mirror of
https://github.com/containers/ramalama.git
synced 2026-02-05 06:46:39 +01:00
updates docsite and adds docsite to the make docs process
Signed-off-by: Ian Eaves <ian.k.eaves@gmail.com>
This commit is contained in:
Ian Eaves
11
Makefile
11
Makefile
@@ -100,9 +100,14 @@ build_multi_arch:
|
||||
install-docs: docs
|
||||
make -C docs install
|
||||
|
||||
.PHONY: docs
|
||||
docs:
|
||||
make -C docs
|
||||
.PHONY: docs docs-manpages docsite-docs
|
||||
docs: docs-manpages docsite-docs
|
||||
|
||||
docs-manpages:
|
||||
$(MAKE) -C docs
|
||||
|
||||
docsite-docs:
|
||||
$(MAKE) -C docsite convert
|
||||
|
||||
.PHONY: lint
|
||||
lint:
|
||||
|
||||
@@ -26,13 +26,15 @@ def extract_title_and_description(content, filename):
|
||||
|
||||
# Generate title from filename pattern
|
||||
base_name = os.path.basename(filename)
|
||||
title = None
|
||||
|
||||
if base_name == 'ramalama.1.md':
|
||||
title = "ramalama" # Base command page
|
||||
if base_name.startswith('ramalama-') and base_name.endswith('.1.md'):
|
||||
title = 'ramalama' # Base command page
|
||||
elif base_name.startswith('ramalama-') and base_name.endswith('.1.md'):
|
||||
# Command: ramalama-chat.1.md -> chat (just the subcommand name)
|
||||
command = base_name.replace('ramalama-', '').replace('.1.md', '')
|
||||
title = command
|
||||
if base_name.startswith('ramalama-') and base_name.endswith('.7.md'):
|
||||
elif base_name.startswith('ramalama-') and base_name.endswith('.7.md'):
|
||||
# Platform guide: ramalama-cuda.7.md -> CUDA Setup
|
||||
platform = base_name.replace('ramalama-', '').replace('.7.md', '')
|
||||
|
||||
@@ -42,7 +44,7 @@ def extract_title_and_description(content, filename):
|
||||
platform = platform.upper()
|
||||
|
||||
title = f"{platform} Setup"
|
||||
if base_name.endswith('.5.md'):
|
||||
elif base_name.endswith('.5.md'):
|
||||
# Config files with custom titles
|
||||
if base_name == 'ramalama.conf.5.md':
|
||||
title = 'Configuration File'
|
||||
@@ -51,8 +53,9 @@ def extract_title_and_description(content, filename):
|
||||
else:
|
||||
# Fallback for other .5.md files
|
||||
title = base_name.replace('.5.md', '')
|
||||
else:
|
||||
# Fallback
|
||||
|
||||
if title is None:
|
||||
# Fallback for any other file types
|
||||
title = base_name.replace('.md', '').replace('-', ' ')
|
||||
|
||||
# Find description from NAME section
|
||||
@@ -105,7 +108,7 @@ def detect_code_language(content):
|
||||
return 'text'
|
||||
|
||||
|
||||
def convert_markdown_to_mdx(content, filename):
|
||||
def convert_markdown_to_mdx(content, filename, current_output_path, output_map):
|
||||
"""Convert manpage markdown to MDX format"""
|
||||
|
||||
# Extract title and description
|
||||
@@ -118,8 +121,13 @@ def convert_markdown_to_mdx(content, filename):
|
||||
|
||||
content = '\n'.join(lines)
|
||||
|
||||
# Convert NAME section
|
||||
content = re.sub(r'## NAME\n([^\n]+)', '', content, flags=re.MULTILINE)
|
||||
# Remove NAME section (handles both H1 and H2 variants)
|
||||
content = re.sub(
|
||||
r'^#{1,2}\s+NAME\s*\n(?:.*?)(?=^#{1,6}\s|\Z)',
|
||||
'',
|
||||
content,
|
||||
flags=re.MULTILINE | re.DOTALL,
|
||||
)
|
||||
|
||||
# Convert SYNOPSIS to proper heading
|
||||
content = re.sub(r'## SYNOPSIS', '## Synopsis', content)
|
||||
@@ -151,6 +159,8 @@ def convert_markdown_to_mdx(content, filename):
|
||||
content = re.sub(r'\*\*\[([^\]]+)\]\(([^)]+)\)\*\*', r'[\1](\2)', content)
|
||||
|
||||
# Convert internal manpage links to docsite links
|
||||
current_dir = current_output_path.parent
|
||||
|
||||
def convert_link(match):
|
||||
text = match.group(1)
|
||||
link = match.group(2)
|
||||
@@ -159,38 +169,24 @@ def convert_markdown_to_mdx(content, filename):
|
||||
if link.startswith(('http://', 'https://')):
|
||||
return f'[{text}]({link})'
|
||||
|
||||
# All files are now in subdirectories, so use relative paths appropriately
|
||||
if filename.endswith('.1.md'):
|
||||
# From commands/ramalama/ directory
|
||||
base_path = "../../"
|
||||
elif filename.endswith('.5.md'):
|
||||
# From configuration/ directory
|
||||
base_path = "../"
|
||||
elif filename.endswith('.7.md'):
|
||||
# From platform-guides/ directory
|
||||
base_path = "../"
|
||||
else:
|
||||
base_path = "./"
|
||||
base_link = os.path.basename(link)
|
||||
target_rel_path = output_map.get(base_link)
|
||||
|
||||
if link.endswith('.1.md'):
|
||||
# Command reference
|
||||
command_name = link.replace('ramalama-', '').replace('.1.md', '')
|
||||
if command_name == 'ramalama':
|
||||
if filename == 'ramalama.1.md':
|
||||
return f'[{text}](#)' # Self-reference
|
||||
else:
|
||||
return f'[{text}](/docs/commands/ramalama/)' # Link to ramalama category index
