yangdx
a8f7b7e2b7
Add "/bypass" mode to skip context retrieval and directly use LLM
...
• Added SearchMode.bypass enum value
• Added /bypass prefix handler
• Skip RAG when in bypass mode
• Pass conversation history to LLM
• Apply bypass mode for both stream/non-stream
2025-02-03 11:49:17 +08:00
zrguo
c07b5522fe
Merge pull request #695 from ShanGor/main
...
Fix the bug from main stream that using doc['status'] and improve Apache AGE performance
2025-02-02 18:27:11 +08:00
zrguo
fade69a2ae
Merge pull request #693 from danielaskdd/fix-concurrent-problem
...
Fixed concurrent problems for document indexing and user query
2025-02-02 18:26:42 +08:00
Samuel Chan
02ac96ff8e
- Fix the bug from main stream that using doc['status']
...
- Improve the performance of Apache AGE.
- Revise the README.md for Apache AGE indexing.
2025-02-02 18:20:32 +08:00
yangdx
7ea1856699
Add comment to clarify LLM cache setting for entity extraction
2025-02-02 07:29:01 +08:00
yangdx
6e1b5d6ce6
Merge branch 'main' into fix-concurrent-problem
2025-02-02 04:36:52 +08:00
yangdx
0a693dbfda
Fix linting
2025-02-02 04:27:55 +08:00
yangdx
ecf48a5be5
Add embedding cache config and disable LLM cache for entity extraction for API Server
2025-02-02 04:27:21 +08:00
yangdx
6f5503ebd6
Update similarity_check prompt to avoid generating two scores sometiimes
2025-02-02 04:22:43 +08:00
yangdx
8484564f50
Fix llm_model_func retrieval error.
2025-02-02 03:54:41 +08:00
yangdx
873b52d2e4
Add debug logging for cache response retrieval
2025-02-02 03:15:43 +08:00
yangdx
fdc9017ded
Set embedding_func in all llm_response_cache
2025-02-02 03:14:07 +08:00
yangdx
bed5a97ae2
Fix prompt respond cache fail when is_embedding_cache_enabled is true
2025-02-02 03:09:06 +08:00
yangdx
5d14ab03eb
Fix linting
2025-02-02 01:56:32 +08:00
yangdx
b45ae1567c
Refactor LLM cache handling and entity extraction
...
- Removed custom LLM function in entity extraction
- Simplified cache handling logic
- Added `force_llm_cache` parameter
- Updated cache handling conditions
2025-02-02 01:28:46 +08:00
yangdx
6c7d7c25d3
Refactor cache handling logic for better readability, keep function unchanged.
2025-02-02 00:10:21 +08:00
yangdx
c9481c81b9
Add cache type "extract" for entity extraction
2025-02-01 23:05:02 +08:00
yangdx
2d387fa6de
Save keywords to cache only when it's no empty
2025-02-01 22:54:23 +08:00
yangdx
3c3cdba499
Fix typo error
2025-02-01 22:27:49 +08:00
yangdx
b87703aea6
Add embedding_func to llm_response_cache
2025-02-01 22:19:16 +08:00
yangdx
3bc7c4d8f1
Save cache_type to llm_response_cache
2025-02-01 22:18:59 +08:00
yangdx
c3942077a9
Use direct embedding_func from hashing_kv (do not by pass maxiumu async control)
2025-02-01 22:12:45 +08:00
yangdx
c98a675b6c
remove unused parm
2025-02-01 22:07:12 +08:00
zrguo
75b5739f81
Merge pull request #689 from ParisNeo/main
...
Use docling for enhanced files loading
2025-02-01 21:39:45 +08:00
zrguo
eafb822344
Merge pull request #688 from TianhongDai/fix-postgres-demo
...
Fix Module Import Bug of PostgresSQL Demo
2025-02-01 21:39:29 +08:00
yangdx
95edf8a51e
Fix linting
2025-02-01 15:22:40 +08:00
yangdx
a0710e9d65
Merge branch 'main' into fix-extract-entity-concurrent-problem
2025-02-01 14:45:42 +08:00
yangdx
b109f57ddd
Refactor async call limiting to use asyncio.Semaphore for better performance.
...
- Replace custom counter with asyncio.Semaphore
- The existing implementation cannot follow the FIFO order
2025-02-01 10:36:25 +08:00
yangdx
635d4fd9e4
Add lock to protect file write operations in NanoVectorDBStorage
...
- Introduce asyncio.Lock for save operations
- Ensure thread-safe file writes
2025-02-01 10:36:25 +08:00
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
