This repository provides a set of ROS 2 packages to integrate llama.cpp into ROS 2. Using the llama_ros packages, you can easily incorporate the powerful optimization capabilities of llama.cpp into your ROS 2 projects by running GGUF-based LLMs and VLMs. You can also use features from llama.cpp such as GBNF grammars and modify LoRAs in real-time.

ROS 2 Distro	Branch	Build status	Docker Image	Documentation
Humble	`main`

Related Projects

chatbot_ros → This chatbot, integrated into ROS 2, uses whisper_ros, to listen to people speech; and llama_ros, to generate responses. The chatbot is controlled by a state machine created with YASMIN.
explainable_ros → A ROS 2 tool to explain the behavior of a robot. Using the integration of LangChain, logs are stored in a vector database. Then, RAG is applied to retrieve relevant logs for user questions answered with llama_ros.

Installation

To run llama_ros with CUDA, first, you must install the CUDA Toolkit. Then, you can compile llama_ros with --cmake-args -DGGML_CUDA=ON to enable CUDA support.

cd ~/ros2_ws/src
git clone https://github.com/mgonzs13/llama_ros.git
pip3 install -r llama_ros/requirements.txt
cd ~/ros2_ws
rosdep install --from-paths src --ignore-src -r -y
colcon build --cmake-args -DGGML_CUDA=ON # add this for CUDA

Docker

Build the llama_ros docker or download an image from DockerHub. You can choose to build llama_ros with CUDA (USE_CUDA) and choose the CUDA version (CUDA_VERSION). Remember that you have to use DOCKER_BUILDKIT=0 to compile llama_ros with CUDA when building the image.

DOCKER_BUILDKIT=0 docker build -t llama_ros --build-arg USE_CUDA=1 --build-arg CUDA_VERSION=12-6 .

Run the docker container. If you want to use CUDA, you have to install the NVIDIA Container Tollkit and add --gpus all.

docker run -it --rm --gpus all llama_ros

Usage

llama_cli

Commands are included in llama_ros to speed up the test of GGUF-based LLMs within the ROS 2 ecosystem. This way, the following commands are integrating into the ROS 2 commands:

launch

Using this command launch a LLM from a YAML file. The configuration of the YAML is used to launch the LLM in the same way as using a regular launch file. Here is an example of how to use it:

ros2 llama launch ~/ros2_ws/src/llama_ros/llama_bringup/models/StableLM-Zephyr.yaml

prompt

Using this command send a prompt to a launched LLM. The command uses a string, which is the prompt and has the following arguments:

(-r, --reset): Whether to reset the LLM before prompting
(-t, --temp): The temperature value
(--image-url): Image url to sent to a VLM

Here is an example of how to use it:

ros2 llama prompt "Do you know ROS 2?" -t 0.0

Launch Files

First of all, you need to create a launch file to use llama_ros or llava_ros. This launch file will contain the main parameters to download the model from HuggingFace and configure it. Take a look at the following examples and the predefined launch files.

llama_ros (Python Launch)

Click to expand

from launch import LaunchDescription
from llama_bringup.utils import create_llama_launch
 
 
def generate_launch_description():
 
    return LaunchDescription([
        create_llama_launch(
            n_ctx=2048, # context of the LLM in tokens
            n_batch=8, # batch size in tokens
            n_gpu_layers=0, # layers to load in GPU
            n_threads=1, # threads
            n_predict=2048, # max tokens, -1 == inf
 
            model_repo="TheBloke/Marcoroni-7B-v3-GGUF", # Hugging Face repo
            model_filename="marcoroni-7b-v3.Q4_K_M.gguf", # model file in repo
 
            system_prompt_type="Alpaca" # system prompt type
        )
    ])

ros2 launch llama_bringup marcoroni.launch.py

llama_ros (YAML Config)