|
||||
return f'[{text}]({base_path}commands/ramalama/{command_name})'
|
||||
if link.endswith('.5.md'):
|
||||
# Configuration file
|
||||
config_name = link.replace('ramalama.', '').replace('.5.md', '')
|
||||
return f'[{text}]({base_path}configuration/{config_name})'
|
||||
if link.endswith('.7.md'):
|
||||
# Platform guide
|
||||
guide_name = link.replace('ramalama-', '').replace('.7.md', '')
|
||||
return f'[{text}]({base_path}platform-guides/{guide_name})'
|
||||
if not target_rel_path:
|
||||
return f'[{text}]({link})'
|
||||
|
||||
return f'[{text}]({link})'
|
||||
target_path = target_rel_path
|
||||
|
||||
if target_path == current_output_path:
|
||||
return f'[{text}](#)' # Self-reference
|
||||
|
||||
if target_path == Path('commands/ramalama/ramalama.mdx'):
|
||||
return f'[{text}](/docs/commands/ramalama/)'
|
||||
|
||||
# Use absolute doc URL (prefix with /docs)
|
||||
target_route = '/docs/' + target_path.with_suffix('').as_posix()
|
||||
|
||||
return f'[{text}]({target_route})'
|
||||
|
||||
content = re.sub(r'\[([^\]]+)\]\(([^)]+\.md)\)', convert_link, content)
|
||||
|
||||
@@ -324,30 +320,29 @@ def main():
|
||||
|
||||
print(f"\nFound {len(manpage_files)} manpage files to convert")
|
||||
|
||||
manpage_entries = []
|
||||
for input_file in manpage_files:
|
||||
filename = os.path.basename(input_file)
|
||||
output_filename = get_output_filename(filename)
|
||||
_, subdir = get_category_info(filename)
|
||||
relative_output_path = Path(subdir) / output_filename
|
||||
manpage_entries.append((input_file, filename, relative_output_path))
|
||||
|
||||
output_map = {filename: relative_path for _, filename, relative_path in manpage_entries}
|
||||
|
||||
for input_file, filename, relative_output_path in manpage_entries:
|
||||
print(f"Converting {filename}...")
|
||||
|
||||
# Convert all files (overwriting existing ones)
|
||||
|
||||
# Read input file
|
||||
with open(input_file, 'r', encoding='utf-8') as f:
|
||||
content = f.read()
|
||||
|
||||
# Convert to MDX
|
||||
mdx_content = convert_markdown_to_mdx(content, filename)
|
||||
mdx_content = convert_markdown_to_mdx(content, filename, relative_output_path, output_map)
|
||||
|
||||
# Determine output directory and filename
|
||||
output_filename = get_output_filename(filename)
|
||||
|
||||
# All manpage files go to their category directories
|
||||
category, subdir = get_category_info(filename)
|
||||
output_dir = docsite_docs_dir / subdir
|
||||
output_path = output_dir / output_filename
|
||||
# Create output directory if it doesn't exist
|
||||
output_dir = (docsite_docs_dir / relative_output_path).parent
|
||||
output_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
# Write output file
|
||||
output_path = docsite_docs_dir / relative_output_path
|
||||
|
||||
with open(output_path, 'w', encoding='utf-8') as f:
|
||||
f.write(mdx_content)
|
||||
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
---
|
||||
title: ramalama bench.1
|
||||
title: bench
|
||||
description: benchmark specified AI Model
|
||||
# This file is auto-generated from manpages. Do not edit manually.
|
||||
# Source: ramalama-bench.1.md
|
||||
---
|
||||
|
||||
# ramalama bench.1
|
||||
# bench
|
||||
|
||||
## Synopsis
|
||||
**ramalama bench** [*options*] *model* [arg ...]
|
||||
@@ -63,7 +63,7 @@ OCI container image to run with specified AI model. RamaLama defaults to using
|
||||
images based on the accelerator it discovers. For example:
|
||||
`quay.io/ramalama/ramalama`. See the table below for all default images.
|
||||
The default image tag is based on the minor version of the RamaLama package.
|
||||
Version 0.12.1 of RamaLama pulls an image with a `:0.12` tag from the quay.io/ramalama OCI repository. The --image option overrides this default.
|
||||
Version 0.12.3 of RamaLama pulls an image with a `:0.12` tag from the quay.io/ramalama OCI repository. The --image option overrides this default.
|
||||
|
||||
The default can be overridden in the ramalama.conf file or via the
|
||||
RAMALAMA_IMAGE environment variable. `export RAMALAMA_IMAGE=quay.io/ramalama/aiimage:1.2` tells
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
---
|
||||
title: ramalama chat.1
|
||||
title: chat
|
||||
description: OpenAI chat with the specified REST API URL
|
||||
# This file is auto-generated from manpages. Do not edit manually.
|
||||
# Source: ramalama-chat.1.md
|
||||
---
|
||||
|
||||
# ramalama chat.1
|
||||
# chat
|
||||
|
||||
## Synopsis
|
||||
**ramalama chat** [*options*] [arg...]
|
||||
@@ -21,7 +21,7 @@ Chat with an OpenAI Rest API
|
||||
|
||||
#### **--api-key**
|
||||
OpenAI-compatible API key.
