WIP: provider types are recongized properly in qml

2025 is too soon to use C++ features from 2020 without running into bugs
in every build tool that touches the project.

.circleci/config.yml

@@ -1,20 +1,20 @@
 version: 2.1
 setup: true
 orbs:
-  path-filtering: circleci/path-filtering@0.0.1
+  path-filtering: circleci/path-filtering@1.1.0
 
 workflows:
   version: 2.1
   generate-config:
     jobs:
       - path-filtering/filter:
+          filters:
+            tags:
+              only:
+                - /.*/
           base-revision: main
           config-path: .circleci/continue_config.yml
           mapping: |
             .circleci/.* run-all-workflows true
             gpt4all-backend/.* run-all-workflows true
-            gpt4all-bindings/python/.* run-python-workflow true
-            gpt4all-bindings/typescript/.* run-ts-workflow true
-            gpt4all-bindings/csharp/.* run-csharp-workflow true
             gpt4all-chat/.* run-chat-workflow true
-            .* run-default-workflow true

.circleci/grab_notary_id.py

@@ -0,0 +1,17 @@
+import re
+import sys
+
+ID_REG = r"id: (.*)"
+
+def main() -> None:
+    notary_log = sys.argv[1]
+    with open(notary_log, "r") as f:
+        notary_output = f.read()
+        id_m = re.search(ID_REG, notary_output)
+        if id_m:
+            print(id_m.group(1))
+        else:
+            raise RuntimeError("Unable to parse ID from notarization logs")
+
+if __name__ == "__main__":
+    main()

.codespellrc

@@ -1,3 +1,3 @@
 [codespell]
-ignore-words-list = blong, afterall, som, assistent, crasher
-skip = .git,*.pdf,*.svg,*.lock
+ignore-words-list = blong, afterall, assistent, crasher, requestor, nam
+skip = ./.git,./gpt4all-chat/translations,*.pdf,*.svg,*.lock

.github/ISSUE_TEMPLATE/bindings-bug.md

@@ -1,35 +0,0 @@
----
-name: "\U0001F6E0 Bindings Bug Report"
-about: A bug report for the GPT4All Bindings
-labels: ["bindings", "bug-unconfirmed"]
----
-
-<!-- Before creating a new issue, please make sure to take a few moments to check the issue tracker for existing issues about the bug. -->
-
-### Bug Report
-
-<!-- A clear and concise description of what the bug is. -->
-
-### Example Code
-
-<!-- Please provide a minimal code example that can be used to experience this issue. Delete this section if it does not apply. -->
-
-### Steps to Reproduce
-
-<!-- List the steps that should be taken to experience this issue. -->
-
-1.
-2.
-3.
-
-### Expected Behavior
-
-<!-- In a few words, what did you expect to happen? -->
-
-### Your Environment
-
-- Bindings version (e.g. "Version" from `pip show gpt4all`):
-- Operating System:
-- Chat model used (if applicable):
-
-<!-- You can freely edit this text, please remove all the lines you believe are unnecessary. -->

.github/workflows/codespell.yml

@@ -14,6 +14,6 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       - name: Codespell
         uses: codespell-project/actions-codespell@v2

.gitignore

@@ -181,6 +181,8 @@ CMakeLists.txt.user
 gpt4all-chat/models/*
 build_*
 build-*
+cmake-build-*
+/gpt4all-chat/tests/python/config.py
 
