diff --git a/DocSum/docker_compose/amd/gpu/rocm/README.md b/DocSum/docker_compose/amd/gpu/rocm/README.md index 1c765cbd81..56c0fc022c 100644 --- a/DocSum/docker_compose/amd/gpu/rocm/README.md +++ b/DocSum/docker_compose/amd/gpu/rocm/README.md @@ -23,7 +23,7 @@ This section describes how to quickly deploy and test the DocSum service manuall ### Access the Code -Clone the GenAIExample repository and access the DocSum AMD GPU platform Docker Compose files and supporting scripts: +Clone the GenAIExample repository and access the ChatQnA AMD GPU platform Docker Compose files and supporting scripts: ```bash git clone https://github.com/opea-project/GenAIExamples.git @@ -42,7 +42,7 @@ Some HuggingFace resources, such as some models, are only accessible if you have ### Configure the Deployment Environment -To set up environment variables for deploying DocSum services, set up some parameters specific to the deployment environment and source the `set_env_*.sh` script in this directory: +To set up environment variables for deploying ChatQnA services, set up some parameters specific to the deployment environment and source the `set_env_*.sh` script in this directory: - if used vLLM - set_env_vllm.sh - if used TGI - set_env.sh @@ -65,7 +65,7 @@ Set the values of the variables: Setting variables in the operating system environment: ```bash -export HF_TOKEN="Your_HuggingFace_API_Token" +export HUGGINGFACEHUB_API_TOKEN="Your_HuggingFace_API_Token" source ./set_env_*.sh # replace the script name with the appropriate one ``` @@ -239,16 +239,13 @@ curl http://${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum \ -F "language=en" \ ``` -Note that the `-F "messages="` flag is required, even for file uploads. Multiple files can be uploaded in a single call with multiple `-F "files=@/path"` inputs. - ### Query with audio and video -> Audio and video can be passed as base64 strings or uploaded by providing a local file path. +> Audio and Video file uploads are not supported in docsum with curl request, please use the Gradio-UI. Audio: ```bash -# Send base64 string curl -X POST http://${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum \ -H "Content-Type: application/json" \ -d '{"type": "audio", "messages": "UklGRigAAABXQVZFZm10IBIAAAABAAEARKwAAIhYAQACABAAAABkYXRhAgAAAAEA"}' @@ -260,21 +257,11 @@ curl http://${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum \ -F "max_tokens=32" \ -F "language=en" \ -F "stream=True" - -# Upload file -curl http://${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum \ - -H "Content-Type: multipart/form-data" \ - -F "type=audio" \ - -F "messages=" \ - -F "files=@/path to your file (.mp3, .wav)" \ - -F "max_tokens=32" \ - -F "language=en" ``` Video: ```bash -# Send base64 string curl -X POST http://${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum \ -H "Content-Type: application/json" \ -d '{"type": "video", "messages": "convert your video to base64 data type"}' @@ -286,15 +273,6 @@ curl http://${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum \ -F "max_tokens=32" \ -F "language=en" \ -F "stream=True" - -# Upload file -curl http://${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum \ - -H "Content-Type: multipart/form-data" \ - -F "type=video" \ - -F "messages=" \ - -F "files=@/path to your file (.mp4)" \ - -F "max_tokens=32" \ - -F "language=en" ``` ### Query with long context diff --git a/DocSum/docker_compose/amd/gpu/rocm/compose.yaml b/DocSum/docker_compose/amd/gpu/rocm/compose.yaml index 563f1468f1..62a588292d 100644 --- a/DocSum/docker_compose/amd/gpu/rocm/compose.yaml +++ b/DocSum/docker_compose/amd/gpu/rocm/compose.yaml @@ -8,6 +8,7 @@ services: ports: - "${DOCSUM_TGI_SERVICE_PORT:-8008}:80" environment: + test_env: test no_proxy: ${no_proxy} http_proxy: ${http_proxy} https_proxy: ${https_proxy} diff --git a/DocSum/docker_compose/amd/gpu/rocm/compose_vllm.yaml b/DocSum/docker_compose/amd/gpu/rocm/compose_vllm.yaml index d8a678f695..4f3aa9308d 100644 --- a/DocSum/docker_compose/amd/gpu/rocm/compose_vllm.yaml +++ b/DocSum/docker_compose/amd/gpu/rocm/compose_vllm.yaml @@ -8,6 +8,7 @@ services: ports: - "${DOCSUM_VLLM_SERVICE_PORT:-8081}:8011" environment: + test_env: test no_proxy: ${no_proxy} http_proxy: ${http_proxy} https_proxy: ${https_proxy}