gardel/lightrag
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'main' into feat-node-expand

Browse Source
This commit is contained in:
yangdx
2025-03-17 00:08:12 +08:00
parent e7456c8579 9875037e6c
commit 1c19290979
7 changed files with 13 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
lightrag/api/README.md
View File

@@ -224,7 +224,7 @@ LightRAG supports binding to various LLM/Embedding backends:
Use environment variables `LLM_BINDING` or CLI argument `--llm-binding` to select LLM backend type. Use environment variables `EMBEDDING_BINDING` or CLI argument `--embedding-binding` to select LLM backend type.
### Entity Extraction Configuration
* ENABLE_LLM_CACHE_FOR_EXTRACT: Enable LLM cache for entity extraction (default: false)
* ENABLE_LLM_CACHE_FOR_EXTRACT: Enable LLM cache for entity extraction (default: true)
It's very common to set `ENABLE_LLM_CACHE_FOR_EXTRACT` to true for test environment to reduce the cost of LLM calls.

2
lightrag/api/docs/LightRagWithPostGRESQL.md
View File

@@ -141,7 +141,7 @@ Start the LightRAG server using specified options:
lightrag-server --port 9621 --key sk-somepassword --kv-storage PGKVStorage --graph-storage PGGraphStorage --vector-storage PGVectorStorage --doc-status-storage PGDocStatusStorage
```
Replace `the-port-number` with your desired port number (default is 9621) and `your-secret-key` with a secure key.
Replace the `port` number with your desired port number (default is 9621) and `your-secret-key` with a secure key.
## Conclusion

2
lightrag/api/utils_api.py
View File

@@ -364,7 +364,7 @@ def parse_args(is_uvicorn_mode: bool = False) -> argparse.Namespace:
# Inject LLM cache configuration
args.enable_llm_cache_for_extract = get_env_value(
"ENABLE_LLM_CACHE_FOR_EXTRACT", False, bool
"ENABLE_LLM_CACHE_FOR_EXTRACT", True, bool
)
# Select Document loading tool (DOCLING, DEFAULT)

6
lightrag/kg/postgres_impl.py
View File

@@ -755,7 +755,7 @@ class PGDocStatusStorage(DocStatusStorage):
result = await self.db.query(sql, params, True)
docs_by_status = {
element["id"]: DocProcessingStatus(
content=result[0]["content"],
content=element["content"],
content_summary=element["content_summary"],
content_length=element["content_length"],
status=element["status"],
@@ -1556,7 +1556,7 @@ TABLES = {
content_vector VECTOR,
create_time TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
update_time TIMESTAMP,
chunk_id VARCHAR(255) NULL,
chunk_id TEXT NULL,
CONSTRAINT LIGHTRAG_VDB_ENTITY_PK PRIMARY KEY (workspace, id)
)"""
},
@@ -1570,7 +1570,7 @@ TABLES = {
content_vector VECTOR,
create_time TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
update_time TIMESTAMP,
chunk_id VARCHAR(255) NULL,
chunk_id TEXT NULL,
CONSTRAINT LIGHTRAG_VDB_RELATION_PK PRIMARY KEY (workspace, id)
)"""
},

6
lightrag/lightrag.py
View File

@@ -214,7 +214,7 @@ class LightRAG:
llm_model_max_token_size: int = field(default=int(os.getenv("MAX_TOKENS", 32768)))
"""Maximum number of tokens allowed per LLM response."""
llm_model_max_async: int = field(default=int(os.getenv("MAX_ASYNC", 16)))
llm_model_max_async: int = field(default=int(os.getenv("MAX_ASYNC", 4)))
"""Maximum number of concurrent LLM calls."""
llm_model_kwargs: dict[str, Any] = field(default_factory=dict)
@@ -238,7 +238,7 @@ class LightRAG:
# Extensions
# ---
max_parallel_insert: int = field(default=int(os.getenv("MAX_PARALLEL_INSERT", 20)))
max_parallel_insert: int = field(default=int(os.getenv("MAX_PARALLEL_INSERT", 2)))
"""Maximum number of parallel insert operations."""
addon_params: dict[str, Any] = field(
@@ -553,6 +553,7 @@ class LightRAG:
Args:
input: Single document string or list of document strings
split_by_character: if split_by_character is not None, split the string by character, if chunk longer than
chunk_token_size, it will be split again by token size.
split_by_character_only: if split_by_character_only is True, split the string by character only, when
split_by_character is None, this parameter is ignored.
ids: single string of the document ID or list of unique document IDs, if not provided, MD5 hash IDs will be generated
@@ -574,6 +575,7 @@ class LightRAG:
Args:
input: Single document string or list of document strings
split_by_character: if split_by_character is not None, split the string by character, if chunk longer than
chunk_token_size, it will be split again by token size.
split_by_character_only: if split_by_character_only is True, split the string by character only, when
split_by_character is None, this parameter is ignored.
ids: list of unique document IDs, if not provided, MD5 hash IDs will be generated