Commit Graph

45 Commits

Author SHA1 Message Date
imClumsyPanda 20eef45a58 update README.md 2023-09-15 09:53:58 +08:00
imClumsyPanda 17985c7f8e update splitter.md 2023-09-14 22:24:58 +08:00
zR 769d75d784
修复测试文件 (#1467)
Co-authored-by: zR <zRzRzRzRzRzRzR>
2023-09-13 17:12:05 +08:00
zR bfdbe69fa1
增加了自定义分词器适配 (#1462)
* 添加了自定义分词器适配和测试文件
---------

Co-authored-by: zR <zRzRzRzRzRzRzR>
2023-09-13 15:42:12 +08:00
mz 78e79af68b
update INSTALL.md (#1250)
Co-authored-by: zzflybird <cmz1@qq.com>
2023-08-26 12:30:54 +08:00
zqt b3450bfc96 添加milvus 和 pg QA说明 2023-08-20 18:03:23 +08:00
imClumsyPanda e196ef0b17 update docs 2023-08-12 17:04:38 +08:00
imClumsyPanda 18fe1b97f9 merge dev_fastchat 2023-08-12 16:30:07 +08:00
imClumsyPanda 8c289e4974 update README.md 2023-08-12 11:21:29 +08:00
liunux4odoo 802ddb7b55 update docs 2023-08-11 23:30:07 +08:00
liunux4odoo 22c8f277bf update readme: describe requirements to install 2023-08-10 17:10:40 +08:00
zqt d4f728dfa2 添加向量数据库pg支持,和向量库docker-compose.ym环境文件 2023-08-10 11:16:52 +08:00
imClumsyPanda 22260af16f update README.md and INSTALL.md 2023-08-09 22:04:28 +08:00
YikunHan 0ad63aee63
Update FAQ.md (#1006) 2023-08-06 16:39:58 +08:00
imClumsyPanda dcf49a59ef v0.2.0 first commit 2023-07-27 23:22:07 +08:00
YuhaoWU 466f0c9c97
安装教程conda create新增默认的/envs下面,而不只是只能要额外指定路径 用-p (#482)
* Update 安装教程中conda虚拟环境的创建与激活
2023-07-25 16:58:25 +08:00
imClumsyPanda 0f43845a98 merge master 2023-07-23 18:38:51 +08:00
Ma Zhiming 3f76cb5f47
[Fix] INSTALL.md (#907)
* Update INSTALL.md

* Update INSTALL.md
2023-07-21 16:42:53 +08:00
hzg0601 50c872c0b8 update faq for 2023-07-19 23:09:19 +08:00
hzg0601 3d082bf566 在FAQ中给出加载量化版本失败的原因和解决方案 2023-07-14 13:45:07 +08:00
Zhi-guo Huang a5ca4bf26a
1.增加对llama-cpp模型的支持;2.增加对bloom/chatyuan/baichuan模型的支持;3. 修复多GPU部署的bug;4. 修复了moss_llm.py的bug;5. 增加对openai支持(没有api,未测试);6. 支持在多卡情况自定义设备GPU (#664)
* 修复 bing_search.py的typo;更新model_config.py中Bing Subscription Key申请方式及注意事项

* 更新FAQ,增加了[Errno 110] Connection timed out的原因与解决方案

* 修改loader.py中load_in_8bit失败的原因和详细解决方案

* update loader.py

* stream_chat_bing

* 修改stream_chat的接口,在请求体中选择knowledge_base_id;增加stream_chat_bing接口

* 优化cli_demo.py的逻辑:支持 输入提示;多输入;重新输入

* update cli_demo.py

* add bloom-3b,bloom-7b1,ggml-vicuna-13b-1.1

* 1.增加对llama-cpp模型的支持;2.增加对bloom模型的支持;3. 修复多GPU部署的bug;4. 增加对openai支持(没有api,未测试);5.增加了llama-cpp模型部署的说明

* llama模型兼容性说明

* modified:   ../configs/model_config.py
	modified:   ../docs/INSTALL.md
在install.md里增加对llama-cpp模型调用的说明

* 修改llama_llm.py以适应llama-cpp模型

* 完成llama-cpp模型的支持;

* make fastchat and openapi compatiable

* 1. 修复/增加对chatyuan,bloom,baichuan-7等模型的支持;2. 修复了moss_llm.py的bug;

