3acbf4d5d1
增加数据库字段，重建知识库使用多线程 ( #1280 )
...
* close #1172 : 给webui_page/utils添加一些log信息，方便定位错误
* 修复：重建知识库时页面未实时显示进度
* skip model_worker running when using online model api such as chatgpt
* 修改知识库管理相关内容:
1.KnowledgeFileModel增加3个字段：file_mtime(文件修改时间),file_size(文件大小),custom_docs(是否使用自定义docs)。为后面比对上传文件做准备。
2.给所有String字段加上长度，防止mysql建表错误(pr#1177)
3.统一[faiss/milvus/pgvector]_kb_service.add_doc接口，使其支持自定义docs
4.为faiss_kb_service增加一些方法，便于调用
5.为KnowledgeFile增加一些方法，便于获取文件信息，缓存file2text的结果。
* 修复/chat/fastchat无法流式输出的问题
* 新增功能：
1、KnowledgeFileModel增加"docs_count"字段，代表该文件加载到向量库中的Document数量，并在WEBUI中进行展示。
2、重建知识库`python init_database.py --recreate-vs`支持多线程。
其它：
统一代码中知识库相关函数用词：file代表一个文件名称或路径，doc代表langchain加载后的Document。部分与API接口有关或含义重叠的函数暂未修改。
---------
Co-authored-by: liunux4odoo <liunux@qq.com>, hongkong9771
2023-08-28 13:50:35 +08:00
96f69edf7b
修复重建知识库界面无反应的问题，添加一些log信息 ( #1258 )
...
* close #1172 : 给webui_page/utils添加一些log信息，方便定位错误
* 修复：重建知识库时页面未实时显示进度
---------
Co-authored-by: liunux4odoo <liunu@qq.com>
2023-08-26 18:26:38 +08:00
c571585ffd
optimize recreate vector store: save vector store once after all docs parsed for FAISS
2023-08-21 08:50:15 +08:00
f40bb69224
优化FAISS向量库多文件操作；修复recreate_vector_store，大量文件时不再超时。
2023-08-20 19:10:29 +08:00
69627a2fa3
update chat and knowledge base api: unify exception processing and return types
2023-08-19 15:14:45 +08:00
67b8ebef52
update api and webui:
...
1. 增加search_docs接口，返回原始知识库检索文档，close #1103
2. 为FAISS检索增加score_threshold参数。milvus和PG暂不支持
2023-08-16 13:18:58 +08:00
cc08e2cb96
update api and webui:
...
1. add download_doc to api
2. return local path or http url in kowledge_base_chat depends on
no_remote_api
3. change assistant avater in webui
2023-08-14 11:46:36 +08:00
2a57f49d80
update knowledge base management ui.
...
remove numpy/pandas from requirements, move them to webui requirements
2023-08-11 13:53:20 +08:00
8a4d9168fa
update import pkgs and format
2023-08-10 21:26:05 +08:00
1b70fb5f9b
update faiss_kb_service.py
2023-08-09 22:57:36 +08:00
997f8b2e3f
update knowledge base api:
...
1. list_kbs_from_db return all kbs by default instead of return kbs with
file_count > 0 only.
2. KBServiceFactory.get_service_by_name could return a FaissKBService
that not in the db
2023-08-09 21:57:40 +08:00
323fc13d4c
make parameter examples available in openapi docs
2023-08-09 18:15:14 +08:00
c7b91bfaf1
update api/kb_doc_api and knowledge base management ui:
...
1. add update_doc to api which can udpate vector store from existed
content file
2. add parameter `delete_content` to delete_doc api. user can decide
whether delete local content file when delete doc.
3. fix bug in ApiReqeust.upload_doc
4. support listing docs existed in local folder bu not in db
2023-08-09 16:52:04 +08:00
b98f5fd0b9
update knowledge base kbservice and api:
...
1. make huggingfaceembeddings hashable
2. unify embeddings' loading method for all kbservie
3. make ApiRequest skip empty content when streaming json to avoid dict
KeyError
2023-08-09 10:46:01 +08:00
135af5f3ff
update knowledge base db orm:
...
1. set default values for file_count, file_version, create_time.
2. fix bug: add_doc_to_db
3. make add_kb_to_db more flexiable with existing kb
2023-08-08 21:47:20 +08:00
2b0f8caa62
improve recreate_vector_store:
...
1. allow empty knowledge base
2. skip unspported files instead of exception
2023-08-08 17:59:41 +08:00
e918244159
move KBServiceFactory to server.knowledge_base.kb_service.base
2023-08-08 17:41:58 +08:00
c4a3995310
move commonto tools from kbservice.base to server.knowledge_base.utils
2023-08-08 16:40:18 +08:00
584e3a9234
remove server/knowledge_base/knowledge_base_factory.py
2023-08-08 16:21:00 +08:00
44c713ef98
use KBServiceFactory to replace all the KnowledgeBase.
...
make KBServiceFactory support embed_model parameter.
rewrite api: recreate_vector_store.
fix some bugs.
2023-08-07 20:37:16 +08:00
b91d96ab0c
update kb_doc_api.py
2023-08-06 18:32:10 +08:00
a447529c2e
update kb_doc_api.py
2023-08-05 23:35:20 +08:00
7f89efee4b
fix kb_doc_api.py
2023-08-05 23:01:56 +08:00
3f045cedb9
1. add add_doc and list_docs to KnowledgeBase class
...
2. add DB_ROOT_PATH to model_config.py.example
2023-08-05 22:57:19 +08:00
206261cd0c
update class method of KnowledgeBase and KnowledgeFile
2023-08-05 13:46:00 +08:00
590367a5b5
add KnowledgeFile class
2023-08-04 23:54:26 +08:00
bc3ee83910
update kb_doc_api.py
2023-08-04 22:22:48 +08:00
5d1a0ec15d
add recreate_vector_store to kb_doc_api, and the router in api.py.
2023-08-04 20:26:14 +08:00
46c7d8d169
allow kb_doc_api.upload_doc to override existed file by parameter.
...
update_doc is not needed.
2023-08-04 15:53:44 +08:00
7bfbe18011
update requirements.txt and kb_doc_api.py
2023-08-04 15:12:14 +08:00
88682c87ff
优化server下知识库相关模块的结构：将知识库相关操作从knowledge_base_chat移动到knowledge_base.utils；优化kb_doc_api中embeddings加载。
2023-08-04 10:16:30 +08:00
dcf49a59ef
v0.2.0 first commit
2023-07-27 23:22:07 +08:00
liunux4odoo
liunux4odoo
imClumsyPanda
liunux4odoo