 # IntelliJ
 .idea/

.gitmodules

@@ -1,4 +1,34 @@
-[submodule "llama.cpp-mainline"]
-	path = gpt4all-backend/llama.cpp-mainline
+[submodule "gpt4all-backend-old/deps/llama.cpp-mainline"]
+	path = gpt4all-backend-old/deps/llama.cpp-mainline
 	url = https://github.com/nomic-ai/llama.cpp.git
-	branch = master
+    branch = master
+[submodule "gpt4all-chat/usearch"]
+	path = gpt4all-chat/deps/usearch
+	url = https://github.com/nomic-ai/usearch.git
+[submodule "gpt4all-chat/deps/SingleApplication"]
+	path = gpt4all-chat/deps/SingleApplication
+	url = https://github.com/nomic-ai/SingleApplication.git
+[submodule "deps/fmt"]
+	path = deps/fmt
+	url = https://github.com/nomic-ai/fmt.git
+[submodule "gpt4all-chat/deps/DuckX"]
+	path = gpt4all-chat/deps/DuckX
+	url = https://github.com/nomic-ai/DuckX.git
+[submodule "gpt4all-chat/deps/QXlsx"]
+	path = gpt4all-chat/deps/QXlsx
+	url = https://github.com/nomic-ai/QXlsx.git
+[submodule "gpt4all-chat/deps/minja"]
+	path = gpt4all-chat/deps/minja
+	url = https://github.com/nomic-ai/minja.git
+[submodule "gpt4all-chat/deps/json"]
+	path = gpt4all-chat/deps/json
+	url = https://github.com/nlohmann/json.git
+[submodule "gpt4all-backend/deps/qcoro"]
+	path = deps/qcoro
+	url = https://github.com/nomic-ai/qcoro.git
+[submodule "gpt4all-backend/deps/date"]
+	path = gpt4all-backend/deps/date
+	url = https://github.com/HowardHinnant/date.git
+[submodule "gpt4all-chat/deps/generator"]
+	path = gpt4all-chat/deps/generator
+	url = https://github.com/TartanLlama/generator.git

LICENSE_SOM.txt

@@ -1,30 +0,0 @@
-Software for Open Models License (SOM)
-Version 1.0 dated August 30th, 2023
-
-This license governs use of the accompanying Software. If you use the Software, you accept this license. If you do not accept the license, do not use the Software.
-
-This license is intended to encourage open release of models created, modified, processed, or otherwise used via the Software under open licensing terms, and should be interpreted in light of that intent.
-
-1. Definitions
-The “Licensor” is the person or entity who is making the Software available under this license. “Software” is the software made available by Licensor under this license.
-A “Model” is the output of a machine learning algorithm, and excludes the Software.
-“Model Source Materials” must include the Model and model weights, and may include any input data, input data descriptions, documentation or training descriptions for the Model.
-“Open Licensing Terms” means: (a) any open source license approved by the Open Source Initiative, or (b) any other terms that make the Model Source Materials publicly available free of charge, and allow recipients to use, modify and distribute the Model Source Materials. Terms described in (b) may include reasonable restrictions such as non-commercial or non-production limitations, or require use in compliance with law.
-
-2. Grant of Rights. Subject to the conditions and limitations in section 3:
-(A) Copyright Grant. Licensor grants you a non-exclusive, worldwide, royalty-free copyright license to copy, modify, and distribute the Software and any modifications of the Software you create under this license. The foregoing license includes without limitation the right to create, modify, and use Models using this Software.
-
-(B) Patent Grant. Licensor grants you a non-exclusive, worldwide, royalty-free license, under any patents owned or controlled by Licensor, to make, have made, use, sell, offer for sale, import, or otherwise exploit the Software.  No license is granted to patent rights that are not embodied in the operation of the Software in the form provided by Licensor.
-
-3. Conditions and Limitations
-(A) Model Licensing and Access. If you use the Software to create, modify, process, or otherwise use any Model, including usage to create inferences with a Model, whether or not you make the Model available to others, you must make that Model Source Materials publicly available under Open Licensing Terms. 
-
-(B) No Re-Licensing. If you redistribute the Software, or modifications to the Software made under the license granted above, you must make it available only under the terms of this license. You may offer additional terms such as warranties, maintenance and support, but You, and not Licensor, are responsible for performing such terms.
-
-(C) No Trademark License. This license does not grant you rights to use the Licensor’s name, logo, or trademarks.
-
-(D) If you assert in writing a claim against any person or entity alleging that the use of the Software infringes any patent, all of your licenses to the Software under Section 2 end automatically as of the date you asserted the claim.
-
-(E) If you distribute any portion of the Software, you must retain all copyright, patent, trademark, and attribution notices that are present in the Software, and you must include a copy of this license.
-
-(F) The Software is licensed “as-is.” You bear the entire risk of using it. Licensor gives You no express warranties, guarantees or conditions. You may have additional consumer rights under your local laws that this license cannot change. To the extent permitted under your local laws, the Licensor disclaims and excludes the implied warranties of merchantability, fitness for a particular purpose and non-infringement. To the extent this disclaimer is unlawful, you, and not Licensor, are responsible for any liability.