Click to expand

n_ctx: 2048 # context of the LLM in tokens
n_batch: 8 # batch size in tokens
n_gpu_layers: 0 # layers to load in GPU
n_threads: 1 # threads
n_predict: 2048 # max tokens, -1 == inf
 
model_repo: "cstr/Spaetzle-v60-7b-GGUF" # Hugging Face repo
model_filename: "Spaetzle-v60-7b-q4-k-m.gguf" # model file in repo
 
system_prompt_type: "Alpaca" # system prompt type

import os
from launch import LaunchDescription
from llama_bringup.utils import create_llama_launch_from_yaml
from ament_index_python.packages import get_package_share_directory
 
 
def generate_launch_description():
    return LaunchDescription([
        create_llama_launch_from_yaml(os.path.join(
            get_package_share_directory("llama_bringup"), "models", "Spaetzle.yaml"))
    ])

ros2 launch llama_bringup spaetzle.launch.py

llama_ros (YAML Config + model shards)

Click to expand

n_ctx: 2048 # context of the LLM in tokens
n_batch: 8 # batch size in tokens
n_gpu_layers: 0 # layers to load in GPU
n_threads: 1 # threads
n_predict: 2048 # max tokens, -1 == inf
 
model_repo: "Qwen/Qwen2.5-Coder-7B-Instruct-GGUF" # Hugging Face repo
model_filename: "qwen2.5-coder-7b-instruct-q4_k_m-00001-of-00002.gguf" # model shard file in repo
 
system_prompt_type: "ChatML" # system prompt type

ros2 llama launch Qwen2.yaml

llava_ros (Python Launch)

Click to expand

from launch import LaunchDescription
from llama_bringup.utils import create_llama_launch
 
def generate_launch_description():
 
    return LaunchDescription([
        create_llama_launch(
            use_llava=True, # enable llava
 
            n_ctx=8192, # context of the LLM in tokens, use a huge context size to load images
            n_batch=512, # batch size in tokens
            n_gpu_layers=33, # layers to load in GPU
            n_threads=1, # threads
            n_predict=8192, # max tokens, -1 == inf
 
            model_repo="cjpais/llava-1.6-mistral-7b-gguf", # Hugging Face repo
            model_filename="llava-v1.6-mistral-7b.Q4_K_M.gguf", # model file in repo
 
            mmproj_repo="cjpais/llava-1.6-mistral-7b-gguf", # Hugging Face repo
            mmproj_filename="mmproj-model-f16.gguf", # mmproj file in repo
 
            system_prompt_type="Mistral" # system prompt type
        )
    ])

ros2 launch llama_bringup llava.launch.py

llava_ros (YAML Config)

Click to expand

use_llava: True # enable llava
 
n_ctx: 8192 # context of the LLM in tokens use a huge context size to load images
n_batch: 512 # batch size in tokens
n_gpu_layers: 33 # layers to load in GPU
n_threads: 1 # threads
n_predict: 8192 # max tokens -1 : :  inf
 
model_repo: "cjpais/llava-1.6-mistral-7b-gguf" # Hugging Face repo
model_filename: "llava-v1.6-mistral-7b.Q4_K_M.gguf" # model file in repo
 
mmproj_repo: "cjpais/llava-1.6-mistral-7b-gguf" # Hugging Face repo
mmproj_filename: "mmproj-model-f16.gguf" # mmproj file in repo
 
system_prompt_type: "mistral" # system prompt type

def generate_launch_description():
    return LaunchDescription([
        create_llama_launch_from_yaml(os.path.join(
            get_package_share_directory("llama_bringup"),
            "models", "llava-1.6-mistral-7b-gguf.yaml"))
    ])

ros2 launch llama_bringup llava.launch.py

LoRA Adapters

You can use LoRA adapters when launching LLMs. Using llama.cpp features, you can load multiple adapters choosing the scale to apply for each adapter. Here you have an example of using LoRA adapters with Phi-3. You can lis the LoRAs using the /llama/list_loras service and modify their scales values by using the /llama/update_loras service. A scale value of 0.0 means not using that LoRA.