|
||||
Can also be set via the API_KEY environment variable.
|
||||
Can also be set via the RAMALAMA_API_KEY environment variable.
|
||||
|
||||
#### **--color**
|
||||
Indicate whether or not to use color in the chat.
|
||||
@@ -33,6 +33,11 @@ Show this help message and exit
|
||||
#### **--list**
|
||||
List the available models at an endpoint
|
||||
|
||||
#### **--mcp**=SERVER_URL
|
||||
MCP (Model Context Protocol) servers to use for enhanced tool calling capabilities.
|
||||
Can be specified multiple times to connect to multiple MCP servers.
|
||||
Each server provides tools that can be automatically invoked during chat conversations.
|
||||
|
||||
#### **--model**=MODEL
|
||||
Model for inferencing (may not be required for endpoints that only serve one model)
|
||||
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
---
|
||||
title: ramalama containers.1
|
||||
title: containers
|
||||
description: list all RamaLama containers
|
||||
# This file is auto-generated from manpages. Do not edit manually.
|
||||
# Source: ramalama-containers.1.md
|
||||
---
|
||||
|
||||
# ramalama containers.1
|
||||
# containers
|
||||
|
||||
## Synopsis
|
||||
**ramalama containers** [*options*]
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
---
|
||||
title: ramalama convert.1
|
||||
title: convert
|
||||
description: convert AI Models from local storage to OCI Image
|
||||
# This file is auto-generated from manpages. Do not edit manually.
|
||||
# Source: ramalama-convert.1.md
|
||||
---
|
||||
|
||||
# ramalama convert.1
|
||||
# convert
|
||||
|
||||
## Synopsis
|
||||
**ramalama convert** [*options*] *model* [*target*]
|
||||
@@ -65,7 +65,7 @@ $ ramalama run oci://quay.io/kugupta/granite-3.2-q4-k-m:latest
|
||||
```
|
||||
|
||||
## See Also
|
||||
[ramalama(1)](/docs/commands/ramalama/), [ramalama-push(1)](../../commands/ramalama/push)
|
||||
[ramalama(1)](/docs/commands/ramalama/), [ramalama-push(1)](/docs/commands/ramalama/push)
|
||||
|
||||
---
|
||||
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
---
|
||||
title: ramalama daemon.1
|
||||
title: daemon
|
||||
description: run a RamaLama REST server
|
||||
# This file is auto-generated from manpages. Do not edit manually.
|
||||
# Source: ramalama-daemon.1.md
|
||||
---
|
||||
|
||||
# ramalama daemon.1
|
||||
# daemon
|
||||
|
||||
## Synopsis
|
||||
**ramalama daemon** [*options*] [start|run]
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
---
|
||||
title: ramalama info.1
|
||||
title: info
|
||||
description: display RamaLama configuration information
|
||||
# This file is auto-generated from manpages. Do not edit manually.
|
||||
# Source: ramalama-info.1.md
|
||||
---
|
||||
|
||||
# ramalama info.1
|
||||
# info
|
||||
|
||||
## Synopsis
|
||||
**ramalama info** [*options*]
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
---
|
||||
title: ramalama inspect.1
|
||||
title: inspect
|
||||
description: inspect the specified AI Model
|
||||
# This file is auto-generated from manpages. Do not edit manually.
|
||||
# Source: ramalama-inspect.1.md
|
||||
---
|
||||
|
||||
# ramalama inspect.1
|
||||
# inspect
|
||||
|
||||
## Synopsis
|
||||
**ramalama inspect** [*options*] *model*
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
---
|
||||
title: ramalama list.1
|
||||
title: list
|
||||
description: list all downloaded AI Models
|
||||
# This file is auto-generated from manpages. Do not edit manually.
|
||||
# Source: ramalama-list.1.md
|
||||
---
|
||||
|
||||
# ramalama list.1
|
||||
# list
|
||||
|
||||
## Synopsis
|
||||
**ramalama list** [*options*]
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
---
|
||||
title: ramalama login.1
|
||||
title: login
|
||||
description: login to remote registry
|
||||
# This file is auto-generated from manpages. Do not edit manually.
|
||||
# Source: ramalama-login.1.md
|
||||
---
|
||||
|
||||
# ramalama login.1
|
||||
# login
|
||||
|
||||
## Synopsis
|
||||
**ramalama login** [*options*] [*registry*]
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
---
|
||||
title: ramalama logout.1
|
||||
title: logout
|
||||
description: logout from remote registry
|
||||
# This file is auto-generated from manpages. Do not edit manually.
|
||||
# Source: ramalama-logout.1.md
|
||||
---
|
||||
|
||||
# ramalama logout.1
|
||||
# logout
|
||||
|
||||
## Synopsis
|
||||
**ramalama logout** [*options*] [*registry*]
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
---
|
||||
title: ramalama perplexity.1
|
||||
title: perplexity
|
||||
description: calculate the perplexity value of an AI Model
|
||||
# This file is auto-generated from manpages. Do not edit manually.
|
||||
# Source: ramalama-perplexity.1.md
|
||||
---
|
||||
|
||||
# ramalama perplexity.1
|
||||
# perplexity
|
||||
|
||||
## Synopsis
|
||||
**ramalama perplexity** [*options*] *model* [arg ...]
|
||||
@@ -66,7 +66,7 @@ OCI container image to run with specified AI model. RamaLama defaults to using
|
||||
images based on the accelerator it discovers. For example:
|
||||
`quay.io/ramalama/ramalama`. See the table below for all default images.
