { + compute_mdhash_id(dp["src_id"] + dp["tgt_id"], prefix="rel-"): { + "src_id": dp["src_id"], + "tgt_id": dp["tgt_id"], + "keywords": dp["keywords"], + "content": f"{dp['src_id']}\t{dp['tgt_id']}\n{dp['keywords']}\n{dp['description']}", + "source_id": dp["source_id"], + "file_path": dp.get("file_path", "unknown_source"), + } + for dp in relationships_data + } + await relationships_vdb.upsert(data_for_vdb) async def extract_entities( @@ -1508,8 +1433,8 @@ async def extract_entities( return maybe_nodes, maybe_edges # Get max async tasks limit from global_config - chunk_max_async = global_config.get("llm_model_max_async", 4) - semaphore = asyncio.Semaphore(chunk_max_async) + llm_model_max_async = global_config.get("llm_model_max_async", 4) + semaphore = asyncio.Semaphore(llm_model_max_async) async def _process_with_semaphore(chunk): async with semaphore: diff --git a/lightrag_webui/src/api/lightrag.ts b/lightrag_webui/src/api/lightrag.ts index 1ecde87b..77601ec7 100644 --- a/lightrag_webui/src/api/lightrag.ts +++ b/lightrag_webui/src/api/lightrag.ts @@ -42,28 +42,12 @@ export type LightragStatus = { vector_storage: string workspace?: string max_graph_nodes?: string - enable_rerank?: boolean - rerank_model?: string | null - rerank_binding_host?: string | null } update_status?: Record core_version?: string api_version?: string auth_mode?: 'enabled' | 'disabled' pipeline_busy: boolean - keyed_locks?: { - process_id: number - cleanup_performed: { - mp_cleaned: number - async_cleaned: number - } - current_status: { - total_mp_locks: number - pending_mp_cleanup: number - total_async_locks: number - pending_async_cleanup: number - } - } webui_title?: string webui_description?: string } diff --git a/lightrag_webui/src/components/retrieval/QuerySettings.tsx b/lightrag_webui/src/components/retrieval/QuerySettings.tsx index f1514a4b..b21f5b11 100644 --- a/lightrag_webui/src/components/retrieval/QuerySettings.tsx +++ b/lightrag_webui/src/components/retrieval/QuerySettings.tsx @@ -2,6 +2,7 @@ import { useCallback } from 'react' import { QueryMode, QueryRequest } from '@/api/lightrag' // Removed unused import for Text component import Checkbox from '@/components/ui/Checkbox' +import NumberInput from '@/components/ui/NumberInput' import Input from '@/components/ui/Input' import { Card, CardContent, CardDescription, CardHeader, CardTitle } from '@/components/ui/Card' import { @@ -120,20 +121,11 @@ export default function QuerySettings() {
{/* Removed sr-only label */} - { - const value = e.target.value - handleChange('top_k', value === '' ? '' : parseInt(value) || 0) - }} - onBlur={(e) => { - const value = e.target.value - if (value === '' || isNaN(parseInt(value))) { - handleChange('top_k', 1) - } - }} + stepper={1} + value={querySettings.top_k} + onValueChange={(v) => handleChange('top_k', v)} min={1} placeholder={t('retrievePanel.querySettings.topKPlaceholder')} /> @@ -286,23 +278,15 @@ export default function QuerySettings() {
{/* Removed sr-only label */} - { - const value = e.target.value - handleChange('history_turns', value === '' ? '' : parseInt(value) || 0) - }} - onBlur={(e) => { - const value = e.target.value - if (value === '' || isNaN(parseInt(value))) { - handleChange('history_turns', 0) - } - }} + stepper={1} + type="text" + value={querySettings.history_turns} + onValueChange={(v) => handleChange('history_turns', v)} min={0} placeholder={t('retrievePanel.querySettings.historyTurnsPlaceholder')} - className="h-9" />
diff --git a/lightrag_webui/src/locales/ar.json b/lightrag_webui/src/locales/ar.json index deca4edc..44a2d65d 100644 --- a/lightrag_webui/src/locales/ar.json +++ b/lightrag_webui/src/locales/ar.json @@ -252,12 +252,12 @@ "inputDirectory": "دليل الإدخال", "llmConfig": "تكوين نموذج اللغة الكبير", "llmBinding": "ربط نموذج اللغة الكبير", - "llmBindingHost": "نقطة نهاية نموذج اللغة الكبير", + "llmBindingHost": "مضيف ربط نموذج اللغة الكبير", "llmModel": "نموذج اللغة الكبير", "maxTokens": "أقصى عدد من الرموز", "embeddingConfig": "تكوين التضمين", "embeddingBinding": "ربط التضمين", - "embeddingBindingHost": "نقطة نهاية التضمين", + "embeddingBindingHost": "مضيف ربط التضمين", "embeddingModel": "نموذج التضمين", "storageConfig": "تكوين التخزين", "kvStorage": "تخزين المفتاح-القيمة", @@ -265,11 +265,7 @@ "graphStorage": "تخزين الرسم البياني", "vectorStorage": "تخزين المتجهات", "workspace": "مساحة العمل", - "maxGraphNodes": "الحد الأقصى لعقد الرسم البياني", - "rerankerConfig": "تكوين إعادة الترتيب", - "rerankerBindingHost": "نقطة نهاية إعادة الترتيب", - "rerankerModel": "نموذج