Skip to content

Update text-embeddings-router --help output #603

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

Merged
merged 1 commit into from
Apr 29, 2025
Merged

Update text-embeddings-router --help output #603

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
58 changes: 23 additions & 35 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -129,31 +129,26 @@ NVIDIA drivers on your machine need to be compatible with CUDA version 12.2 or h

To see all options to serve your models:

```shell
text-embeddings-router --help
```
```console
$ text-embeddings-router --help
Text Embedding Webserver

```
Usage: text-embeddings-router [OPTIONS]

Options:
--model-id <MODEL_ID>
The name of the model to load. Can be a MODEL_ID as listed on <https://hf.co/models> like `thenlper/gte-base`.
Or it can be a local directory containing the necessary files as saved by `save_pretrained(...)` methods of
transformers
The name of the model to load. Can be a MODEL_ID as listed on <https://hf.co/models> like `BAAI/bge-large-en-v1.5`. Or it can be a local directory containing the necessary files as saved by `save_pretrained(...)` methods of transformers

[env: MODEL_ID=]
[default: thenlper/gte-base]
[default: BAAI/bge-large-en-v1.5]

--revision <REVISION>
The actual revision of the model if you're referring to a model on the hub. You can use a specific commit id
or a branch like `refs/pr/2`
The actual revision of the model if you're referring to a model on the hub. You can use a specific commit id or a branch like `refs/pr/2`

[env: REVISION=]

--tokenization-workers <TOKENIZATION_WORKERS>
Optionally control the number of tokenizer workers used for payload tokenization, validation and truncation.
Default to the number of CPU cores on the machine
Optionally control the number of tokenizer workers used for payload tokenization, validation and truncation. Default to the number of CPU cores on the machine

[env: TOKENIZATION_WORKERS=]

Expand All @@ -175,14 +170,11 @@ Options:
Possible values:
- cls: Select the CLS token as embedding
- mean: Apply Mean pooling to the model embeddings
- splade: Apply SPLADE (Sparse Lexical and Expansion) to the model embeddings. This option is only
available if the loaded model is a `ForMaskedLM` Transformer model
- splade: Apply SPLADE (Sparse Lexical and Expansion) to the model embeddings. This option is only available if the loaded model is a `ForMaskedLM` Transformer model
- last-token: Select the last token as embedding

--max-concurrent-requests <MAX_CONCURRENT_REQUESTS>
The maximum amount of concurrent requests for this particular deployment.
Having a low limit will refuse clients requests instead of having them wait for too long and is usually good
to handle backpressure correctly
The maximum amount of concurrent requests for this particular deployment. Having a low limit will refuse clients requests instead of having them wait for too long and is usually good to handle backpressure correctly

[env: MAX_CONCURRENT_REQUESTS=]
[default: 512]
Expand All @@ -194,8 +186,7 @@ Options:

For `max_batch_tokens=1000`, you could fit `10` queries of `total_tokens=100` or a single query of `1000` tokens.

Overall this number should be the largest possible until the model is compute bound. Since the actual memory
overhead depends on the model implementation, text-embeddings-inference cannot infer this number automatically.
Overall this number should be the largest possible until the model is compute bound. Since the actual memory overhead depends on the model implementation, text-embeddings-inference cannot infer this number automatically.

[env: MAX_BATCH_TOKENS=]
[default: 16384]
Expand Down Expand Up @@ -223,9 +214,7 @@ Options:

Must be a key in the `sentence-transformers` configuration `prompts` dictionary.

For example if ``default_prompt_name`` is "query" and the ``prompts`` is {"query": "query: ", ...}, then the
sentence "What is the capital of France?" will be encoded as "query: What is the capital of France?" because
the prompt text will be prepended before any text to encode.
For example if ``default_prompt_name`` is "query" and the ``prompts`` is {"query": "query: ", ...}, then the sentence "What is the capital of France?" will be encoded as "query: What is the capital of France?" because the prompt text will be prepended before any text to encode.

The argument '--default-prompt-name <DEFAULT_PROMPT_NAME>' cannot be used with '--default-prompt <DEFAULT_PROMPT>`

Expand All @@ -234,9 +223,7 @@ Options:
--default-prompt <DEFAULT_PROMPT>
The prompt that should be used by default for encoding. If not set, no prompt will be applied.