|
||||
The default image tag is based on the minor version of the RamaLama package.
|
||||
Version 0.12.1 of RamaLama pulls an image with a `:0.12` tag from the quay.io/ramalama OCI repository. The --image option overrides this default.
|
||||
Version 0.12.3 of RamaLama pulls an image with a `:0.12` tag from the quay.io/ramalama OCI repository. The --image option overrides this default.
|
||||
|
||||
The default can be overridden in the ramalama.conf file or via the
|
||||
RAMALAMA_IMAGE environment variable. `export RAMALAMA_IMAGE=quay.io/ramalama/aiimage:1.2` tells
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
---
|
||||
title: ramalama pull.1
|
||||
title: pull
|
||||
description: pull AI Models from Model registries to local storage
|
||||
# This file is auto-generated from manpages. Do not edit manually.
|
||||
# Source: ramalama-pull.1.md
|
||||
---
|
||||
|
||||
# ramalama pull.1
|
||||
# pull
|
||||
|
||||
## Synopsis
|
||||
**ramalama pull** [*options*] *model*
|
||||
@@ -24,6 +24,9 @@ Print usage message
|
||||
#### **--tls-verify**=*true*
|
||||
require HTTPS and verify certificates when contacting OCI registries
|
||||
|
||||
#### **--verify**=*true*
|
||||
verify the model after pull, disable to allow pulling of models with different endianness
|
||||
|
||||
## See Also
|
||||
[ramalama(1)](/docs/commands/ramalama/)
|
||||
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
---
|
||||
title: ramalama push.1
|
||||
title: push
|
||||
description: push AI Models from local storage to remote registries
|
||||
# This file is auto-generated from manpages. Do not edit manually.
|
||||
# Source: ramalama-push.1.md
|
||||
---
|
||||
|
||||
# ramalama push.1
|
||||
# push
|
||||
|
||||
## Synopsis
|
||||
**ramalama push** [*options*] *model* [*target*]
|
||||
@@ -74,7 +74,7 @@ Writing manifest to image destination
|
||||
```
|
||||
|
||||
## See Also
|
||||
[ramalama(1)](/docs/commands/ramalama/), [ramalama-convert(1)](../../commands/ramalama/convert)
|
||||
[ramalama(1)](/docs/commands/ramalama/), [ramalama-convert(1)](/docs/commands/ramalama/convert)
|
||||
|
||||
---
|
||||
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
---
|
||||
title: ramalama rag.1
|
||||
title: rag
|
||||
description: generate and convert Retrieval Augmented Generation (RAG) data from provided documents into an OCI Image
|
||||
# This file is auto-generated from manpages. Do not edit manually.
|
||||
# Source: ramalama-rag.1.md
|
||||
---
|
||||
|
||||
# ramalama rag.1
|
||||
# rag
|
||||
|
||||
## Synopsis
|
||||
**ramalama rag** [options] [path ...] image
|
||||
@@ -56,7 +56,7 @@ OCI container image to run with specified AI model. RamaLama defaults to using
|
||||
images based on the accelerator it discovers. For example:
|
||||
`quay.io/ramalama/ramalama-rag`. See the table below for all default images.
|
||||
The default image tag is based on the minor version of the RamaLama package.
|
||||
Version 0.12.1 of RamaLama pulls an image with a `:0.12` tag from the quay.io/ramalama OCI repository. The --image option overrides this default.
|
||||
Version 0.12.3 of RamaLama pulls an image with a `:0.12` tag from the quay.io/ramalama OCI repository. The --image option overrides this default.
|
||||
|
||||
The default can be overridden in the ramalama.conf file or via the
|
||||
RAMALAMA_IMAGE environment variable. `export RAMALAMA_IMAGE=quay.io/ramalama/aiimage:1.2` tells
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
---
|
||||
title: ramalama.1
|
||||
title: ramalama
|
||||
description: Simple management tool for working with AI Models
|
||||
# This file is auto-generated from manpages. Do not edit manually.
|
||||
# Source: ramalama.1.md
|
||||
---
|
||||
|
||||
# ramalama.1
|
||||
# ramalama
|
||||
|
||||
## Synopsis
|
||||
**ramalama** [*options*] *command*
|
||||
@@ -32,14 +32,14 @@ RamaLama pulls AI Models from model registries. Starting a chatbot or a rest API
|
||||
When both Podman and Docker are installed, RamaLama defaults to Podman, The `RAMALAMA_CONTAINER_ENGINE=docker` environment variable can override this behaviour. When neither are installed RamaLama attempts to run the model with software on the local system.
|
||||
|
||||
:::note
|
||||
On MacOS systems that use Podman for containers, configure the Podman machine to use the `libkrun` machine provider. The `libkrun` provider enables containers within the Podman Machine access to the Mac's GPU. See [ramalama-macos(7)](../../platform-guides/macos) for further information.
|
||||
On MacOS systems that use Podman for containers, configure the Podman machine to use the `libkrun` machine provider. The `libkrun` provider enables containers within the Podman Machine access to the Mac's GPU. See [ramalama-macos(7)](/docs/platform-guides/macos) for further information.
|
||||
:::
|
||||
|
||||
:::note
|
||||
On systems with NVIDIA GPUs, see [ramalama-cuda(7)](../../platform-guides/cuda) to correctly configure the host system.