Click to expand

n_ctx: 2048
n_batch: 8
n_gpu_layers: 0
n_threads: 1
n_predict: 2048
 
model_repo: "bartowski/Phi-3.5-mini-instruct-GGUF"
model_filename: "Phi-3.5-mini-instruct-Q4_K_M.gguf"
 
lora_adapters:
  - repo: "zhhan/adapter-Phi-3-mini-4k-instruct_code_writing"
    filename: "Phi-3-mini-4k-instruct-adaptor-f16-code_writer.gguf"
    scale: 0.5
  - repo: "zhhan/adapter-Phi-3-mini-4k-instruct_summarization"
    filename: "Phi-3-mini-4k-instruct-adaptor-f16-summarization.gguf"
    scale: 0.5
 
system_prompt_type: "Phi-3"

ROS 2 Clients

Both llama_ros and llava_ros provide ROS 2 interfaces to access the main functionalities of the models. Here you have some examples of how to use them inside ROS 2 nodes. Moreover, take a look to the llama_demo_node.py and llava_demo_node.py demos.

Tokenize

Click to expand

from rclpy.node import Node
from llama_msgs.srv import Tokenize
 
 
class ExampleNode(Node):
    def __init__(self) -> None:
        super().__init__("example_node")
 
        # create the client
        self.srv_client = self.create_client(Tokenize, "/llama/tokenize")
 
        # create the request
        req = Tokenize.Request()
        req.text = "Example text"
 
        # call the tokenize service
        self.srv_client.wait_for_service()
        tokens = self.srv_client.call(req).tokens

Detokenize

Click to expand

from rclpy.node import Node
from llama_msgs.srv import Detokenize
 
 
class ExampleNode(Node):
    def __init__(self) -> None:
        super().__init__("example_node")
 
        # create the client
        self.srv_client = self.create_client(Detokenize, "/llama/detokenize")
 
        # create the request
        req = Detokenize.Request()
        req.tokens = [123, 123]
 
        # call the tokenize service
        self.srv_client.wait_for_service()
        text = self.srv_client.call(req).text

Embeddings

Click to expand

Remember to launch llama_ros with embedding set to true to be able of generating embeddings with your LLM.

from rclpy.node import Node
from llama_msgs.srv import Embeddings
 
 
class ExampleNode(Node):
    def __init__(self) -> None:
        super().__init__("example_node")
 
        # create the client
        self.srv_client = self.create_client(Embeddings, "/llama/generate_embeddings")
 
        # create the request
        req = Embeddings.Request()
        req.prompt = "Example text"
        req.normalize = True
 
        # call the embedding service
        self.srv_client.wait_for_service()
        embeddings = self.srv_client.call(req).embeddings

Generate Response

Click to expand

import rclpy
from rclpy.node import Node
from rclpy.action import ActionClient
from llama_msgs.action import GenerateResponse
 
 
class ExampleNode(Node):
    def __init__(self) -> None:
        super().__init__("example_node")
 
        # create the client
        self.action_client = ActionClient(
            self, GenerateResponse, "/llama/generate_response")
 
        # create the goal and set the sampling config
        goal = GenerateResponse.Goal()
        goal.prompt = self.prompt
        goal.sampling_config.temp = 0.2
 
        # wait for the server and send the goal
        self.action_client.wait_for_server()
        send_goal_future = self.action_client.send_goal_async(
            goal)
 
        # wait for the server
        rclpy.spin_until_future_complete(self, send_goal_future)
        get_result_future = send_goal_future.result().get_result_async()
 
        # wait again and take the result
        rclpy.spin_until_future_complete(self, get_result_future)
        result: GenerateResponse.Result = get_result_future.result().result

Generate Response (llava)

Click to expand

import cv2
from cv_bridge import CvBridge
 
import rclpy
from rclpy.node import Node
from rclpy.action import ActionClient
from llama_msgs.action import GenerateResponse
 
 
class ExampleNode(Node):
    def __init__(self) -> None:
        super().__init__("example_node")
 