For example if ``default_prompt`` is "query: " then the sentence "What is the capital of France?" will be
encoded as "query: What is the capital of France?" because the prompt text will be prepended before any text
to encode.
For example if ``default_prompt`` is "query: " then the sentence "What is the capital of France?" will be encoded as "query: What is the capital of France?" because the prompt text will be prepended before any text to encode.

The argument '--default-prompt <DEFAULT_PROMPT>' cannot be used with '--default-prompt-name <DEFAULT_PROMPT_NAME>`

Expand All @@ -260,15 +247,13 @@ Options:
[default: 3000]

--uds-path <UDS_PATH>
The name of the unix socket some text-embeddings-inference backends will use as they communicate internally
with gRPC
The name of the unix socket some text-embeddings-inference backends will use as they communicate internally with gRPC

[env: UDS_PATH=]
[default: /tmp/text-embeddings-inference-server]

--huggingface-hub-cache <HUGGINGFACE_HUB_CACHE>
The location of the huggingface hub cache. Used to override the location if you want to provide a mounted disk
for instance
The location of the huggingface hub cache. Used to override the location if you want to provide a mounted disk for instance

[env: HUGGINGFACE_HUB_CACHE=]

Expand All @@ -283,8 +268,7 @@ Options:
--api-key <API_KEY>
Set an api key for request authorization.

By default the server responds to every request. With an api key set, the requests must have the Authorization
header set with the api key as Bearer token.
By default the server responds to every request. With an api key set, the requests must have the Authorization header set with the api key as Bearer token.

[env: API_KEY=]

Expand All @@ -294,8 +278,6 @@ Options:
[env: JSON_OUTPUT=]

--disable-spans
Disables the span logging trace

[env: DISABLE_SPANS=]

--otlp-endpoint <OTLP_ENDPOINT>
Expand All @@ -309,8 +291,8 @@ Options:
[env: OTLP_SERVICE_NAME=]
[default: text-embeddings-inference.server]

--prometheus-port <PORT>
The Prometheus metrics port to listen on
--prometheus-port <PROMETHEUS_PORT>
The Prometheus port to listen on

[env: PROMETHEUS_PORT=]
[default: 9000]
Expand All @@ -319,6 +301,12 @@ Options:
Unused for gRPC servers

[env: CORS_ALLOW_ORIGIN=]

-h, --help
Print help (see a summary with '-h')

-V, --version
Print version
```

### Docker Images
Expand Down
60 changes: 27 additions & 33 deletions docs/source/en/cli_arguments.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,31 +18,26 @@ rendered properly in your Markdown viewer.

To see all options to serve your models, run the following:

