A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 13:30 UTC
[doc] add Anything LLM integration (#17216)
Signed-off-by: reidliu41 <reid201711@gmail.com> Co-authored-by: reidliu41 <reid201711@gmail.com>
Reid committed
Apr 26, 2025 at 12:03 UTC
537d5ee0251bcfcedbb8ca934d273366e05f80fa
6 files changed
+48
docs/source/assets/deployment/anything-llm-chat-with-doc.png
Binary files /dev/null and b/docs/source/assets/deployment/anything-llm-chat-with-doc.png differ
docs/source/assets/deployment/anything-llm-chat-without-doc.png
Binary files /dev/null and b/docs/source/assets/deployment/anything-llm-chat-without-doc.png differ
docs/source/assets/deployment/anything-llm-provider.png
Binary files /dev/null and b/docs/source/assets/deployment/anything-llm-provider.png differ
docs/source/assets/deployment/anything-llm-upload-doc.png
Binary files /dev/null and b/docs/source/assets/deployment/anything-llm-upload-doc.png differ
docs/source/deployment/frameworks/anything-llm.md
new
+47
@@ -0,0 +1,47 @@
1
+(deployment-anything-llm)=
2
+
3
+# Anything LLM
4
+
5
+[Anything LLM](https://github.com/Mintplex-Labs/anything-llm) is a full-stack application that enables you to turn any document, resource, or piece of content into context that any LLM can use as references during chatting.
6
+
7
+It allows you to deploy a large language model (LLM) server with vLLM as the backend, which exposes OpenAI-compatible endpoints.
8
+
9
+## Prerequisites
10
+
11
+- Setup vLLM environment
12
+
13
+## Deploy
14
+
15
+- Start the vLLM server with the supported chat completion model, e.g.
16
+
17
+```console
18
+vllm serve Qwen/Qwen1.5-32B-Chat-AWQ --max-model-len 4096
19
+```
20
+
21
+- Download and install [Anything LLM desktop](https://anythingllm.com/desktop).
22
+
23
+- On the bottom left of open settings, AI Prooviders --> LLM:
24
+ - LLM Provider: Generic OpenAI
25
+ - Base URL: http://{vllm server host}:{vllm server port}/v1
26
+ - Chat Model Name: `Qwen/Qwen1.5-32B-Chat-AWQ`
27
+
28
+:::{image} /assets/deployment/anything-llm-provider.png
29
+:::
30
+
31
+- Back to home page, New Workspace --> create `vllm` workspace, and start to chat:
32
+
33
+:::{image} /assets/deployment/anything-llm-chat-without-doc.png
34
+:::
35
+
36
+- Click the upload button:
37
+ - upload the doc
38
+ - select the doc and move to the workspace
39
+ - save and embed
40
+
41
+:::{image} /assets/deployment/anything-llm-upload-doc.png
42
+:::
43
+
44
+- Chat again:
45
+
46
+:::{image} /assets/deployment/anything-llm-chat-with-doc.png
47
+:::
docs/source/deployment/frameworks/index.md
+1
@@ -3,6 +3,7 @@
3
:::{toctree}
4
:maxdepth: 1
5
6
+anything-llm
7
bentoml
8
cerebrium
9
dstack