إعادة الترتيب", - "lockStatus": "حالة القفل" + "maxGraphNodes": "الحد الأقصى لعقد الرسم البياني" }, "propertiesView": { "editProperty": "تعديل {{property}}", diff --git a/lightrag_webui/src/locales/en.json b/lightrag_webui/src/locales/en.json index 4a55ab40..219e1fcc 100644 --- a/lightrag_webui/src/locales/en.json +++ b/lightrag_webui/src/locales/en.json @@ -252,12 +252,12 @@ "inputDirectory": "Input Directory", "llmConfig": "LLM Configuration", "llmBinding": "LLM Binding", - "llmBindingHost": "LLM Endpoint", + "llmBindingHost": "LLM Binding Host", "llmModel": "LLM Model", "maxTokens": "Max Tokens", "embeddingConfig": "Embedding Configuration", "embeddingBinding": "Embedding Binding", - "embeddingBindingHost": "Embedding Endpoint", + "embeddingBindingHost": "Embedding Binding Host", "embeddingModel": "Embedding Model", "storageConfig": "Storage Configuration", "kvStorage": "KV Storage", @@ -265,11 +265,7 @@ "graphStorage": "Graph Storage", "vectorStorage": "Vector Storage", "workspace": "Workspace", - "maxGraphNodes": "Max Graph Nodes", - "rerankerConfig": "Reranker Configuration", - "rerankerBindingHost": "Reranker Endpoint", - "rerankerModel": "Reranker Model", - "lockStatus": "Lock Status" + "maxGraphNodes": "Max Graph Nodes" }, "propertiesView": { "editProperty": "Edit {{property}}", diff --git a/lightrag_webui/src/locales/fr.json b/lightrag_webui/src/locales/fr.json index 1395fa75..75ca6732 100644 --- a/lightrag_webui/src/locales/fr.json +++ b/lightrag_webui/src/locales/fr.json @@ -252,12 +252,12 @@ "inputDirectory": "Répertoire d'entrée", "llmConfig": "Configuration du modèle de langage", "llmBinding": "Liaison du modèle de langage", - "llmBindingHost": "Point de terminaison LLM", + "llmBindingHost": "Hôte de liaison du modèle de langage", "llmModel": "Modèle de langage", "maxTokens": "Nombre maximum de jetons", "embeddingConfig": "Configuration d'incorporation", "embeddingBinding": "Liaison d'incorporation", - "embeddingBindingHost": "Point de terminaison d'incorporation", + "embeddingBindingHost": "Hôte de liaison d'incorporation", "embeddingModel": "Modèle d'incorporation", "storageConfig": "Configuration de stockage", "kvStorage": "Stockage clé-valeur", @@ -265,11 +265,7 @@ "graphStorage": "Stockage du graphe", "vectorStorage": "Stockage vectoriel", "workspace": "Espace de travail", - "maxGraphNodes": "Nombre maximum de nœuds du graphe", - "rerankerConfig": "Configuration du reclassement", - "rerankerBindingHost": "Point de terminaison de reclassement", - "rerankerModel": "Modèle de reclassement", - "lockStatus": "État des verrous" + "maxGraphNodes": "Nombre maximum de nœuds du graphe" }, "propertiesView": { "editProperty": "Modifier {{property}}", diff --git a/lightrag_webui/src/locales/zh.json b/lightrag_webui/src/locales/zh.json index 430336c3..4482317f 100644 --- a/lightrag_webui/src/locales/zh.json +++ b/lightrag_webui/src/locales/zh.json @@ -252,12 +252,12 @@ "inputDirectory": "输入目录", "llmConfig": "LLM配置", "llmBinding": "LLM绑定", - "llmBindingHost": "LLM端点", + "llmBindingHost": "LLM绑定主机", "llmModel": "LLM模型", "maxTokens": "最大令牌数", "embeddingConfig": "嵌入配置", "embeddingBinding": "嵌入绑定", - "embeddingBindingHost": "嵌入端点", + "embeddingBindingHost": "嵌入绑定主机", "embeddingModel": "嵌入模型", "storageConfig": "存储配置", "kvStorage": "KV存储", @@ -265,11 +265,7 @@ "graphStorage": "图存储", "vectorStorage": "向量存储", "workspace": "工作空间", - "maxGraphNodes": "最大图节点数", - "rerankerConfig": "重排序配置", - "rerankerBindingHost": "重排序端点", - "rerankerModel": "重排序模型", - "lockStatus": "锁状态" + "maxGraphNodes": "最大图节点数" }, "propertiesView": { "editProperty": "编辑{{property}}", diff --git a/lightrag_webui/src/locales/zh_TW.json b/lightrag_webui/src/locales/zh_TW.json index acb85ce6..cf571e62 100644 --- a/lightrag_webui/src/locales/zh_TW.json +++ b/lightrag_webui/src/locales/zh_TW.json @@ -252,12 +252,12 @@ "inputDirectory": "輸入目錄", "llmConfig": "LLM 設定", "llmBinding": "LLM 綁定", - "llmBindingHost": "LLM 端點", + "llmBindingHost": "LLM 綁定主機", "llmModel": "LLM 模型", "maxTokens": "最大權杖數", "embeddingConfig": "嵌入設定", "embeddingBinding": "嵌入綁定", - "embeddingBindingHost": "嵌入端點", + "embeddingBindingHost": "嵌入綁定主機", "embeddingModel": "嵌入模型", "storageConfig": "儲存設定", "kvStorage": "KV 儲存", @@ -265,11 +265,7 @@ "graphStorage": "圖形儲存", "vectorStorage": "向量儲存", "workspace": "工作空間", - "maxGraphNodes": "最大圖形節點數", - "rerankerConfig": "重排序設定", - "rerankerBindingHost": "重排序端點", - "rerankerModel": "重排序模型", - "lockStatus": "鎖定狀態" + "maxGraphNodes": "最大圖形節點數" }, "propertiesView": { "editProperty": "編輯{{property}}",