* set default model be chatglm-6b

* 在多卡情况下也支持自定义GPU设备

---------

Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
2023-07-11 19:36:50 +08:00
Fan 10abb8d781
添加启动API的参数,支持https、wss方式API调用 (#728)
* update README.md

* 添加启动API的参数,支持https、wss方式API调用。(CA证书自备)
添加启动API服务的markdown说明文档。

---------

Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
Co-authored-by: 一帆 <zhang.f@digitalcnzz.com>
2023-07-04 19:52:17 +08:00
Zhi-guo Huang a70df98825
更新FAQ,model_config.py,bing_search.py文件,增加bing搜索问答相关问题的原因和可能解决方案,修复了一些typo;修改loader.py中load_in_8bit失败的原因和详细解决方案 (#610)
* 修复 bing_search.py的typo;更新model_config.py中Bing Subscription Key申请方式及注意事项

* 更新FAQ,增加了[Errno 110] Connection timed out的原因与解决方案

* 修改loader.py中load_in_8bit失败的原因和详细解决方案

* update loader.py
2023-06-14 21:31:26 +08:00
Zhi-guo Huang 27a9bf2433
更新FAQ和requirements,解决upload_file接口的两个异常 (#593) 2023-06-11 21:25:02 +08:00
imClumsyPanda 20f1daff1a add fastchat.md 2023-05-31 22:50:35 +08:00
imClumsyPanda 99e9d1d730 update FAQ.md 2023-05-31 21:13:21 +08:00
imClumsyPanda 06f6e1913e merge master 2023-05-22 00:24:07 +08:00
imClumsyPanda e352a04cbb merge master 2023-05-22 00:18:48 +08:00
glide-the d9cc4e918c
Update INSTALL.md 2023-05-19 11:04:28 +08:00
glide-the 4c008c25d4 增加项目可选启动项说明、增加项目结构说明
cli_demo.py、api.py: 兼容loader加载器
2023-05-18 22:55:50 +08:00
CHANGXUBO a5417e1cf5
更新install说明,解决PaddleOCR依赖问题 (#387) 2023-05-17 13:28:10 +08:00
zqt996 a0cb14de23
添加命令行管理脚本 (#355)
* 添加加命令行工具

* 添加加命令行工具

---------

Co-authored-by: zqt <1178747941@qq.com>
Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
2023-05-15 19:13:12 +08:00
imClumsyPanda 1a1989d860 update README.md 2023-05-13 11:24:06 +08:00
zhenkaivip d2716addd6
使用paddleocr实现实现UnstructuredPaddlePDFLoader和UnstructuredPaddleImageLoader (#344)
* jpg and png ocr

* fix

* write docs to tmp file

* fix

* image loader

* fix

* fix

* add pdf_loader

* fix

* update INSTALL.md

---------

Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
2023-05-13 11:13:40 +08:00
imClumsyPanda 6e23253013 update pdf_loader.py and image_loader.py 2023-05-13 09:50:30 +08:00
zhenkaivip dd93837343
使用paddleocr实现 (#342)
* jpg and png ocr

* fix

* write docs to tmp file

* fix

* [BUGFIX] local_doc_qa.py line 172: logging have no end args. (#323)

* image loader

* fix

* fix

* update api.py

* update api.py

* update api.py

* update README.md

* update api.py

* add pdf_loader

* fix

---------

Co-authored-by: RainGather <3255329+RainGather@users.noreply.github.com>
Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
2023-05-13 08:45:17 +08:00
miller 09f57741fa
Update INSTALL.md (#223) 2023-05-04 13:34:01 +08:00
imClumsyPanda b03634fb7c add api.py 2023-05-03 22:35:05 +08:00
Bing Han e0cf26019b
Use fastapi to implement API (#209)
* Use fastapi to implement API

* Update model_config.py

---------

Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
2023-05-03 21:29:28 +08:00
imClumsyPanda 634c0c19d8 update FAQ.md 2023-04-21 21:36:23 +08:00
imClumsyPanda d35eb12078 Update FAQ.md 2023-04-20 21:53:48 +08:00
dong 4b2a597e12 新增处理"OutOfMemoryError: CUDA out of memory"和"Resource averaged_perceptron_tagger not found"的方法 2023-04-20 21:53:48 +08:00
imClumsyPanda 57d78bd1f6 update README.md 2023-04-18 19:59:07 +08:00
Calcitem 2af0606221 Update docs 2023-04-14 01:49:15 +08:00
zmf b6248f1e77 增加项目环境说明,环境问题解答 2023-04-14 00:38:45 +08:00