Bump to latest oobabooga commit and install the legacy API as an exte…

…nsion

Dockerfile

@@ -1,7 +1,7 @@
 # Stage 1: Base
 FROM nvidia/cuda:12.1.1-cudnn8-devel-ubuntu22.04 as base
 
-ARG OOBABOOGA_COMMIT=2af7e382b121f2eae16dd1f7ace621d31028b319
+ARG OOBABOOGA_COMMIT=454fcf39a95691f5e375c48fbc6fe6aa96f0c738
 
 SHELL ["/bin/bash", "-o", "pipefail", "-c"]
 ENV DEBIAN_FRONTEND=noninteractive \
@@ -86,6 +86,15 @@ RUN source /venv/bin/activate && \
  pip3 install https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+cu121-cp310-cp310-linux_x86_64.whl && \
  deactivate
 
+# Install legacy API as an extension \
+WORKDIR /text-generation-webui
+RUN source /venv/bin/activate && \
+ cd /workspace/text-generation-webui && \
+ git clone --depth=1 https://github.com/ashleykleynhans/oobabooga-legacy-api-extension.git extensions/api && \
+ source /workspace/venv/bin/activate && \
+ pip3 install -r extensions/api/requirements.txt && \
+ deactivate
+
 # Install rclone
 RUN curl https://rclone.org/install.sh | bash
 

nginx/template-readme.md

@@ -1,6 +1,6 @@
 ## Text Generation Web UI: A Gradio web UI for Large Language Models. Supports transformers, GPTQ, llama.cpp (GGUF), Llama models
 
-### Version 1.8.0
+### Version 1.9.0
 
 ### Included in this Template
 

start_textgen_server.sh

@@ -1,6 +1,6 @@
 #!/usr/bin/env bash
 
-ARGS=("$@" --listen --api --listen-port 3001 --api-port 5001 --api-blocking-port 6050 --api-streaming-port 6055 --extensions openai)
+ARGS=("$@" --listen --api --listen-port 3001 --api-port 5001 --api-blocking-port 6050 --api-streaming-port 6055 --extensions api)
 
 if [[ -f /workspace/text-gen-model ]];
 then