Saifeddine ALOUI
27a52ddf37
fixed linting
2024-12-26 23:39:10 +01:00
Saifeddine ALOUI
4d0184189f
Added the option to only return context without doing a query to the AI (useful for automated systems like lollms)
2024-12-26 23:32:02 +01:00
Saifeddine ALOUI
5fcfb05e62
fixed file uploading
2024-12-26 22:48:52 +01:00
Saifeddine ALOUI
f2b52a2a38
Added azure openai lightrag server to the api install and fused documentation.
2024-12-26 21:32:56 +01:00
zrguo
457e683acd
Update lightrag.py
2024-12-26 22:14:04 +08:00
zrguo
a1493f56d6
Update utils.py
2024-12-26 22:09:46 +08:00
zrguo
1d3d4c092d
Merge pull request #513 from theClassLight/GG/pr
...
fix(utils): 修复缓存未正确启用的问题
2024-12-26 22:07:28 +08:00
GG
04293466ad
fix(utils): 修复缓存未正确启用的问题
...
- 在 handle_cache 函数中添加了对 global_config 中 enable_l`lm_cache 设置的检查
- 如果配置禁用了缓存，则直接返回 None
-这个修改确保了在不需要缓存的情况下，函数能够正确地跳过缓存处理
2024-12-26 22:03:45 +08:00
zrguo
1ca3f64e7d
Update __init__.py
2024-12-26 15:13:24 +08:00
Saifeddine ALOUI
9921223281
Merge remote-tracking branch 'upstream/main'
2024-12-25 18:04:02 +01:00
zrguo
dc0d60ea58
Merge pull request #504 from congiuluc/feature-azureopenai-api
...
Added Azure OpenAI api sample with streaming
2024-12-24 19:01:46 +08:00
Saifeddine ALOUI
69b3f0b37b
fixed the default lollms server port number
2024-12-24 11:33:28 +01:00
Saifeddine ALOUI
848465d5d7
precommit tested
2024-12-24 10:35:00 +01:00
Saifeddine ALOUI
9951f8584a
Added API as an option to the installation, reorganized the API and fused all documentations in README.md
2024-12-24 10:31:12 +01:00
Luca Congiu
725d5af215
Refactor code formatting and update requirements for improved clarity and consistency
2024-12-24 09:56:33 +01:00
Alex Potapenko
848b3f6e33
GremlinStorage: fixes and patch to support other Gremlin compatible BD. Tested on ArcadeDB with Gremlin plugin. The main change is using "entity_name" vertex property instead of the label as a node_id since different implementations have different restrictions on label names.
2024-12-23 16:16:17 +01:00
Luca Congiu
58e74d5fb2
Added Azure OpenAI api sample with streaming
2024-12-23 14:34:34 +01:00
Saifeddine ALOUI
469fa9f574
Added lollms integration with lightrag
...
Removed a depricated function from ollamaserver
2024-12-22 00:38:38 +01:00
zrguo
4042783a55
Update __init__.py
2024-12-20 18:26:53 +08:00
Alex Potapenko
016d9f572d
GremlinStorage: fix linting error, use asyncio.gather in get_node_edges()
2024-12-20 09:57:35 +01:00
Alex Potapenko
6f71293c83
Add Gremlin graph storage
2024-12-19 17:47:42 +01:00
Weaxs
344d8f277b
support TiDBGraphStorage
2024-12-18 10:57:33 +08:00
GG
2d048b5eb0
fix(llm): hashing_kv初始化修复
...
-hybrid模式对hashing_kv的依赖不止global_config，干脆复用llm_response_cache的初始化结构
2024-12-17 16:44:42 +08:00
Alex Potapenko
a44aceab1e
AGEStorage: fix has_node() and has_edge()
2024-12-14 13:37:34 +01:00
Alex Potapenko
25d6939ca3
AGEStorage: all queries as multiline strings for consistency
2024-12-14 12:49:39 +01:00
Alex Potapenko
05c73bcfd1
AGEStorage: fix debug logging, and some cosmetics
2024-12-14 12:47:29 +01:00
Alex Potapenko
eb2e6d0d87
AGEStorage: fix has_edge(): AGE always returns field names in lower case
2024-12-14 12:24:45 +01:00
Alex Potapenko
7564841450
Add Apache AGE graph storage
2024-12-13 20:41:38 +01:00
LarFii
b7a2d336e6
Update __version__
2024-12-13 20:15:49 +08:00
zrguo
9cac3b0ed7
Merge pull request #462 from JasonGuoo/main
...