```shell
text-embeddings-router --help
```
```console
$ text-embeddings-router --help
Text Embedding Webserver

```
Usage: text-embeddings-router [OPTIONS]

Options:
--model-id <MODEL_ID>
The name of the model to load. Can be a MODEL_ID as listed on <https://hf.co/models> like `thenlper/gte-base`.
Or it can be a local directory containing the necessary files as saved by `save_pretrained(...)` methods of
transformers
The name of the model to load. Can be a MODEL_ID as listed on <https://hf.co/models> like `BAAI/bge-large-en-v1.5`. Or it can be a local directory containing the necessary files as saved by `save_pretrained(...)` methods of transformers

[env: MODEL_ID=]
[default: thenlper/gte-base]
[default: BAAI/bge-large-en-v1.5]

--revision <REVISION>
The actual revision of the model if you're referring to a model on the hub. You can use a specific commit id
or a branch like `refs/pr/2`
The actual revision of the model if you're referring to a model on the hub. You can use a specific commit id or a branch like `refs/pr/2`

[env: REVISION=]

--tokenization-workers <TOKENIZATION_WORKERS>
Optionally control the number of tokenizer workers used for payload tokenization, validation and truncation.
Default to the number of CPU cores on the machine
Optionally control the number of tokenizer workers used for payload tokenization, validation and truncation. Default to the number of CPU cores on the machine

[env: TOKENIZATION_WORKERS=]

Expand All @@ -64,14 +59,11 @@ Options:
Possible values:
- cls: Select the CLS token as embedding
- mean: Apply Mean pooling to the model embeddings
- splade: Apply SPLADE (Sparse Lexical and Expansion) to the model embeddings. This option is only
available if the loaded model is a `ForMaskedLM` Transformer model
- splade: Apply SPLADE (Sparse Lexical and Expansion) to the model embeddings. This option is only available if the loaded model is a `ForMaskedLM` Transformer model
- last-token: Select the last token as embedding

--max-concurrent-requests <MAX_CONCURRENT_REQUESTS>
The maximum amount of concurrent requests for this particular deployment.
Having a low limit will refuse clients requests instead of having them wait for too long and is usually good
to handle backpressure correctly
The maximum amount of concurrent requests for this particular deployment. Having a low limit will refuse clients requests instead of having them wait for too long and is usually good to handle backpressure correctly

[env: MAX_CONCURRENT_REQUESTS=]
[default: 512]
Expand All @@ -83,8 +75,7 @@ Options:

For `max_batch_tokens=1000`, you could fit `10` queries of `total_tokens=100` or a single query of `1000` tokens.

Overall this number should be the largest possible until the model is compute bound. Since the actual memory
overhead depends on the model implementation, text-embeddings-inference cannot infer this number automatically.
Overall this number should be the largest possible until the model is compute bound. Since the actual memory overhead depends on the model implementation, text-embeddings-inference cannot infer this number automatically.

[env: MAX_BATCH_TOKENS=]
[default: 16384]
Expand Down Expand Up @@ -112,9 +103,7 @@ Options:

Must be a key in the `sentence-transformers` configuration `prompts` dictionary.

For example if ``default_prompt_name`` is "query" and the ``prompts`` is {"query": "query: ", ...}, then the
sentence "What is the capital of France?" will be encoded as "query: What is the capital of France?" because
the prompt text will be prepended before any text to encode.
For example if ``default_prompt_name`` is "query" and the ``prompts`` is {"query": "query: ", ...}, then the sentence "What is the capital of France?" will be encoded as "query: What is the capital of France?" because the prompt text will be prepended before any text to encode.

The argument '--default-prompt-name <DEFAULT_PROMPT_NAME>' cannot be used with '--default-prompt <DEFAULT_PROMPT>`

Expand All @@ -123,9 +112,7 @@ Options:
--default-prompt <DEFAULT_PROMPT>
The prompt that should be used by default for encoding. If not set, no prompt will be applied.

For example if ``default_prompt`` is "query: " then the sentence "What is the capital of France?" will be
encoded as "query: What is the capital of France?" because the prompt text will be prepended before any text
to encode.
For example if ``default_prompt`` is "query: " then the sentence "What is the capital of France?" will be encoded as "query: What is the capital of France?" because the prompt text will be prepended before any text to encode.

The argument '--default-prompt <DEFAULT_PROMPT>' cannot be used with '--default-prompt-name <DEFAULT_PROMPT_NAME>`

Expand All @@ -149,15 +136,13 @@ Options:
[default: 3000]

--uds-path <UDS_PATH>
The name of the unix socket some text-embeddings-inference backends will use as they communicate internally
with gRPC
The name of the unix socket some text-embeddings-inference backends will use as they communicate internally with gRPC

[env: UDS_PATH=]
[default: /tmp/text-embeddings-inference-server]

--huggingface-hub-cache <HUGGINGFACE_HUB_CACHE>
The location of the huggingface hub cache. Used to override the location if you want to provide a mounted disk
for instance
The location of the huggingface hub cache. Used to override the location if you want to provide a mounted disk for instance

[env: HUGGINGFACE_HUB_CACHE=]

Expand All @@ -172,8 +157,7 @@ Options:
--api-key <API_KEY>
Set an api key for request authorization.

By default the server responds to every request. With an api key set, the requests must have the Authorization
header set with the api key as Bearer token.
By default the server responds to every request. With an api key set, the requests must have the Authorization header set with the api key as Bearer token.

[env: API_KEY=]

Expand All @@ -183,8 +167,6 @@ Options:
[env: JSON_OUTPUT=]

--disable-spans
Disables the span logging trace

[env: DISABLE_SPANS=]

--otlp-endpoint <OTLP_ENDPOINT>
Expand All @@ -198,8 +180,20 @@ Options:
[env: OTLP_SERVICE_NAME=]
[default: text-embeddings-inference.server]

--prometheus-port <PROMETHEUS_PORT>
The Prometheus port to listen on

[env: PROMETHEUS_PORT=]
[default: 9000]

--cors-allow-origin <CORS_ALLOW_ORIGIN>
Unused for gRPC servers

[env: CORS_ALLOW_ORIGIN=]

-h, --help
Print help (see a summary with '-h')

-V, --version
Print version
```
Loading