Skip to content

Commit 2b040c0

Browse files
alexsin368alexsin368
committed
2 parents 8cc38df + a6e9984 commit 2b040c0

File tree

321 files changed

+4694
-2065
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

321 files changed

+4694
-2065
lines changed

‎.github/code_spell_ignore.txt‎

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,4 @@
11
ModelIn
22
modelin
3-
pressEnter
3+
pressEnter
4+
PromptIn

‎.github/env/_build_image.sh‎

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,6 @@
1+
#!/bin/bash
12
# Copyright (C) 2025 Intel Corporation
23
# SPDX-License-Identifier: Apache-2.0
34

4-
export VLLM_VER=v0.8.3
5+
export VLLM_VER=v0.9.0.1
56
export VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0

‎.github/workflows/_gmc-e2e.yml‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -56,7 +56,7 @@ jobs:
5656
- name: Run tests
5757
id: run-test
5858
env:
59-
HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
59+
HF_TOKEN: ${{ secrets.HF_TOKEN }}
6060
GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
6161
GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
6262
run: |

‎.github/workflows/_run-docker-compose.yml‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -170,8 +170,8 @@ jobs:
170170
- name: Run test
171171
shell: bash
172172
env:
173-
HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
174-
HF_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
173+
HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HF_TOKEN }}
174+
HF_TOKEN: ${{ secrets.HF_TOKEN }}
175175
GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
176176
GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
177177
PINECONE_KEY: ${{ secrets.PINECONE_KEY }}

‎.set_env.sh‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,4 @@
1+
#!/bin/bash
12
# Copyright (C) 2024 Intel Corporation
23
# SPDX-License-Identifier: Apache-2.0
34
#

‎AgentQnA/README.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -123,7 +123,7 @@ Set up a [HuggingFace](https://huggingface.co/) account and generate a [user acc
123123
Then set an environment variable with the token and another for a directory to download the models:
124124

125125
```bash
126-
export HUGGINGFACEHUB_API_TOKEN=<your-HF-token>
126+
export HF_TOKEN=<your-HF-token>
127127
export HF_CACHE_DIR=<directory-where-llms-are-downloaded> # to avoid redownloading models
128128
```
129129

‎AgentQnA/docker_compose/amd/gpu/rocm/README.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -170,7 +170,7 @@ Use AMD GPU driver utilities to determine the correct `cardN` and `renderN` IDs
170170
### Replace the string 'server_address' with your local server IP address
171171
export host_ip='server_address'
172172
### Replace the string 'your_huggingfacehub_token' with your HuggingFacehub repository access token.
173-
export HUGGINGFACEHUB_API_TOKEN='your_huggingfacehub_token'
173+
export HF_TOKEN='your_huggingfacehub_token'
174174
### Replace the string 'your_langchain_api_key' with your LANGCHAIN API KEY.
175175
export LANGCHAIN_API_KEY='your_langchain_api_key'
176176
export LANGCHAIN_TRACING_V2=""

‎AgentQnA/docker_compose/amd/gpu/rocm/compose.yaml‎

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -13,8 +13,8 @@ services:
1313
http_proxy: ${http_proxy}
1414
https_proxy: ${https_proxy}
1515
TGI_LLM_ENDPOINT: "http://${ip_address}:${TGI_SERVICE_PORT}"
16-
HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
17-
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
16+
HUGGING_FACE_HUB_TOKEN: ${HF_TOKEN}
17+
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
1818
shm_size: 32g
1919
devices:
2020
- /dev/kfd:/dev/kfd
@@ -42,7 +42,7 @@ services:
4242
with_memory: false
4343
recursion_limit: ${recursion_limit_worker}
4444
llm_engine: tgi
45-
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
45+
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
4646
llm_endpoint_url: ${LLM_ENDPOINT_URL}
4747
model: ${LLM_MODEL_ID}
4848
temperature: ${temperature}
@@ -76,7 +76,7 @@ services:
7676
use_hints: false
7777
recursion_limit: ${recursion_limit_worker}
7878
llm_engine: vllm
79-
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
79+
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
8080
llm_endpoint_url: ${LLM_ENDPOINT_URL}
8181
model: ${LLM_MODEL_ID}
8282
temperature: ${temperature}
@@ -104,7 +104,7 @@ services:
104104
with_memory: true
105105
recursion_limit: ${recursion_limit_supervisor}
106106
llm_engine: tgi
107-
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
107+
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
108108
llm_endpoint_url: ${LLM_ENDPOINT_URL}
109109
model: ${LLM_MODEL_ID}
110110
temperature: ${temperature}