Supporting Zhipu AI API
2024-12-13 20:09:11 +08:00
Jason Guo
e64cf5068f
Fix import
2024-12-13 19:57:25 +08:00
billvsme
a788c78197
keep tqdm_async work
2024-12-13 16:48:22 +08:00
Jason Guo
6a0e9c6c77
Modify the chat_complete method to support keywords extraction.
2024-12-13 16:18:33 +08:00
billvsme
cf0278ca43
The asyncio.as_completed() function does not guarantee that the results are ordered
2024-12-13 15:42:41 +08:00
zrguo
b7552f35aa
Merge pull request #461 from tjyiiuan/main
...
fix: update operate.py
2024-12-13 15:10:53 +08:00
Jiyu Tian
aac26b086e
fix: update operate.py
...
1. 避免变量在赋值之前就被引用
2. 解决未找到entity返回None导致的unpack问题
2024-12-12 15:47:57 -05:00
chenzihong
e9107a67c3
fix: fix variable name(entitiy->entity)
2024-12-12 23:59:40 +08:00
Weaxs
288985eab4
pre-commit fix tidb
2024-12-12 10:22:31 +08:00
Weaxs
8ef5a6b8cd
support TiDB: add TiDBKVStorage, TiDBVectorDBStorage
2024-12-11 16:23:50 +08:00
zrguo
504a3c233b
Merge branch 'main' into pkaushal/vectordb-chroma
2024-12-11 14:21:36 +08:00
zrguo
7fbd9aa3e0
Merge pull request #444 from davidleon/fix/lazy_import
...
Fix/lazy import
2024-12-11 14:19:48 +08:00
Magic_yuan
9a2afc9484
style(lightrag): 调整代码格式
2024-12-11 14:06:55 +08:00
Magic_yuan
b89041b5b3
feat(operate): 添加实体类型配置并优化提示生成
...
- 在全局配置中添加 entity_types 参数，用于自定义实体类型
- 在生成实体提取和关系提取的提示时，使用配置的实体类型替代默认值
- 优化了提示生成逻辑，提高了代码的可配置性和灵活性
2024-12-11 13:53:05 +08:00
Magic_yuan
a09e1ba190
refactor(prompt): 优化提示模板以提高相似度评估的准确性- 明确了相似度评分的评判标准，包括不同情况下的评分依据
...
- 简化了评分流程，要求直接返回数字
- 期望通过这些改动提高评估的准确性和一致性
2024-12-11 12:57:58 +08:00
Magic_yuan
0a41cc8a9a
feat(llm, prompt):增加日志输出并扩展实体类型
...
- 在 llm.py 中添加了日志输出，用于调试和记录 LLM 查询输入
- 在 prompt.py 中增加了 "category" 实体类型，扩展了实体提取的范围
2024-12-11 12:45:10 +08:00
Pankaj Kaushal
ca788463cc
feat: Add ChromaDB integration for vector storage
...
- Implemented `ChromaVectorDBStorage` class in `lightrag/kg/chroma_impl.py` to support ChromaDB as a vector storage backend.
- Updated `lightrag.py` to include `ChromaVectorDBStorage` in the storage class mapping.
- Added a test script `test_chromadb.py` to demonstrate the usage of ChromaDB with LightRAG, including configuration for embedding functions and ChromaDB connection settings.
- fix lazy import function to support package context for dynamic class loading.
288d4b8355
2024-12-10 16:23:05 +01:00
david
288d4b8355
fix lazy import
2024-12-10 17:16:21 +08:00
Magic_yuan
316c4df949
更新日志描述
2024-12-10 14:15:43 +08:00
Magic_yuan
58c0f94346
fix(lightrag): 修复只有实体没有关系的chunk处理逻辑
...
- 只有实体没有关系时，继续处理，而不是直接return
- 当只有实体而没有关系的图片在高阶查询关系时会返回空，这里优化返回，当没有关系时降级为local查询
2024-12-10 14:13:11 +08:00
david
21a3992e39
fix extra keyword_extraction.
2024-12-10 09:52:27 +08:00
