You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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. This application allows you to pick and choose which LLM or Vector Database you want to use as well as supporting multi-user management and permissions.
39
+
A full-stack application that enables you to turn any document, resource, or piece of content into context that any LLM can use as a reference during chatting. This application allows you to pick and choose which LLM or Vector Database you want to use as well as supporting multi-user management and permissions.
@@ -63,7 +63,7 @@ AnythingLLM divides your documents into objects called `workspaces`. A Workspace
63
63
- 🦾 Agents inside your workspace (browse the web, etc)
64
64
- 💬 [Custom Embeddable Chat widget for your website](https://github.com/Mintplex-Labs/anythingllm-embed/blob/main/README.md)_Docker version only_
65
65
- 📖 Multiple document type support (PDF, TXT, DOCX, etc)
66
-
- Simple chat UI with Drag-n-Drop funcitonality and clear citations.
66
+
- Simple chat UI with Drag-n-Drop functionality and clear citations.
67
67
- 100% Cloud deployment ready.
68
68
- Works with all popular [closed and open-source LLM providers](#supported-llms-embedder-models-speech-models-and-vector-databases).
69
69
- Built-in cost & time-saving measures for managing very large documents compared to any other chat UI.
@@ -85,7 +85,7 @@ AnythingLLM divides your documents into objects called `workspaces`. A Workspace
85
85
-[Hugging Face (chat models)](https://huggingface.co/)
86
86
-[Ollama (chat models)](https://ollama.ai/)
87
87
-[LM Studio (all models)](https://lmstudio.ai)
88
-
-[LocalAi (all models)](https://localai.io/)
88
+
-[LocalAI (all models)](https://localai.io/)
89
89
-[Together AI (chat models)](https://www.together.ai/)
90
90
-[Fireworks AI (chat models)](https://fireworks.ai/)
@@ -142,16 +143,16 @@ AnythingLLM divides your documents into objects called `workspaces`. A Workspace
142
143
143
144
### Technical Overview
144
145
145
-
This monorepo consists of three main sections:
146
+
This monorepo consists of six main sections:
146
147
147
148
-`frontend`: A viteJS + React frontend that you can run to easily create and manage all your content the LLM can use.
148
149
-`server`: A NodeJS express server to handle all the interactions and do all the vectorDB management and LLM interactions.
149
-
-`collector`: NodeJS express server that process and parses documents from the UI.
150
+
-`collector`: NodeJS express server that processes and parses documents from the UI.
150
151
-`docker`: Docker instructions and build process + information for building from source.
151
152
-`embed`: Submodule for generation & creation of the [web embed widget](https://github.com/Mintplex-Labs/anythingllm-embed).
152
153
-`browser-extension`: Submodule for the [chrome browser extension](https://github.com/Mintplex-Labs/anythingllm-extension).
153
154
154
-
## 🛳 SelfHosting
155
+
## 🛳 Self-Hosting
155
156
156
157
Mintplex Labs & the community maintain a number of deployment methods, scripts, and templates that you can use to run AnythingLLM locally. Refer to the table below to read how to deploy on your preferred environment or to automatically deploy.
@@ -207,15 +208,15 @@ We will only track usage details that help us make product and roadmap decisions
207
208
208
209
- When a document is added or removed. No information _about_ the document. Just that the event occurred. This gives us an idea of use.
209
210
210
-
- Type of vector database in use. Let's us know which vector database provider is the most used to prioritize changes when updates arrive for that provider.
211
+
- Type of vector database in use. This helps us prioritize changes when updates arrive for that provider.
211
212
212
-
- Type of LLM provider & model tag in use. Let's us know the most popular choice and prioritize changes when updates arrive for that provider or model, or combination thereof. eg: reasoning vs regular, multi-modal models, etc.
213
+
- Type of LLM provider & model tag in use. This helps us prioritize changes when updates arrive for that provider or model, or combination thereof. eg: reasoning vs regular, multi-modal models, etc.
213
214
214
215
- When a chat is sent. This is the most regular "event" and gives us an idea of the daily-activity of this project across all installations. Again, only the **event** is sent - we have no information on the nature or content of the chat itself.
