Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

OPEA Triage Tool for ChatQnA #1185

Open
wants to merge 9 commits into
base: main
Choose a base branch
from
+960 −1
Open

OPEA Triage Tool for ChatQnA #1185

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
2698276
First Draft of OPEA Triage Tool
louie-tsai Nov 20, 2024
e3bb7cb
Update ChatQnA/tests/ChatQnA_Xeon.json
louie-tsai Dec 4, 2024
47c64b0
fix some health check issues
louie-tsai Dec 6, 2024
cdaa391
first draft for profiling feature
louie-tsai Dec 7, 2024
5035eda
enable vllm profiling for Triage Tool
louie-tsai Dec 9, 2024
9424f00
add Gaudi support
louie-tsai Dec 9, 2024
efa43a2
add vllm support
louie-tsai Dec 10, 2024
da12881
add AIPC, NVGPU, AMD Rocm support
louie-tsai Dec 10, 2024
ad12531
move Triage Tool into parent folder of OPEA Examples github repo
louie-tsai Dec 11, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
502 changes: 502 additions & 0 deletions .Triage.py
View file
Open in desktop

Large diffs are not rendered by default.

1 change: 0 additions & 1 deletion ChatQnA/docker_compose/intel/cpu/xeon/set_env.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,6 @@
pushd "../../../../../" > /dev/null
source .set_env.sh
popd > /dev/null