        # create a cv bridge for the image
        self.cv_bridge = CvBridge()
 
        # create the client
        self.action_client = ActionClient(
            self, GenerateResponse, "/llama/generate_response")
 
        # create the goal and set the sampling config
        goal = GenerateResponse.Goal()
        goal.prompt = self.prompt
        goal.sampling_config.temp = 0.2
 
        # add your image to the goal
        image = cv2.imread("/path/to/your/image", cv2.IMREAD_COLOR)
        goal.image = self.cv_bridge.cv2_to_imgmsg(image)
 
        # wait for the server and send the goal
        self.action_client.wait_for_server()
        send_goal_future = self.action_client.send_goal_async(
            goal)
 
        # wait for the server
        rclpy.spin_until_future_complete(self, send_goal_future)
        get_result_future = send_goal_future.result().get_result_async()
 
        # wait again and take the result
        rclpy.spin_until_future_complete(self, get_result_future)
        result: GenerateResponse.Result = get_result_future.result().result

LangChain

There is a llama_ros integration for LangChain. Thus, prompt engineering techniques could be applied. Here you have an example to use it.

llama_ros (Chain)

Click to expand

import rclpy
from llama_ros.langchain import LlamaROS
from langchain.prompts import PromptTemplate
from langchain_core.output_parsers import StrOutputParser
 
 
rclpy.init()
 
# create the llama_ros llm for langchain
llm = LlamaROS()
 
# create a prompt template
prompt_template = "tell me a joke about {topic}"
prompt = PromptTemplate(
    input_variables=["topic"],
    template=prompt_template
)
 
# create a chain with the llm and the prompt template
chain = prompt | llm | StrOutputParser()
 
# run the chain
text = chain.invoke({"topic": "bears"})
print(text)
 
rclpy.shutdown()

llama_ros (Stream)

Click to expand

import rclpy
from llama_ros.langchain import LlamaROS
from langchain.prompts import PromptTemplate
from langchain_core.output_parsers import StrOutputParser
 
 
rclpy.init()
 
# create the llama_ros llm for langchain
llm = LlamaROS()
 
# create a prompt template
prompt_template = "tell me a joke about {topic}"
prompt = PromptTemplate(
    input_variables=["topic"],
    template=prompt_template
)
 
# create a chain with the llm and the prompt template
chain = prompt | llm | StrOutputParser()
 
# run the chain
for c in chain.stream({"topic": "bears"}):
    print(c, flush=True, end="")
 
rclpy.shutdown()

llava_ros

Click to expand

import rclpy
from llama_ros.langchain import LlamaROS
 
rclpy.init()
 
# create the llama_ros llm for langchain
llm = LlamaROS()
 
# bind the url_image
image_url = "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
llm = llm.bind(image_url=image_url).stream("Describe the image")
 
# run the llm
for c in llm:
    print(c, flush=True, end="")
 
rclpy.shutdown()

llama_ros_embeddings (RAG)

Click to expand

import rclpy
from langchain_chroma import Chroma
from llama_ros.langchain import LlamaROSEmbeddings
 
 
rclpy.init()
 
# create the llama_ros embeddings for langchain
embeddings = LlamaROSEmbeddings()
 
# create a vector database and assign it
db = Chroma(embedding_function=embeddings)
 
# create the retriever
retriever = db.as_retriever(search_kwargs={"k": 5})
 
# add your texts
db.add_texts(texts=["your_texts"])
 
# retrieve documents
documents = retriever.invoke("your_query")
print(documents)
 
rclpy.shutdown()

llama_ros (Renranker)

Click to expand

import rclpy
from llama_ros.langchain import LlamaROSReranker
from llama_ros.langchain import LlamaROSEmbeddings
 
from langchain_community.vectorstores import FAISS
from langchain_community.document_loaders import TextLoader
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain.retrievers import ContextualCompressionRetriever
 
 
rclpy.init()
 