‎AgentQnA/docker_compose/amd/gpu/rocm/compose_vllm.yaml‎

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -10,8 +10,8 @@ services:
1010
no_proxy: ${no_proxy}
1111
http_proxy: ${http_proxy}
1212
https_proxy: ${https_proxy}
13-
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
14-
HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
13+
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
14+
HF_TOKEN: ${HF_TOKEN}
1515
HF_HUB_DISABLE_PROGRESS_BARS: 1
1616
HF_HUB_ENABLE_HF_TRANSFER: 0
1717
WILM_USE_TRITON_FLASH_ATTENTION: 0
@@ -46,7 +46,7 @@ services:
4646
with_memory: false
4747
recursion_limit: ${recursion_limit_worker}
4848
llm_engine: vllm
49-
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
49+
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
5050
llm_endpoint_url: ${LLM_ENDPOINT_URL}
5151
model: ${LLM_MODEL_ID}
5252
temperature: ${temperature}
@@ -80,7 +80,7 @@ services:
8080
use_hints: false
8181
recursion_limit: ${recursion_limit_worker}
8282
llm_engine: vllm
83-
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
83+
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
8484
llm_endpoint_url: ${LLM_ENDPOINT_URL}
8585
model: ${LLM_MODEL_ID}
8686
temperature: ${temperature}
@@ -108,7 +108,7 @@ services:
108108
with_memory: true
109109
recursion_limit: ${recursion_limit_supervisor}
110110
llm_engine: vllm
111-
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
111+
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
112112
llm_endpoint_url: ${LLM_ENDPOINT_URL}
113113
model: ${LLM_MODEL_ID}
114114
temperature: ${temperature}

‎AgentQnA/docker_compose/amd/gpu/rocm/launch_agent_service_tgi_rocm.sh‎

Lines changed: 4 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,9 +1,10 @@
1+
#!/bin/bash
12
# Copyright (C) 2024 Advanced Micro Devices, Inc.
23
# SPDX-License-Identifier: Apache-2.0
34

45
# Before start script:
56
# export host_ip="your_host_ip_or_host_name"
6-
# export HUGGINGFACEHUB_API_TOKEN="your_huggingface_api_token"
7+
# export HF_TOKEN="your_huggingface_api_token"
78
# export LANGCHAIN_API_KEY="your_langchain_api_key"
89
# export LANGCHAIN_TRACING_V2=""
910

@@ -19,7 +20,7 @@ export CRAG_SERVER_PORT="18114"
1920

2021
export WORKPATH=$(dirname "$PWD")
2122
export WORKDIR=${WORKPATH}/../../../
22-
export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
23+
export HF_TOKEN=${HF_TOKEN}
2324
export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
2425
export HF_CACHE_DIR="./data"
2526
export MODEL_CACHE="./data"
@@ -39,7 +40,7 @@ export CRAG_SERVER=http://${ip_address}:${CRAG_SERVER_PORT}
3940
export WORKER_AGENT_URL="http://${ip_address}:${WORKER_RAG_AGENT_PORT}/v1/chat/completions"
4041
export SQL_AGENT_URL="http://${ip_address}:${WORKER_SQL_AGENT_PORT}/v1/chat/completions"
4142
export HF_CACHE_DIR=${HF_CACHE_DIR}
42-
export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
43+
export HF_TOKEN=${HF_TOKEN}
4344
export no_proxy=${no_proxy}
4445
export http_proxy=${http_proxy}
4546
export https_proxy=${https_proxy}

0 commit comments

Comments
 (0)