Merge branch 'add-neuron-backend' of github.com:JingyaHuang/text-embeddings-inference into add-neuron-backend

Author: JingyaHuang

Dockerfile-neuron

@@ -174,15 +174,14 @@ RUN pip install --no-cache-dir -U \
     peft==${PEFT_VERSION} \
  && rm -rf ~/.cache/pip/*
 
-
 FROM neuron AS grpc
 
 COPY --from=grpc-builder /usr/src/target/release/text-embeddings-router /usr/local/bin/text-embeddings-router
 
 ENTRYPOINT ["text-embeddings-router"]
 CMD ["--json-output"]
 
-FROM neuron
+FROM neuron AS http
 
 COPY --from=http-builder /usr/src/target/release/text-embeddings-router /usr/local/bin/text-embeddings-router
 

router/src/main.rs

@@ -87,7 +87,7 @@ struct Args {
     /// will refuse to start with an error instead of silently truncating sequences.
     ///
     /// Unused for gRPC servers
-    #[clap(long, env, default_value = "true")]
+    #[clap(long, env, default_value = "true", num_args = 0..=1, default_missing_value = "true")]
     auto_truncate: bool,
 
     /// The name of the prompt that should be used by default for encoding. If not set, no prompt