@tduncan / Nvidia-Optimization-Stack-VLLM
Code Commits Issues Pulls Cloud Agent CI/CD
main
main
md 55 lines 2.3 KB
Rendered Raw
1 # Haystack
2
3 [Haystack](https://github.com/deepset-ai/haystack) is an end-to-end LLM framework that allows you to build applications powered by LLMs, Transformer models, vector search and more. Whether you want to perform retrieval-augmented generation (RAG), document search, question answering or answer generation, Haystack can orchestrate state-of-the-art embedding models and LLMs into pipelines to build end-to-end NLP applications and solve your use case.
4
5 It allows you to deploy a large language model (LLM) server with vLLM as the backend, which exposes OpenAI-compatible endpoints.
6
7 ## Prerequisites
8
9 Set up the vLLM and Haystack environment:
10
11 ```bash
12 pip install vllm haystack-ai
13 ```
14
15 ## Deploy
16
17 1. Start the vLLM server with the supported chat completion model, e.g.
18
19 ```bash
20 vllm serve mistralai/Mistral-7B-Instruct-v0.1
21 ```
22
23 1. Use the `OpenAIGenerator` and `OpenAIChatGenerator` components in Haystack to query the vLLM server.
24
25 ??? code
26
27 ```python
28 from haystack.components.generators.chat import OpenAIChatGenerator
29 from haystack.dataclasses import ChatMessage
30 from haystack.utils import Secret
31
32 generator = OpenAIChatGenerator(
33 # for compatibility with the OpenAI API, a placeholder api_key is needed
34 api_key=Secret.from_token("VLLM-PLACEHOLDER-API-KEY"),
35 model="mistralai/Mistral-7B-Instruct-v0.1",
36 api_base_url="http://{your-vLLM-host-ip}:{your-vLLM-host-port}/v1",
37 generation_kwargs={"max_tokens": 512},
38 )
39
40 response = generator.run(
41 messages=[ChatMessage.from_user("Hi. Can you help me plan my next trip to Italy?")]
42 )
43
44 print("-"*30)
45 print(response)
46 print("-"*30)
47 ```
48
49 ```console
50 ------------------------------
51 {'replies': [ChatMessage(_role=<ChatRole.ASSISTANT: 'assistant'>, _content=[TextContent(text=' Of course! Where in Italy would you like to go and what type of trip are you looking to plan?')], _name=None, _meta={'model': 'mistralai/Mistral-7B-Instruct-v0.1', 'index': 0, 'finish_reason': 'stop', 'usage': {'completion_tokens': 23, 'prompt_tokens': 21, 'total_tokens': 44, 'completion_tokens_details': None, 'prompt_tokens_details': None}})]}
52 ------------------------------
53 ```
54
55 For details, see the tutorial [Using vLLM in Haystack](https://github.com/deepset-ai/haystack-integrations/blob/main/integrations/vllm.md).