Daria Fokina 3e81ec75dc
docs: add 2.18 and 2.19 actual documentation pages (#9946)
* versioned-docs

* external-documentstores
2025-10-27 13:03:22 +01:00

253 lines
11 KiB
Plaintext

---
title: "LlamaCppChatGenerator"
id: llamacppchatgenerator
slug: "/llamacppchatgenerator"
description: "`LlamaCppGenerator` enables chat completion using an LLM running on Llama.cpp."
---
# LlamaCppChatGenerator
`LlamaCppGenerator` enables chat completion using an LLM running on Llama.cpp.
| | |
| :------------------------------------- | :------------------------------------------------------------------------------------------------------------------------ |
| **Most common position in a pipeline** | After a [`ChatPromptBuilder`](../builders/chatpromptbuilder.mdx) |
| **Mandatory init variables** | "model": The path of the model to use |
| **Mandatory run variables** | “messages”: A list of [`ChatMessage`](/docs/data-classes#chatmessage) instances representing the input messages |
| **Output variables** | “replies”: A list of [`ChatMessage`](/docs/data-classes#chatmessage) instances with all the replies generated by the LLM |
| **API reference** | [Llama.cpp](/reference/integrations-llama-cpp) |
| **GitHub link** | https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/llama_cpp |
## Overview
[Llama.cpp](https://github.com/ggerganov/llama.cpp) is a library written in C/C++ for efficient inference of Large Language Models. It leverages the efficient quantized GGUF format, dramatically reducing memory requirements and accelerating inference. This means it is possible to run LLMs efficiently on standard machines (even without GPUs).
`Llama.cpp` uses the quantized binary file of the LLM in GGUF format, which can be downloaded from [Hugging Face](https://huggingface.co/models?library=gguf). `LlamaCppChatGenerator` supports models running on `Llama.cpp` by taking the path to the locally saved GGUF file as `model` parameter at initialization.
## Installation
Install the `llama-cpp-haystack` package to use this integration:
```shell
pip install llama-cpp-haystack
```
### Using a different compute backend
The default installation behavior is to build `llama.cpp` for CPU on Linux and Windows and use Metal on MacOS. To use other compute backends:
1. Follow instructions on the [llama.cpp installation page](https://github.com/abetlen/llama-cpp-python#installation) to install [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) for your preferred compute backend.
2. Install [llama-cpp-haystack](https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/llama_cpp) using the command above.
For example, to use `llama-cpp-haystack` with the **cuBLAS backend**, you have to run the following commands:
```shell
export GGML_CUDA=1
CMAKE_ARGS="-DGGML_CUDA=on" pip install llama-cpp-python
pip install llama-cpp-haystack
```
## Usage
1. Download the GGUF version of the desired LLM. The GGUF versions of popular models can be downloaded from [Hugging Face](https://huggingface.co/models?library=gguf).
2. Initialize `LlamaCppChatGenerator` with the path to the GGUF file and specify the required model and text generation parameters:
```python
from haystack_integrations.components.generators.llama_cpp import LlamaCppChatGenerator
generator = LlamaCppChatGenerator(
model="/content/openchat-3.5-1210.Q3_K_S.gguf",
n_ctx=512,
n_batch=128,
model_kwargs={"n_gpu_layers": -1},
generation_kwargs={"max_tokens": 128, "temperature": 0.1},
)
generator.warm_up()
messages = [ChatMessage.from_user("Who is the best American actor?")]
result = generator.run(messages)
```
### Passing additional model parameters
The `model`, `n_ctx`, `n_batch` arguments have been exposed for convenience and can be directly passed to the Generator during initialization as keyword arguments. Note that `model` translates to `llama.cpp`'s `model_path` parameter.
The `model_kwargs` parameter can pass additional arguments when initializing the model. In case of duplication, these parameters override the `model`, `n_ctx`, and `n_batch` initialization parameters.
See [Llama.cpp's LLM documentation](https://llama-cpp-python.readthedocs.io/en/latest/api-reference/#llama_cpp.Llama.__init__) for more information on the available model arguments.
**Note**: Llama.cpp automatically extracts the `chat_template` from the model metadata for applying formatting to ChatMessages. You can override the `chat_template` used by passing in a custom `chat_handler` or `chat_format` as a model parameter.
For example, to offload the model to GPU during initialization:
```python
from haystack_integrations.components.generators.llama_cpp import LlamaCppChatGenerator
from haystack.dataclasses import ChatMessage
generator = LlamaCppChatGenerator(
model="/content/openchat-3.5-1210.Q3_K_S.gguf",
n_ctx=512,
n_batch=128,
model_kwargs={"n_gpu_layers": -1}
)
generator.warm_up()
messages = [ChatMessage.from_user("Who is the best American actor?")]
result = generator.run(messages, generation_kwargs={"max_tokens": 128})
generated_reply = result["replies"][0].content
print(generated_reply)
```
### Passing text generation parameters
The `generation_kwargs` parameter can pass additional generation arguments like `max_tokens`, `temperature`, `top_k`, `top_p`, and others to the model during inference.