# load the documents
documents = TextLoader("../state_of_the_union.txt",).load()
text_splitter = RecursiveCharacterTextSplitter(
    chunk_size=500, chunk_overlap=100)
texts = text_splitter.split_documents(documents)
 
# create the llama_ros embeddings
embeddings = LlamaROSEmbeddings()
 
# create the VD and the retriever
retriever = FAISS.from_documents(
    texts, embeddings).as_retriever(search_kwargs={"k": 20})
 
# create the compressor using the llama_ros reranker
compressor = LlamaROSReranker()
compression_retriever = ContextualCompressionRetriever(
    base_compressor=compressor, base_retriever=retriever
)
 
# retrieve the documents
compressed_docs = compression_retriever.invoke(
    "What did the president say about Ketanji Jackson Brown"
)
 
for doc in compressed_docs:
    print("-" * 50)
    print(doc.page_content)
    print("\n")
 
rclpy.shutdown()

llama_ros (LLM + RAG + Reranker)

Click to expand

import bs4
import rclpy
 
from langchain_chroma import Chroma
from langchain_community.document_loaders import WebBaseLoader
from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnablePassthrough
from langchain_core.messages import SystemMessage
from langchain_core.prompts import ChatPromptTemplate, HumanMessagePromptTemplate
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain.retrievers import ContextualCompressionRetriever
 
from llama_ros.langchain import ChatLlamaROS, LlamaROSEmbeddings, LlamaROSReranker
 
 
rclpy.init()
 
# load, chunk and index the contents of the blog
loader = WebBaseLoader(
    web_paths=("https://lilianweng.github.io/posts/2023-06-23-agent/",),
    bs_kwargs=dict(
        parse_only=bs4.SoupStrainer(class_=("post-content", "post-title", "post-header"))
    ),
)
docs = loader.load()
 
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
splits = text_splitter.split_documents(docs)
vectorstore = Chroma.from_documents(documents=splits, embedding=LlamaROSEmbeddings())
 
# retrieve and generate using the relevant snippets of the blog
retriever = vectorstore.as_retriever(search_kwargs={"k": 20})
 
# create prompt
prompt = ChatPromptTemplate.from_messages(
    [
        SystemMessage("You are an AI assistant that answer questions briefly."),
        HumanMessagePromptTemplate.from_template(
            "Taking into account the followin information:{context}\n\n{question}"
        ),
    ]
)
 
# create rerank compression retriever
compressor = LlamaROSReranker(top_n=3)
compression_retriever = ContextualCompressionRetriever(
    base_compressor=compressor, base_retriever=retriever
)
 
 
def format_docs(docs):
    formated_docs = ""
 
    for d in docs:
        formated_docs += f"\n\n\t- {d.page_content}"
 
    return formated_docs
 
 
# create and use the chain
rag_chain = (
    {"context": compression_retriever | format_docs, "question": RunnablePassthrough()}
    | prompt
    | ChatLlamaROS(temp=0.0)
    | StrOutputParser()
)
 
for c in rag_chain.stream("What is Task Decomposition?"):
    print(c, flush=True, end="")
 
rclpy.shutdown()

chat_llama_ros (Chat + VLM)

Click to expand

import rclpy
from llama_ros.langchain import ChatLlamaROS
from langchain_core.messages import SystemMessage
from langchain_core.prompts import ChatPromptTemplate, HumanMessagePromptTemplate
from langchain_core.output_parsers import StrOutputParser
 
 
rclpy.init()
 
# create chat
chat = ChatLlamaROS(
    temp=0.2,
    penalty_last_n=8,
)
 
# create prompt template with messages
prompt = ChatPromptTemplate.from_messages([
    SystemMessage("You are a IA that just answer with a single word."),
    HumanMessagePromptTemplate.from_template(template=[
        {"type": "text", "text": "<image>Who is the character in the middle of the image?"},
        {"type": "image_url", "image_url": "{image_url}"}
    ])
])
 