|
||||
On systems with NVIDIA GPUs, see [ramalama-cuda(7)](/docs/platform-guides/cuda) to correctly configure the host system.
|
||||
:::
|
||||
|
||||
RamaLama CLI defaults can be modified via ramalama.conf files. Default settings for flags are defined in [ramalama.conf(5)](../../configuration/conf).
|
||||
RamaLama CLI defaults can be modified via ramalama.conf files. Default settings for flags are defined in [ramalama.conf(5)](/docs/configuration/conf).
|
||||
|
||||
## SECURITY
|
||||
|
||||
@@ -146,25 +146,25 @@ The default can be overridden in the ramalama.conf file.
|
||||
|
||||
| Command | Description |
|
||||
| ------------------------------------------------- | ---------------------------------------------------------- |
|
||||
| [ramalama-bench(1)](../../commands/ramalama/bench) |benchmark specified AI Model|
|
||||
| [ramalama-chat(1)](../../commands/ramalama/chat) |OpenAI chat with the specified REST API URL|
|
||||
| [ramalama-containers(1)](../../commands/ramalama/containers)|list all RamaLama containers|
|
||||
| [ramalama-convert(1)](../../commands/ramalama/convert) |convert AI Models from local storage to OCI Image|
|
||||
| [ramalama-daemon(1)](../../commands/ramalama/daemon) |run a RamaLama REST server|
|
||||
| [ramalama-info(1)](../../commands/ramalama/info) |display RamaLama configuration information|
|
||||
| [ramalama-inspect(1)](../../commands/ramalama/inspect) |inspect the specified AI Model|
|
||||
| [ramalama-list(1)](../../commands/ramalama/list) |list all downloaded AI Models|
|
||||
| [ramalama-login(1)](../../commands/ramalama/login) |login to remote registry|
|
||||
| [ramalama-logout(1)](../../commands/ramalama/logout) |logout from remote registry|
|
||||
| [ramalama-perplexity(1)](../../commands/ramalama/perplexity)|calculate the perplexity value of an AI Model|
|
||||
| [ramalama-pull(1)](../../commands/ramalama/pull) |pull AI Models from Model registries to local storage|
|
||||
| [ramalama-push(1)](../../commands/ramalama/push) |push AI Models from local storage to remote registries|
|
||||
| [ramalama-rag(1)](../../commands/ramalama/rag) |generate and convert Retrieval Augmented Generation (RAG) data from provided documents into an OCI Image|
|
||||
| [ramalama-rm(1)](../../commands/ramalama/rm) |remove AI Models from local storage|
|
||||
| [ramalama-run(1)](../../commands/ramalama/run) |run specified AI Model as a chatbot|
|
||||
| [ramalama-serve(1)](../../commands/ramalama/serve) |serve REST API on specified AI Model|
|
||||
| [ramalama-stop(1)](../../commands/ramalama/stop) |stop named container that is running AI Model|
|
||||
| [ramalama-version(1)](../../commands/ramalama/version) |display version of RamaLama|
|
||||
| [ramalama-bench(1)](/docs/commands/ramalama/bench) |benchmark specified AI Model|
|
||||
| [ramalama-chat(1)](/docs/commands/ramalama/chat) |OpenAI chat with the specified REST API URL|
|
||||
| [ramalama-containers(1)](/docs/commands/ramalama/containers)|list all RamaLama containers|
|
||||
| [ramalama-convert(1)](/docs/commands/ramalama/convert) |convert AI Models from local storage to OCI Image|
|
||||
| [ramalama-daemon(1)](/docs/commands/ramalama/daemon) |run a RamaLama REST server|
|
||||
| [ramalama-info(1)](/docs/commands/ramalama/info) |display RamaLama configuration information|
|
||||
| [ramalama-inspect(1)](/docs/commands/ramalama/inspect) |inspect the specified AI Model|
|
||||
| [ramalama-list(1)](/docs/commands/ramalama/list) |list all downloaded AI Models|
|
||||
| [ramalama-login(1)](/docs/commands/ramalama/login) |login to remote registry|
|
||||
| [ramalama-logout(1)](/docs/commands/ramalama/logout) |logout from remote registry|
|
||||
| [ramalama-perplexity(1)](/docs/commands/ramalama/perplexity)|calculate the perplexity value of an AI Model|
|
||||
| [ramalama-pull(1)](/docs/commands/ramalama/pull) |pull AI Models from Model registries to local storage|
|
||||
| [ramalama-push(1)](/docs/commands/ramalama/push) |push AI Models from local storage to remote registries|
|
||||
| [ramalama-rag(1)](/docs/commands/ramalama/rag) |generate and convert Retrieval Augmented Generation (RAG) data from provided documents into an OCI Image|
|
||||
| [ramalama-rm(1)](/docs/commands/ramalama/rm) |remove AI Models from local storage|
|
||||
| [ramalama-run(1)](/docs/commands/ramalama/run) |run specified AI Model as a chatbot|
|
||||
| [ramalama-serve(1)](/docs/commands/ramalama/serve) |serve REST API on specified AI Model|
|
||||
| [ramalama-stop(1)](/docs/commands/ramalama/stop) |stop named container that is running AI Model|
|
||||
| [ramalama-version(1)](/docs/commands/ramalama/version) |display version of RamaLama|
|
||||
|
||||
## CONFIGURATION FILES
|
||||
|
||||
@@ -195,7 +195,7 @@ although the recommended way is to use the ramalama.conf file.