See [Llama.cpp's Chat Completion API documentation](https://llama-cpp-python.readthedocs.io/en/latest/api-reference/#llama_cpp.Llama.create_chat_completion) for more information on the available generation arguments.
**Note**: JSON mode, Function Calling, and Tools are all supported as `generation_kwargs`. Please see the [llama-cpp-python GitHub README](https://github.com/abetlen/llama-cpp-python?tab=readme-ov-file#json-and-json-schema-mode) for more information on how to use them.
For example, to set the `max_tokens` and `temperature`:
```python
from haystack_integrations.components.generators.llama_cpp import LlamaCppChatGenerator
from haystack.dataclasses import ChatMessage
generator = LlamaCppChatGenerator(
model="/content/openchat-3.5-1210.Q3_K_S.gguf",
n_ctx=512,
n_batch=128,
generation_kwargs={"max_tokens": 128, "temperature": 0.1},
)
generator.warm_up()
messages = [ChatMessage.from_user("Who is the best American actor?")]
result = generator.run(messages)
```
The `generation_kwargs` can also be passed to the `run` method of the generator directly:
```python
from haystack_integrations.components.generators.llama_cpp import LlamaCppChatGenerator
from haystack.dataclasses import ChatMessage
generator = LlamaCppChatGenerator(
model="/content/openchat-3.5-1210.Q3_K_S.gguf",
n_ctx=512,
n_batch=128,
)
generator.warm_up()
messages = [ChatMessage.from_user("Who is the best American actor?")]
result = generator.run(
messages,
generation_kwargs={"max_tokens": 128, "temperature": 0.1},
)
```
### In a pipeline
We use the `LlamaCppChatGenerator` in a Retrieval Augmented Generation pipeline on the [Simple Wikipedia](https://huggingface.co/datasets/pszemraj/simple_wikipedia) Dataset from Hugging Face and generate answers using the [OpenChat-3.5](https://huggingface.co/openchat/openchat-3.5-1210) LLM.
Load the dataset:
```python
## Install HuggingFace Datasets using "pip install datasets"
from datasets import load_dataset
from haystack import Document, Pipeline
from haystack.components.builders.answer_builder import AnswerBuilder
from haystack.components.builders import ChatPromptBuilder
from haystack.components.embedders import SentenceTransformersDocumentEmbedder, SentenceTransformersTextEmbedder
from haystack.components.retrievers.in_memory import InMemoryEmbeddingRetriever
from haystack.components.writers import DocumentWriter
from haystack.document_stores.in_memory import InMemoryDocumentStore
from haystack.dataclasses import ChatMessage
## Import LlamaCppChatGenerator
from haystack_integrations.components.generators.llama_cpp import LlamaCppChatGenerator
## Load first 100 rows of the Simple Wikipedia Dataset from HuggingFace
dataset = load_dataset("pszemraj/simple_wikipedia", split="validation[:100]")
docs = [
Document(
content=doc["text"],
meta={
"title": doc["title"],
"url": doc["url"],
},
)
for doc in dataset
]
```
Index the documents to the `InMemoryDocumentStore` using the `SentenceTransformersDocumentEmbedder` and `DocumentWriter`:
```python
doc_store = InMemoryDocumentStore(embedding_similarity_function="cosine")
## Install sentence transformers using "pip install sentence-transformers"
doc_embedder = SentenceTransformersDocumentEmbedder(model="sentence-transformers/all-MiniLM-L6-v2")
## Indexing Pipeline
indexing_pipeline = Pipeline()
indexing_pipeline.add_component(instance=doc_embedder, name="DocEmbedder")
indexing_pipeline.add_component(instance=DocumentWriter(document_store=doc_store), name="DocWriter")
indexing_pipeline.connect("DocEmbedder", "DocWriter")
indexing_pipeline.run({"DocEmbedder": {"documents": docs}})
```
Create the RAG pipeline and add the `LlamaCppChatGenerator` to it:
```python
system_message = ChatMessage.from_system(
"""
Answer the question using the provided context.
Context:
{% for doc in documents %}
{{ doc.content }}
{% endfor %}
"""
)
user_message = ChatMessage.from_user("Question: {{question}}")
assistent_message = ChatMessage.from_assistant("Answer: ")
chat_template = [system_message, user_message, assistent_message]
rag_pipeline = Pipeline()
text_embedder = SentenceTransformersTextEmbedder(model="sentence-transformers/all-MiniLM-L6-v2")
## Load the LLM using LlamaCppChatGenerator
model_path = "openchat-3.5-1210.Q3_K_S.gguf"
generator = LlamaCppChatGenerator(model=model_path, n_ctx=4096, n_batch=128)
rag_pipeline.add_component(
instance=text_embedder,
name="text_embedder",
)
rag_pipeline.add_component(instance=InMemoryEmbeddingRetriever(document_store=doc_store, top_k=3), name="retriever")
rag_pipeline.add_component(instance=ChatPromptBuilder(template=chat_template), name="prompt_builder")
rag_pipeline.add_component(instance=generator, name="llm")
rag_pipeline.add_component(instance=AnswerBuilder(), name="answer_builder")
rag_pipeline.connect("text_embedder", "retriever")
rag_pipeline.connect("retriever", "prompt_builder.documents")
rag_pipeline.connect("prompt_builder", "llm")
rag_pipeline.connect("llm", "answer_builder")
rag_pipeline.connect("retriever", "answer_builder.documents")
```
Run the pipeline:
```python
question = "Which year did the Joker movie release?"
result = rag_pipeline.run(
{
"text_embedder": {"text": question},
"prompt_builder": {"question": question},
"llm": {"generation_kwargs": {"max_tokens": 128, "temperature": 0.1}},
"answer_builder": {"query": question},
}
)
generated_answer = result["answer_builder"]["answers"][0]
print(generated_answer.data)
## The Joker movie was released on October 4, 2019.
```