# create the chain
chain = prompt | chat | StrOutputParser()
 
# stream and print the LLM output
for text in chain.stream({"image_url": "https://pics.filmaffinity.com/Dragon_Ball_Bola_de_Dragaon_Serie_de_TV-973171538-large.jpg"}):
    print(text, end="", flush=True)
 
print("", end="\n", flush=True)
 
rclpy.shutdown()

chat_llama_ros (Tools)

Click to expand

The current implementation of Tools allows executing tools without requiring a model trained for that task.

import time
from random import randint
 
import rclpy
 
from langchain.tools import tool
from langchain_core.messages import HumanMessage
from llama_ros.langchain import ChatLlamaROS
 
rclpy.init()
 
@tool
def get_inhabitants(city: str) -> int:
    """Get the current temperature of a city"""
    return randint(4_000_000, 8_000_000)
 
 
@tool
def get_curr_temperature(city: str) -> int:
    """Get the current temperature of a city"""
    return randint(20, 30)
 
chat = ChatLlamaROS(temp=0.6, penalty_last_n=8, use_default_template=True)
 
messages = [
    HumanMessage(
        "What is the current temperature in Madrid? And its inhabitants?"
    )
]
 
llm_tools = chat.bind_tools(
    [get_inhabitants, get_curr_temperature], tool_choice='any'
)
 
all_tools_res = llm_tools.invoke(messages)
messages.append(all_tools_res)
 
for tool in all_tools_res.tool_calls:
    selected_tool = {
        "get_inhabitants": get_inhabitants, "get_curr_temperature": get_curr_temperature
    }[tool['name']]
 
    tool_msg = selected_tool.invoke(tool)
 
    formatted_output = f"{tool['name']}({''.join(tool['args'].values())}) = {tool_msg.content}"
 
    tool_msg.additional_kwargs = {'args': tool['args']}
    messages.append(tool_msg)
 
res = chat.invoke(messages)
 
print(f"Response: {res.content}")
 
rclpy.shutdown()

chat_llama_ros (langgraph)

Click to expand

import time
from random import randint
 
import rclpy
 
from langchain.tools import tool
from langchain_core.messages import HumanMessage
from langgraph.prebuilt import create_react_agent
from llama_ros.langchain import ChatLlamaROS
 
rclpy.init()
 
@tool
def get_inhabitants(city: str) -> int:
    """Get the current temperature of a city"""
    return randint(4_000_000, 8_000_000)
 
 
@tool
def get_curr_temperature(city: str) -> int:
    """Get the current temperature of a city"""
    return randint(20, 30)
 
chat = ChatLlamaROS(temp=0.0, use_default_template=True)
 
agent_executor = create_react_agent(
    self.chat, [get_inhabitants, get_curr_temperature]
)
 
response = self.agent_executor.invoke(
    {
        "messages": [
            HumanMessage(
                content="What is the current temperature in Madrid? And its inhabitants?"
            )
        ]
    }
)
 
print(f"Response: {response['messages'][-1].content}")
 
rclpy.shutdown()

Demos

LLM Demo

ros2 launch llama_bringup spaetzle.launch.py

ros2 run llama_demos llama_demo_node --ros-args -p prompt:="your prompt"

https://github.com/mgonzs13/llama_ros/assets/25979134/9311761b-d900-4e58-b9f8-11c8efefdac4