|
||||
| TMPDIR | directory for temporary files. Defaults to /var/tmp if unset.|
|
||||
|
||||
## See Also
|
||||
[podman(1)](https://github.com/containers/podman/blob/main/docs/source/markdown/podman.1.md), **docker(1)**, [ramalama.conf(5)](../../configuration/conf), [ramalama-cuda(7)](../../platform-guides/cuda), [ramalama-macos(7)](../../platform-guides/macos)
|
||||
[podman(1)](https://github.com/containers/podman/blob/main/docs/source/markdown/podman.1.md), **docker(1)**, [ramalama.conf(5)](/docs/configuration/conf), [ramalama-cuda(7)](/docs/platform-guides/cuda), [ramalama-macos(7)](/docs/platform-guides/macos)
|
||||
|
||||
---
|
||||
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
---
|
||||
title: ramalama rm.1
|
||||
title: rm
|
||||
description: remove AI Models from local storage
|
||||
# This file is auto-generated from manpages. Do not edit manually.
|
||||
# Source: ramalama-rm.1.md
|
||||
---
|
||||
|
||||
# ramalama rm.1
|
||||
# rm
|
||||
|
||||
## Synopsis
|
||||
**ramalama rm** [*options*] *model* [...]
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
---
|
||||
title: ramalama run.1
|
||||
title: run
|
||||
description: run specified AI Model as a chatbot
|
||||
# This file is auto-generated from manpages. Do not edit manually.
|
||||
# Source: ramalama-run.1.md
|
||||
---
|
||||
|
||||
# ramalama run.1
|
||||
# run
|
||||
|
||||
## Synopsis
|
||||
**ramalama run** [*options*] *model* [arg ...]
|
||||
@@ -77,7 +77,7 @@ OCI container image to run with specified AI model. RamaLama defaults to using
|
||||
images based on the accelerator it discovers. For example:
|
||||
`quay.io/ramalama/ramalama`. See the table below for all default images.
|
||||
The default image tag is based on the minor version of the RamaLama package.
|
||||
Version 0.12.1 of RamaLama pulls an image with a `:0.12` tag from the quay.io/ramalama OCI repository. The --image option overrides this default.
|
||||
Version 0.12.3 of RamaLama pulls an image with a `:0.12` tag from the quay.io/ramalama OCI repository. The --image option overrides this default.
|
||||
|
||||
The default can be overridden in the ramalama.conf file or via the
|
||||
RAMALAMA_IMAGE environment variable. `export RAMALAMA_IMAGE=quay.io/ramalama/aiimage:1.2` tells
|
||||
@@ -102,6 +102,11 @@ If GPU device on host system is accessible to user via group access, this option
|
||||
#### **--keepalive**
|
||||
duration to keep a model loaded (e.g. 5m)
|
||||
|
||||
#### **--mcp**=SERVER_URL
|
||||
MCP (Model Context Protocol) servers to use for enhanced tool calling capabilities.
|
||||
Can be specified multiple times to connect to multiple MCP servers.
|
||||
Each server provides tools that can be automatically invoked during chat conversations.
|
||||
|
||||
#### **--name**, **-n**
|
||||
name of the container to run the Model in
|
||||
|
||||
@@ -229,10 +234,10 @@ $ ramalama run granite
|
||||
|
||||
## NVIDIA CUDA Support
|
||||
|
||||
See [ramalama-cuda(7)](../../platform-guides/cuda) for setting up the host Linux system for CUDA support.
|
||||
See [ramalama-cuda(7)](/docs/platform-guides/cuda) for setting up the host Linux system for CUDA support.
|
||||
|
||||
## See Also
|
||||
[ramalama(1)](/docs/commands/ramalama/), [ramalama-cuda(7)](../../platform-guides/cuda)
|
||||
[ramalama(1)](/docs/commands/ramalama/), [ramalama-cuda(7)](/docs/platform-guides/cuda)
|
||||
|
||||
---
|
||||
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
---
|
||||
title: ramalama serve.1
|
||||
title: serve
|
||||
description: serve REST API on specified AI Model
|
||||
# This file is auto-generated from manpages. Do not edit manually.
|
||||
# Source: ramalama-serve.1.md
|
||||
---
|
||||
|
||||
# ramalama serve.1
|
||||
# serve
|
||||
|
||||
## Synopsis
|
||||
**ramalama serve** [*options*] _model_
|
||||
@@ -106,6 +106,7 @@ Generate specified configuration format for running the AI Model as a service
|
||||
| quadlet | Podman supported container definition for running AI Model under systemd |
|
||||
| kube | Kubernetes YAML definition for running the AI Model as a service |
|
||||
| quadlet/kube | Kubernetes YAML definition for running the AI Model as a service and Podman supported container definition for running the Kube YAML specified pod under systemd|
|
||||
| compose | Compose YAML definition for running the AI Model as a service |
|
||||
|
||||
Optionally, an output directory for the generated files can be specified by
|
||||
appending the path to the type, e.g. `--generate kube:/etc/containers/systemd`.
|
||||
@@ -121,7 +122,7 @@ OCI container image to run with specified AI model. RamaLama defaults to using
|
||||
images based on the accelerator it discovers. For example:
|
||||
`quay.io/ramalama/ramalama`. See the table above for all default images.
|
||||
The default image tag is based on the minor version of the RamaLama package.
|
||||
Version 0.12.1 of RamaLama pulls an image with a `:0.12` tag from the quay.io/ramalama OCI repository. The --image option overrides this default.
