yangdx
6a326e2783
Revert "Refactor embedding functions and add async query limit"
...
This reverts commit 21481dba8f
2025-02-01 10:36:25 +08:00
yangdx
2ba36f87e3
Add support for list input in quantize_embedding function
...
- Convert list to numpy array if needed
- Maintain existing functionality
2025-02-01 10:36:25 +08:00
yangdx
1192727be7
remove semaphore logic from EmbeddingFunc(cause num of instances is already control by limit_async_func_call)
2025-02-01 10:36:25 +08:00
yangdx
60b66b95e3
Fix typo in prompt
2025-02-01 10:36:25 +08:00
yangdx
0692635ebd
Improve prompts to avoid make-up respond from LLM like qwen-plus when very long context is provided.
2025-02-01 10:36:25 +08:00
yangdx
b22a8b216c
Fix linting
2025-02-01 10:36:25 +08:00
yangdx
2a010c985e
Add logging for chunk truncation in mix_kg_vector_query
2025-02-01 10:36:25 +08:00
Saifeddine ALOUI
3a40772d30
Simplified file loading
2025-02-01 01:19:32 +01:00
Saifeddine ALOUI
e09cb85f37
fixed linting as well as file path
2025-02-01 01:15:06 +01:00
Saifeddine ALOUI
ef35f9a4e4
Introduced docling instead of other tools for loading files
2025-02-01 00:56:43 +01:00
Tianhong Dai
5dda38eeb9
fix import bugs of postgres example
2025-01-31 17:13:21 +00:00
Saifeddine ALOUI
e24a0a86e5
Update requirements.txt
2025-01-31 17:12:10 +01:00
zrguo
e59cb7493c
fixed linting
2025-01-31 23:35:42 +08:00
zrguo
58a9ae2f83
Merge pull request #686 from gurjot-05/main
...
Implement Faiss Vector Storage Support for LightRAG
2025-01-31 23:34:53 +08:00
zrguo
a3f2a3f1de
Merge pull request #682 from ParisNeo/main
...
Few upgrades in the webui
2025-01-31 23:33:28 +08:00
zrguo
470b39930c
Merge pull request #681 from danielaskdd/Improve-prompt-prevent-make-up-answer
...
Improve prompts to avoid LLM make up answer
2025-01-31 23:32:54 +08:00
Saifeddine ALOUI
78b858c03b
Finished testing api key
2025-01-31 16:19:46 +01:00
Saifeddine ALOUI
d2a550fd31
Update api.js
2025-01-31 16:08:23 +01:00
Saifeddine ALOUI
d1210851aa
Update api.js
2025-01-31 16:07:27 +01:00
Saifeddine ALOUI
e9591548b4
Update api.js
2025-01-31 16:03:31 +01:00
Gurjot Singh
2894e8faf2
Fix linting errors
2025-01-31 19:05:47 +05:30
Gurjot Singh
8a624e198a
Add faiss integration for storage
2025-01-31 19:00:36 +05:30
yangdx
2d4991dfbd
Fix typo in prompt
2025-01-31 20:40:37 +08:00
Saifeddine ALOUI
2444975bf1
Update api.js
2025-01-31 13:22:19 +01:00
Saifeddine ALOUI
6889606a48
Update lightrag_server.py
2025-01-31 11:19:12 +01:00
yangdx
b0d87b2e29
Fix linting
2025-01-31 15:33:50 +08:00
yangdx
389f4ee872
Shorten log message for cosine similarity threshold.
2025-01-31 15:33:41 +08:00
yangdx
21481dba8f
Refactor embedding functions and add async query limit
...
- Separate insert/query embedding funcs
- Add query-specific async limit
- Update storage classes to use new funcs
- Protect vector DB save with lock
- Improve config handling for thresholds
2025-01-31 15:00:56 +08:00
Saifeddine ALOUI
381f7deec6
linting
2025-01-30 23:29:21 +01:00
Saifeddine ALOUI
219cbab1e3
Added progress when scanning files and fixed some bugs in the API
2025-01-30 23:27:43 +01:00
yangdx
54b68074a1
Merge branch 'main' into fix-extract-entity-concurrent-problem
2025-01-31 01:19:44 +08:00
yangdx
fb63e5ed39
Improve prompts to avoid make-up respond from LLM like qwen-plus when very long context is provided.
2025-01-30 22:38:32 +08:00
yangdx
601f10b132
Fix linting
2025-01-30 22:26:28 +08:00
yangdx
82460088da
Merge commit '59617da83e224e3af1c97fb21dd661b088effc2d' into Improve-prompt-prevent-make-up-answer
2025-01-30 22:24:13 +08:00
yangdx
81655829bc
Add logging for chunk truncation in mix_kg_vector_query
2025-01-30 22:21:52 +08:00
zrguo
59617da83e
Merge pull request #675 from danielaskdd/Fix-get_conversation_turns
...
Fix get conversation turns
2025-01-30 20:36:59 +08:00
zrguo
9ef1438ff6
Merge pull request #674 from danielaskdd/topk-cosine-threshold-env-config
...
Add top_k and cosine_better_than_threshold support for API server
2025-01-30 20:36:44 +08:00
yangdx
e31482e49b
Merge commit '5d3060dfa56b5e9f149f170a76db874ce8ca6ffb' into Improve-prompt-prevent-make-up-answer
2025-01-30 13:42:04 +08:00
yangdx
5d3060dfa5
Refactor configuration and conversation history handling of unit test code
...
- Add DEFAULT_CONFIG constant
- Introduce EXAMPLE_CONVERSATION
- Remove redundant DEFAULT_CONFIG
- Simplify chat request creation
- Update tests to use shared history
2025-01-30 13:12:19 +08:00
yangdx
3150c2812f
Fix loop step from 1 to 2 in get_conversation_turns, ensure user-assistant pairing
2025-01-30 13:08:27 +08:00
yangdx
cc50ade14e
Fix concurrent problem on extract_entities function.
...
- Abandon the approach of temporarily replacing the global llm_model_func configuration
- Introduce custom_llm function with new_config for handle_cache while extracting entities
- Update handle_cache to accept custom_llm
2025-01-30 02:45:33 +08:00
yangdx
06647438b2
Refactor threshold handling to use environment variables and global config settings for oracle, postgres and tidb
2025-01-29 23:47:57 +08:00
yangdx
46c9c7d95b
Update sample env file and documentation
...
- Change COSINE_THRESHOLD to 0.4
- Adjust TOP_K to 50
- Enhance API README details
2025-01-29 23:45:20 +08:00
yangdx
e29682eef8
Allow configuration of LLM parameters through environment variables
2025-01-29 23:39:47 +08:00
yangdx
20d6355a4a
Fix cosine threshold parameter setting error for chroma
2025-01-29 22:41:18 +08:00
yangdx
90c765c724
Fix linting
2025-01-29 22:14:18 +08:00
yangdx
5c7b2d7c9f
Merge from main
2025-01-29 22:13:01 +08:00
yangdx
c8b890547a
Add logging for query parameters in NanoVectorDBStorage.query
2025-01-29 21:36:31 +08:00
yangdx
7ff8c7b9d8
Add timeout parameter to OpenAI alike LLM model configuration
2025-01-29 21:35:46 +08:00
yangdx
7aedc08caf
Add RAG configuration options and enhance parameter configurability
...
- Add top-k and cosine-threshold parms for api server
- Update .env and cli parms handling with new parameters
- Improve splash screen display
- Update bash and storage classes to read new parameters from .env file.
2025-01-29 21:34:34 +08:00