Embeddings Generation Demo

ros2 llama launch ~/ros2_ws/src/llama_ros/llama_bringup/models/bge-base-en-v1.5.yaml

ros2 run llama_demos llama_embeddings_demo_node

https://github.com/user-attachments/assets/7d722017-27dc-417c-ace7-bf6b747e4ced

Reranking Demo

ros2 llama launch ~/ros2_ws/src/llama_ros/llama_bringup/models/jina-reranker.yaml

ros2 run llama_demos llama_rerank_demo_node

https://github.com/user-attachments/assets/4b4adb4d-7c70-43ea-a2c1-9be57d211484

VLM Demo

ros2 launch llama_bringup minicpm-2.6.launch.py

ros2 run llama_demos llava_demo_node --ros-args -p prompt:="your prompt" -p image_url:="url of the image" -p use_image:="whether to send the image"

https://github.com/mgonzs13/llama_ros/assets/25979134/4a9ef92f-9099-41b4-8350-765336e3503c

Chat Template Demo

ros2 llama launch MiniCPM-2.6.yaml

Click to expand MiniCPM-2.6.yaml

use_llava: True
 
n_ctx: 8192
n_batch: 512
n_gpu_layers: 20
n_threads: -1
n_predict: 8192
 
image_prefix: "<image>"
image_suffix: "</image>"
 
model_repo: "openbmb/MiniCPM-V-2_6-gguf"
model_filename: "ggml-model-Q4_K_M.gguf"
 
mmproj_repo: "openbmb/MiniCPM-V-2_6-gguf"
mmproj_filename: "mmproj-model-f16.gguf"
 
stopping_words: ["<|im_end|>"]

ros2 run llama_demos chatllama_demo_node

ChatLlamaROS demo

Tools Demo

ros2 llama launch MiniCPM-2.6.yaml

ros2 run llama_demos chatllama_tools_demo_node

Tools ChatLlama

Langgraph Demo

ros2 llama launch Qwen2.yaml

Click to expand Qwen2.yaml

_ctx: 4096
n_batch: 256
n_gpu_layers: 29
n_threads: -1
n_predict: -1
 
model_repo: "Qwen/Qwen2.5-Coder-7B-Instruct-GGUF"
model_filename: "qwen2.5-coder-7b-instruct-q4_k_m-00001-of-00002.gguf"
 
stopping_words: ["<|im_end|>"]

ros2 run llama_demos chatllama_langgraph_demo_node

Langgraph ChatLlama

RAG Demo (LLM + chat template + RAG + Reranking + Stream)

ros2 llama launch ~/ros2_ws/src/llama_ros/llama_bringup/models/bge-base-en-v1.5.yaml

ros2 llama launch ~/ros2_ws/src/llama_ros/llama_bringup/models/jina-reranker.yaml

ros2 llama launch Qwen2.yaml

Click to expand Qwen2.yaml

_ctx: 4096
n_batch: 256
n_gpu_layers: 29
n_threads: -1
n_predict: -1
 
model_repo: "Qwen/Qwen2.5-Coder-3B-Instruct-GGUF"
model_filename: "qwen2.5-coder-3b-instruct-q4_k_m.gguf"
 
stopping_words: ["<|im_end|>"]

ros2 run llama_demos llama_rag_demo_node

https://github.com/user-attachments/assets/b4e3957d-1f92-427b-a1a8-cfc76737c0d6

Table of Contents

Related Projects

Installation

Docker

Usage

llama_cli

launch

prompt

Launch Files

llama_ros (Python Launch)

llama_ros (YAML Config)

llama_ros (YAML Config + model shards)

llava_ros (Python Launch)

llava_ros (YAML Config)

LoRA Adapters

ROS 2 Clients

Tokenize

Detokenize

Embeddings

Generate Response

Generate Response (llava)

LangChain

llama_ros (Chain)

llama_ros (Stream)

llava_ros

llama_ros_embeddings (RAG)

llama_ros (Renranker)

llama_ros (LLM + RAG + Reranker)

chat_llama_ros (Chat + VLM)

chat_llama_ros (Tools)

chat_llama_ros (langgraph)

Demos

LLM Demo

Embeddings Generation Demo

Reranking Demo

VLM Demo

Chat Template Demo

Tools Demo

Langgraph Demo

RAG Demo (LLM + chat template + RAG + Reranking + Stream)