|
||||
Version 0.12.3 of RamaLama pulls an image with a `:0.12` tag from the quay.io/ramalama OCI repository. The --image option overrides this default.
|
||||
|
||||
The default can be overridden in the ramalama.conf file or via the
|
||||
RAMALAMA_IMAGE environment variable. `export RAMALAMA_IMAGE=quay.io/ramalama/aiimage:1.2` tells
|
||||
@@ -402,6 +403,30 @@ spec:
|
||||
name: dri
|
||||
```
|
||||
|
||||
### Generate Compose file
|
||||
```bash
|
||||
$ ramalama serve --name=my-smollm-server --port 1234 --generate=compose smollm:135m
|
||||
Generating Compose YAML file: docker-compose.yaml
|
||||
$ cat docker-compose.yaml
|
||||
version: '3.8'
|
||||
services:
|
||||
my-smollm-server:
|
||||
image: quay.io/ramalama/ramalama:latest
|
||||
container_name: my-smollm-server
|
||||
command: ramalama serve --host 0.0.0.0 --port 1234 smollm:135m
|
||||
ports:
|
||||
- "1234:1234"
|
||||
volumes:
|
||||
- ~/.local/share/ramalama/models/smollm-135m-instruct:/mnt/models/model.file:ro
|
||||
environment:
|
||||
- HOME=/tmp
|
||||
cap_drop:
|
||||
- ALL
|
||||
security_opt:
|
||||
- no-new-privileges
|
||||
- label=disable
|
||||
```
|
||||
|
||||
### Generate a Llama Stack Kubernetes YAML file named MyLamaStack
|
||||
```bash
|
||||
$ ramalama serve --api llama-stack --name MyLamaStack --generate=kube oci://quay.io/rhatdan/granite:latest
|
||||
@@ -520,7 +545,7 @@ WantedBy=multi-user.target default.target
|
||||
|
||||
## NVIDIA CUDA Support
|
||||
|
||||
See [ramalama-cuda(7)](../../platform-guides/cuda) for setting up the host Linux system for CUDA support.
|
||||
See [ramalama-cuda(7)](/docs/platform-guides/cuda) for setting up the host Linux system for CUDA support.
|
||||
|
||||
## MLX Support
|
||||
|
||||
@@ -544,7 +569,7 @@ ramalama --runtime=mlx serve hf://mlx-community/Unsloth-Phi-4-4bit
|
||||
```
|
||||
|
||||
## See Also
|
||||
[ramalama(1)](/docs/commands/ramalama/), [ramalama-stop(1)](../../commands/ramalama/stop), **quadlet(1)**, **systemctl(1)**, **podman(1)**, **podman-ps(1)**, [ramalama-cuda(7)](../../platform-guides/cuda)
|
||||
[ramalama(1)](/docs/commands/ramalama/), [ramalama-stop(1)](/docs/commands/ramalama/stop), **quadlet(1)**, **systemctl(1)**, **podman(1)**, **podman-ps(1)**, [ramalama-cuda(7)](/docs/platform-guides/cuda)
|
||||
|
||||
---
|
||||
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
---
|
||||
title: ramalama stop.1
|
||||
title: stop
|
||||
description: stop named container that is running AI Model
|
||||
# This file is auto-generated from manpages. Do not edit manually.
|
||||
# Source: ramalama-stop.1.md
|
||||
---
|
||||
|
||||
# ramalama stop.1
|
||||
# stop
|
||||
|
||||
## Synopsis
|
||||
**ramalama stop** [*options*] *name*
|
||||
@@ -38,7 +38,7 @@ $ ramalama stop --all
|
||||
```
|
||||
|
||||
## See Also
|
||||
[ramalama(1)](/docs/commands/ramalama/), [ramalama-run(1)](../../commands/ramalama/run), [ramalama-serve(1)](../../commands/ramalama/serve)
|
||||
[ramalama(1)](/docs/commands/ramalama/), [ramalama-run(1)](/docs/commands/ramalama/run), [ramalama-serve(1)](/docs/commands/ramalama/serve)
|
||||
|
||||
---
|
||||
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
---
|
||||
title: ramalama version.1
|
||||
title: version
|
||||
description: display version of RamaLama
|
||||
# This file is auto-generated from manpages. Do not edit manually.
|
||||
# Source: ramalama-version.1.md
|
||||
---
|
||||
|
||||
# ramalama version.1
|
||||
# version
|
||||
|
||||
## Synopsis
|
||||
**ramalama version**
|
||||
@@ -22,9 +22,9 @@ Print usage message
|
||||
|
||||
```bash
|
||||
$ ramalama version
|
||||
ramalama version 0.12.1
|
||||
ramalama version 0.12.3
|
||||
$ ramalama -q version
|
||||
0.12.1
|
||||
0.12.3
|
||||
>
|
||||
```
|
||||
## See Also
|
||||
|
||||
@@ -7,10 +7,6 @@ description: Configuration file reference
|
||||
|
||||
# Configuration File
|
||||
|
||||
# NAME
|
||||
ramalama.conf - These configuration files specifies default
|
||||
configuration options and command-line flags for RamaLama.
|
||||
|
||||
# DESCRIPTION
|
||||
RamaLama reads all ramalama.conf files, if they exists
|
||||
and modify the defaults for running RamaLama on the host. ramalama.conf uses
|
||||
@@ -71,6 +67,10 @@ The ramalama table contains settings to configure and manage the OCI runtime.
|
||||
Unified API layer for Inference, RAG, Agents, Tools, Safety, Evals, and Telemetry.