export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
export RERANK_MODEL_ID="BAAI/bge-reranker-base"
export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
Expand Down
71 changes: 71 additions & 0 deletions ChatQnA/tests/ChatQnA_AIPC.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,71 @@
{
"ChatQnA_AIPC": [
{
"service": "env",
"port": "",
"endpoint": "",
"EMBEDDING_MODEL_ID": true,
"RERANK_MODEL_ID": true,
"OLLAMA_MODEL": true,
"OLLAMA_HOST": true,
"INDEX_NAME": true,
"HUGGINGFACEHUB_API_TOKEN": true,
"http_proxy": false,
"https_proxy": false,
"no_proxy": false,
"output": false
},
{
"service": "embed",
"port": "6006",
"endpoint": "embed",
"inputs": "What is Deep Learning?",
"output": "[["
},
{
"service": "dataprep",
"port": "6007",
"endpoint": "/v1/dataprep",
"file_path": "",
"output": "Data preparation succeeded"
},
{
"service": "retrieval",
"port": "7000",
"endpoint": "/v1/retrieval",
"text": "test",
"embedding": "",
"output": "retrieved_docs"
},
{
"service": "rerank",
"port": "8808",
"endpoint": "rerank",
"query": "What is Deep Learning?",
"texts": ["Deep Learning is not...", "Deep learning is..."],
"output": "index"
},
{
"service": "llm",
"port": "11434",
"endpoint": "api/generate",
"model": "llama3.2",
"prompt": "What is Deep Learning?",
"output": "generated_text"
},
{
"service": "nginx",
"port": "80",
"endpoint": "v1/chatqna",
"messages": "What is the revenue of Nike in 2023?",
"output": "data: "
},
{
"service": "mega",
"port": "8888",
"endpoint": "v1/chatqna",
"messages": "What is the revenue of Nike in 2023?",
"output": "data: "
}
]
}
70 changes: 70 additions & 0 deletions ChatQnA/tests/ChatQnA_Gaudi.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,70 @@
{
"ChatQnA_Xeon": [
{
"service": "env",
"port": "",
"endpoint": "",
"EMBEDDING_MODEL_ID": true,
"RERANK_MODEL_ID": true,
"LLM_MODEL_ID": true,
"INDEX_NAME": true,
"HUGGINGFACEHUB_API_TOKEN": true,
"http_proxy": false,
"https_proxy": false,
"no_proxy": false,
"output": false
},
{
"service": "embed",
"port": "8090",
"endpoint": "embed",
"inputs": "What is Deep Learning?",
"output": "[["
},
{
"service": "dataprep",
"port": "6007",
"endpoint": "/v1/dataprep",
"file_path": "",
"output": "Data preparation succeeded"
},
{
"service": "retrieval",
"port": "7000",
"endpoint": "/v1/retrieval",
"text": "test",
"embedding": "",
"output": "retrieved_docs"
},
{
"service": "rerank",
"port": "8808",
"endpoint": "rerank",
"query": "What is Deep Learning?",
"texts": ["Deep Learning is not...", "Deep learning is..."],
"output": "index"
},
{
"service": "llm",
"port": "8005",
"endpoint": "v1/chat/completions",
"model": "Intel/neural-chat-7b-v3-3",
"messages": [{ "role": "user", "content": "What is Deep Learning?" }],
"output": "generated_text"
},
{
"service": "nginx",
"port": "80",
"endpoint": "v1/chatqna",
"messages": "What is the revenue of Nike in 2023?",
"output": "data: "
},
{
"service": "mega",
"port": "8888",
"endpoint": "v1/chatqna",
"messages": "What is the revenue of Nike in 2023?",
"output": "data: "
}
]
}
70 changes: 70 additions & 0 deletions ChatQnA/tests/ChatQnA_Gaudi_vllm.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,70 @@
{
"ChatQnA_Xeon": [
{
"service": "env",
"port": "",
"endpoint": "",
"EMBEDDING_MODEL_ID": true,
"RERANK_MODEL_ID": true,
"LLM_MODEL_ID": true,
"INDEX_NAME": true,
"HUGGINGFACEHUB_API_TOKEN": true,
"http_proxy": false,
"https_proxy": false,
"no_proxy": false,
"output": false
},
{
"service": "embed",
"port": "8090",
"endpoint": "embed",
"inputs": "What is Deep Learning?",
"output": "[["
},
{
"service": "dataprep",
"port": "6007",
"endpoint": "/v1/dataprep",
"file_path": "",
"output": "Data preparation succeeded"
},
{
"service": "retrieval",
"port": "7000",
"endpoint": "/v1/retrieval",
"text": "test",
"embedding": "",
"output": "retrieved_docs"
},
{
"service": "rerank",
"port": "8808",
"endpoint": "rerank",
"query": "What is Deep Learning?",
"texts": ["Deep Learning is not...", "Deep learning is..."],
"output": "index"
},
{
"service": "llm",
"port": "8007",
"endpoint": "v1/chat/completions",
"model": "Intel/neural-chat-7b-v3-3",
"messages": [{ "role": "user", "content": "What is Deep Learning?" }],
"output": "generated_text"
},
{
"service": "nginx",
"port": "80",
"endpoint": "v1/chatqna",
"messages": "What is the revenue of Nike in 2023?",
"output": "data: "
},
{
"service": "mega",
"port": "8888",
"endpoint": "v1/chatqna",
"messages": "What is the revenue of Nike in 2023?",
"output": "data: "
}
]
}
82 changes: 82 additions & 0 deletions ChatQnA/tests/ChatQnA_NVGPU.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,82 @@
{
"ChatQnA_NVGPU": [
{
"service": "env",
"port": "",
"endpoint": "",
"EMBEDDING_MODEL_ID": true,
"RERANK_MODEL_ID": true,
"LLM_MODEL_ID": true,
"INDEX_NAME": true,
"HUGGINGFACEHUB_API_TOKEN": true,
"TEI_EMBEDDING_ENDPOINT": true,
"MEGA_SERVICE_HOST_IP": true,
"RETRIEVER_SERVICE_HOST_IP": true,
"BACKEND_SERVICE_ENDPOINT": true,
"DATAPREP_SERVICE_ENDPOINT": true,
"DATAPREP_GET_FILE_ENDPOINT": true,
"DATAPREP_DELETE_FILE_ENDPOINT": true,
"FRONTEND_SERVICE_IP": true,
"FRONTEND_SERVICE_PORT": true,
"BACKEND_SERVICE_NAME": true,
"BACKEND_SERVICE_IP": true,
"BACKEND_SERVICE_PORT": true,
"http_proxy": false,
"https_proxy": false,
"no_proxy": false,
"output": false
},
{
"service": "embed",
"port": "8090",
"endpoint": "embed",
"inputs": "What is Deep Learning?",
"output": "[["
},
{
"service": "dataprep",
"port": "6007",
"endpoint": "/v1/dataprep",
"file_path": "",
"output": "Data preparation succeeded"
},
{
"service": "retrieval",
"port": "7000",
"endpoint": "/v1/retrieval",
"text": "test",
"embedding": "",
"output": "retrieved_docs"
},
{
"service": "rerank",
"port": "8808",
"endpoint": "rerank",
"query": "What is Deep Learning?",
"texts": ["Deep Learning is not...", "Deep learning is..."],
"output": "index"
},
{
"service": "llm",
"port": "8008",
"endpoint": "v1/chat/completions",
"model": "Intel/neural-chat-7b-v3-3",
"messages": [{ "role": "user", "content": "What is Deep Learning?" }],
"output": "generated_text"
},
{
"service": "nginx",
"port": "80",
"endpoint": "v1/chatqna",
"messages": "What is the revenue of Nike in 2023?",
"output": "data: "
},
{
"service": "mega",
"port": "8888",
"endpoint": "v1/chatqna",
"messages": "What is the revenue of Nike in 2023?",
"output": "data: "
}
]
}
Loading
Loading