Commit Graph

57 Commits

Author SHA1 Message Date
FangYin Cheng
581cf361bf feat(model): multi-model supports embedding model and simple component design implementation 2023-09-13 12:14:21 +08:00
FangYin Cheng
986ada3aeb feat(model): supports the deployment of multiple models through the API and add the corresponding command line interface 2023-09-11 17:15:20 +08:00
FangYin Cheng
f19551a7cd feat: Optimize code import time 2023-09-01 10:40:18 +08:00
FangYin Cheng
d467092766 merge multi-model and ChatExcel 2023-08-29 22:54:18 +08:00
csunny
5f53463221 fix: gpt4all output bug 2023-08-23 16:47:59 +08:00
FangYin Cheng
3f6e9687ee feat: Support windows
fix: Fix install error on linux

doc: Add torch cuda FAQ
2023-08-22 14:35:11 +08:00
FangYin Cheng
b5fd5d2a3a feat: Support llama.cpp 2023-08-15 19:00:08 +08:00
FangYin Cheng
a4574aa614 feat: Support vicuna-v1.5 and WizardLM-v1.2 2023-08-03 14:14:29 +08:00
FangYin Cheng
bceb609cf6 feat: Modify config for quantization and doc 2023-08-02 19:29:59 +08:00
FangYin Cheng
d8a4b776d5 feat: Support 8-bit quantization and 4-bit quantization for multi-gpu inference 2023-08-02 19:29:59 +08:00
FangYin Cheng
35d0c17ae8 feat: Support baichuan-7B model 2023-07-25 19:48:21 +08:00
FangYin Cheng
01074660bc feat: Support baichuan-13B model 2023-07-25 19:48:21 +08:00
FangYin Cheng
168c754a3f feat: Support llama-2 model 2023-07-20 21:44:40 +08:00
FangYin Cheng
d805e6ab42 feat: structured prompt data interaction between dbgpt-server and llm-server 2023-07-19 12:10:22 +08:00
aries_ckt
eb31d5523e doc:update dbgpt_demo.mp4
1.update dbgpt_demo.mp4
2.format code
2023-07-06 13:47:46 +08:00
tuyang.yhj
02b51291b7 Merge remote-tracking branch 'origin/new-page-framework' into dev_ty_06_end
# Conflicts:
#	pilot/server/webserver.py
2023-07-03 22:17:03 +08:00
tuyang.yhj
be8ead568a WEB API independent 2023-07-03 21:26:53 +08:00
tuyang.yhj
85d834d5b4 WEB API independent 2023-07-03 18:37:25 +08:00
aries_ckt
cdb616cc21 style:format code style
format code style
2023-06-29 13:52:53 +08:00
tuyang.yhj
caa1a41065 Merge branch 'llm_framework' into dev_ty_06_end
# Conflicts:
#	pilot/memory/chat_history/duckdb_history.py
#	pilot/openapi/api_v1/api_v1.py
#	pilot/scene/base.py
#	pilot/scene/base_chat.py
#	pilot/scene/chat_execution/example.py
2023-06-28 11:40:22 +08:00
tuyang.yhj
820214faa8 WEB API independent 2023-06-28 11:34:40 +08:00
aries_ckt
682b1468d1 style:format code
format code
2023-06-27 22:20:21 +08:00
aries_ckt
57da3c23a6 feat: knowledge backend management
1.knowledge_type.py
2.knowledge backend api
2023-06-27 15:29:13 +08:00
aries_ckt
91d6edc4eb feat: knowledge management backend api
1.create knowledge space
2.list knowledge space
3.create knowledge document
4.list knowledge document
5.save document chunks
6.sync embedding document
2023-06-26 15:24:25 +08:00
tuyang.yhj
d372e73cd5 WEB API independent 2023-06-25 14:46:46 +08:00
LBYPatrick
0b1d54afa6 chore: run black against modified code 2023-06-16 12:23:28 +08:00
LBYPatrick
1580aaa8eb chore: bump requirement.txt for guanaco support 2023-06-16 11:45:42 +08:00
magic.chen
f19b92af02 Update llmserver.py 2023-06-14 22:52:26 +08:00
csunny
d0b270cb95 fix: async output 2023-06-14 22:02:23 +08:00
csunny
4f82cfde63 pylint: multi model for gp4all (#138) 2023-06-14 10:17:53 +08:00
csunny
0f4569e5c8 Merge branch 'dbgpt_doc' into llm_fxp 2023-06-14 10:14:13 +08:00
csunny
1f78c21c08 debug: more detail error info 2023-06-13 19:46:03 +08:00
sheri528
5da4b38964 format code 2023-06-13 14:22:55 +08:00
sheri528
a88e8aa51b update stream output 2023-06-13 14:11:23 +08:00
xuyuan23
6e3b48c7c4 support multi process to launch llmserver, add openai proxy api. 2023-06-12 21:29:16 +08:00
ykgong
cacab625cf rm log 2023-06-09 11:39:51 +08:00
ykgong
545c323216 add gpt4all 2023-06-09 11:35:06 +08:00
yhjun1026
661a7b5697 model server fix message model 2023-06-01 16:34:51 +08:00
csunny
16c6986666 fix: lint 2023-05-30 19:11:34 +08:00
csunny
ea334b172e feature: add model server proxy 2023-05-30 17:16:29 +08:00
yihong0618
b098a48898 ci: make ci happy lint the code, delete unused imports
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2023-05-24 18:43:04 +08:00
csunny
89970bd71c llms: add cpu support 2023-05-21 16:05:53 +08:00
csunny
ce72820085 llms: add mps support 2023-05-21 14:48:54 +08:00
csunny
42b76979a3 llms: multi model support 2023-05-21 11:22:56 +08:00
csunny
8e127b3863 llms: add chatglm 2023-05-21 10:13:59 +08:00
csunny
cbf1d0662a llms: add models 2023-05-20 16:06:32 +08:00
hyj1991
67f5bbc96a feat: support customizing port for llmserver 2023-05-19 22:33:50 +08:00
csunny
9ddd089381 fix run path 2023-05-18 17:28:06 +08:00
yhjun1026
ba7e23d37f Unified configuration 2023-05-18 16:30:57 +08:00
csunny
7ee0805eff fix 2023-05-13 23:43:05 +08:00