|
||||
Options: llama-stack, none
|
||||
|
||||
**api_key**=""
|
||||
|
||||
OpenAI-compatible API key. Can also be set via the RAMALAMA_API_KEY environment variable.
|
||||
|
||||
**carimage**="registry.access.redhat.com/ubi10-micro:latest"
|
||||
|
||||
OCI model car image
|
||||
|
||||
@@ -7,9 +7,6 @@ description: Configuration file reference
|
||||
|
||||
# OCI Spec
|
||||
|
||||
# NAME
|
||||
ramalama-oci - RamaLama oci:// Image Format
|
||||
|
||||
# DESCRIPTION
|
||||
RamaLama’s `oci://` transport uses [OpenContainers image registries](https://github.com/opencontainers/distribution-spec) to store AI models.
|
||||
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
---
|
||||
title: ramalama cann.7
|
||||
title: CANN Setup
|
||||
description: Platform-specific setup guide
|
||||
# This file is auto-generated from manpages. Do not edit manually.
|
||||
# Source: ramalama-cann.7.md
|
||||
---
|
||||
|
||||
# ramalama cann.7
|
||||
# CANN Setup
|
||||
|
||||
# Setting Up RamaLama with Ascend NPU Support on Linux systems
|
||||
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
---
|
||||
title: ramalama cuda.7
|
||||
title: CUDA Setup
|
||||
description: Platform-specific setup guide
|
||||
# This file is auto-generated from manpages. Do not edit manually.
|
||||
# Source: ramalama-cuda.7.md
|
||||
---
|
||||
|
||||
# ramalama cuda.7
|
||||
# CUDA Setup
|
||||
|
||||
# Setting Up RamaLama with CUDA Support on Linux systems
|
||||
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
---
|
||||
title: ramalama macos.7
|
||||
title: macOS Setup
|
||||
description: Platform-specific setup guide
|
||||
# This file is auto-generated from manpages. Do not edit manually.
|
||||
# Source: ramalama-macos.7.md
|
||||
---
|
||||
|
||||
# ramalama macos.7
|
||||
# macOS Setup
|
||||
|
||||
# Configure Podman Machine on Mac for GPU Acceleration
|
||||
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
---
|
||||
title: ramalama musa.7
|
||||
title: MUSA Setup
|
||||
description: Platform-specific setup guide
|
||||
# This file is auto-generated from manpages. Do not edit manually.
|
||||
# Source: ramalama-musa.7.md
|
||||
---
|
||||
|
||||
# ramalama musa.7
|
||||
# MUSA Setup
|
||||
|
||||
# Setting Up RamaLama with MUSA Support on Linux systems
|
||||
|
||||
|
||||
@@ -26,7 +26,12 @@ const config: Config = {
|
||||
projectName: 'ramalama', // Usually your repo name.
|
||||
|
||||
onBrokenLinks: 'throw',
|
||||
onBrokenMarkdownLinks: 'warn',
|
||||
|
||||
markdown: {
|
||||
hooks: {
|
||||
onBrokenMarkdownLinks: 'warn',
|
||||
},
|
||||
},
|
||||
|
||||
// Even if you don't use internationalization, you can use this field to set
|
||||
// useful metadata like html lang. For example, if your site is Chinese, you
|
||||
|
||||
2373
docsite/package-lock.json
generated
2373
docsite/package-lock.json
generated
File diff suppressed because it is too large
Load Diff
@@ -5,6 +5,7 @@
|
||||
"scripts": {
|
||||
"docusaurus": "docusaurus",
|
||||
"start": "docusaurus start",
|
||||
"dev": "docusaurus start",
|
||||
"build": "docusaurus build",
|
||||
"swizzle": "docusaurus swizzle",
|
||||
"deploy": "docusaurus deploy",
|
||||
@@ -15,20 +16,20 @@
|
||||
"typecheck": "tsc"
|
||||
},
|
||||
"dependencies": {
|
||||
"@docusaurus/core": "3.8.1",
|
||||
"@docusaurus/plugin-client-redirects": "^3.8.1",
|
||||
"@docusaurus/preset-classic": "3.8.1",
|
||||
"@mdx-js/react": "^3.0.0",
|
||||
"clsx": "^2.0.0",
|
||||
"prism-react-renderer": "^2.3.0",
|
||||
"react": "^19.0.0",
|
||||
"react-dom": "^19.0.0"
|
||||
"@docusaurus/core": "3.9.1",
|
||||
"@docusaurus/plugin-client-redirects": "^3.9.1",
|
||||
"@docusaurus/preset-classic": "3.9.1",
|
||||
"@mdx-js/react": "^3.1.1",
|
||||
"clsx": "^2.1.1",
|
||||
"prism-react-renderer": "^2.4.1",
|
||||
"react": "^19.1.1",
|
||||
"react-dom": "^19.1.1"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@docusaurus/module-type-aliases": "3.8.1",
|
||||
"@docusaurus/tsconfig": "3.8.1",
|
||||
"@docusaurus/types": "3.8.1",
|
||||
"typescript": "~5.9.0"
|
||||
"@docusaurus/module-type-aliases": "3.9.1",
|
||||
"@docusaurus/tsconfig": "3.9.1",
|
||||
"@docusaurus/types": "3.9.1",
|
||||
"typescript": "~5.9.3"
|
||||
},
|
||||
"browserslist": {
|
||||
"production": [
|
||||
|
||||
Reference in New Issue
Block a user