215
216
216
217
You can verify these claims by finding all locations `Telemetry.sendTelemetry` is called. Additionally these events are written to the output log so you can also see the specific data which was sent - if enabled. **No IP or other identifying information is collected**. The Telemetry provider is [PostHog](https://posthog.com/) - an open-source telemetry collection service.
217
218
218
-
We take privacy very seriously and hopefully you can understand our position to also glimpse into how our tool is used with asking for annoying popup surveys so we can build something worth using. The anonymous data is _never_ shared with third parties, ever.
219
+
We take privacy very seriously, and we hope you understand that we want to learn how our tool is used, without using annoying popup surveys, so we can build something worth using. The anonymous data is _never_ shared with third parties, ever.
219
220
220
221
[View all telemetry events in source code](https://github.com/search?q=repo%3AMintplex-Labs%2Fanything-llm%20.sendTelemetry\(&type=code)
221
222
@@ -228,6 +229,20 @@ We take privacy very seriously and hopefully you can understand our position to
228
229
- create PR with branch name format of `<issue number>-<short name>`
229
230
- LGTM from core-team
230
231
232
+
## 💖 Sponsors
233
+
234
+
### Premium Sponsors
235
+
236
+
<!-- premium-sponsors (reserved for $100/mth sponsors who request to be called out here and/or are non-private sponsors) -->
Copy file name to clipboardExpand all lines: cloud-deployments/aws/cloudformation/DEPLOY.md
+1-1Lines changed: 1 addition & 1 deletion
Original file line number
Diff line number
Diff line change
@@ -1,6 +1,6 @@
1
1
# How to deploy a private AnythingLLM instance on AWS
2
2
3
-
With an AWS account you can easily deploy a private AnythingLLM instance on AWS. This will create a url that you can access from any browser over HTTP (HTTPS not supported). This single instance will run on your own keys and they will not be exposed - however if you want your instance to be protected it is highly recommend that you set a password one setup is complete.
3
+
With an AWS account you can easily deploy a private AnythingLLM instance on AWS. This will create a url that you can access from any browser over HTTP (HTTPS not supported). This single instance will run on your own keys and they will not be exposed - however if you want your instance to be protected it is highly recommend that you set a password once setup is complete.
Copy file name to clipboardExpand all lines: cloud-deployments/digitalocean/terraform/DEPLOY.md
+1-1Lines changed: 1 addition & 1 deletion
Original file line number
Diff line number
Diff line change
@@ -1,6 +1,6 @@
1
1
# How to deploy a private AnythingLLM instance on DigitalOcean using Terraform
2
2
3
-
With a DigitalOcean account, you can easily deploy a private AnythingLLM instance using Terraform. This will create a URL that you can access from any browser over HTTP (HTTPS not supported). This single instance will run on your own keys, and they will not be exposed. However, if you want your instance to be protected, it is highly recommended that you set a password one setup is complete.
3
+
With a DigitalOcean account, you can easily deploy a private AnythingLLM instance using Terraform. This will create a URL that you can access from any browser over HTTP (HTTPS not supported). This single instance will run on your own keys, and they will not be exposed. However, if you want your instance to be protected, it is highly recommended that you set a password once setup is complete.
4
4
5
5
The output of this Terraform configuration will be:
Copy file name to clipboardExpand all lines: cloud-deployments/gcp/deployment/DEPLOY.md
+1-1Lines changed: 1 addition & 1 deletion
Original file line number
Diff line number
Diff line change
@@ -1,6 +1,6 @@
1
1
# How to deploy a private AnythingLLM instance on GCP
2
2
3
-
With a GCP account you can easily deploy a private AnythingLLM instance on GCP. This will create a url that you can access from any browser over HTTP (HTTPS not supported). This single instance will run on your own keys and they will not be exposed - however if you want your instance to be protected it is highly recommend that you set a password one setup is complete.
3
+
With a GCP account you can easily deploy a private AnythingLLM instance on GCP. This will create a url that you can access from any browser over HTTP (HTTPS not supported). This single instance will run on your own keys and they will not be exposed - however if you want your instance to be protected it is highly recommend that you set a password once setup is complete.
0 commit comments