MAINTAINERS.md

@@ -0,0 +1,70 @@
+# MAINTAINERS
+
+## Rules
+
+* All content inside GPT4All shall have a documented maintainer
+* If a maintainer decides to retire or resign a call for volunteers will go
+  out
+* If no further maintainer can be found in a reasonable time frame, then the
+  content will be marked deprecated and removed in time
+
+## Job
+
+Maintainers will be...
+
+1. Responsible for overseeing content under their stewardship
+2. Responsible for triaging new issues, reviewing PRs, assigning priority
+   to tasks
+3. Responsible for keeping content in sufficient quality in a timely fashion
+
+## List
+
+Adam Treat ([@manyoso](https://github.com/manyoso))<br/>
+E-mail: adam@nomic.ai<br/>
+Discord: `@gonzochess75`
+- Overall project maintainer
+- Chat UI
+
+Jared Van Bortel ([@cebtenzzre](https://github.com/cebtenzzre))<br/>
+E-mail: jared@nomic.ai<br/>
+Discord: `@cebtenzzre`
+- gpt4all-backend
+
+Dominik ([@cosmic-snow](https://github.com/cosmic-snow))<br/>
+E-mail: cosmic-snow@mailfence.com<br/>
+Discord: `@cosmic__snow`
+- Community documentation (GitHub Wiki)
+
+Max Cembalest ([@mcembalest](https://github.com/mcembalest))<br/>
+E-mail: max@nomic.ai<br/>
+Discord: `@maxcembalest.`
+- Official documentation (docs -> https://docs.gpt4all.io/)
+
+Thiago Ramos ([@thiagojramos](https://github.com/thiagojramos))<br/>
+E-mail: thiagojramos@outlook.com<br/>
+- pt\_BR translation
+
+不知火 Shiranui ([@supersonictw](https://github.com/supersonictw))<br/>
+E-mail: supersonic@livemail.tw<br/>
+Discord: `@supersonictw`
+- zh\_TW translation
+
+Jeremy Tayco ([@jstayco](https://github.com/jstayco))<br/>
+E-mail: jstayco@protonmail.ch<br/>
+Discord: `@vertana`
+- es\_MX translation
+
+Riccardo Giovanetti ([@Harvester62](https://github.com/Harvester62))<br/>
+E-mail: riccardo.giovanetti@gmail.com<br/>
+Discord: `@harvester62`
+- it\_IT translation
+
+Tim ([@Tim453](https://github.com/Tim453))<br/>
+E-mail: tim453@mailbox.org<br/>
+Discord: `@Tim453`
+- Flatpak
+
+Jack ([@wuodoo](https://github.com/wuodoo))<br/>
+E-mail: 2296103047@qq.com<br/>
+Discord: `@mikage`
+- zh\_CN translation

README.md

@@ -1,78 +1,99 @@
 <h1 align="center">GPT4All</h1>
 
-<p align="center">Open-source large language models that run locally on your CPU and nearly any GPU</p>
-
 <p align="center">
-<a href="https://gpt4all.io">GPT4All Website and Models</a> • <a href="https://docs.gpt4all.io">GPT4All Documentation</a> • <a href="https://discord.gg/mGZE39AS3e">Discord</a>
+  Now with support for DeepSeek R1 Distillations
 </p>
 
+<p align="center">
+  <a href="https://www.nomic.ai/gpt4all">Website</a> &bull; <a href="https://docs.gpt4all.io">Documentation</a> &bull; <a href="https://discord.gg/mGZE39AS3e">Discord</a> &bull; <a href="https://www.youtube.com/watch?v=gQcZDXRVJok">YouTube Tutorial</a>
+</p>
 
 <p align="center">
-<a href="https://python.langchain.com/en/latest/modules/models/llms/integrations/gpt4all.html">🦜️🔗 Official Langchain Backend</a> 
+  GPT4All runs large language models (LLMs) privately on everyday desktops & laptops.
 </p>
+<p align="center">
+  No API calls or GPUs required - you can just download the application and <a href="https://docs.gpt4all.io/gpt4all_desktop/quickstart.html#quickstart">get started</a>.
+</p>
+
+<p align="center">
+  Read about what's new in <a href="https://www.nomic.ai/blog/tag/gpt4all">our blog</a>.
+</p>
+<p align="center">
+  <a href="https://nomic.ai/gpt4all/#newsletter-form">Subscribe to the newsletter</a>
+</p>
+
+https://github.com/nomic-ai/gpt4all/assets/70534565/513a0f15-4964-4109-89e4-4f9a9011f311
 
 <p align="center">
 GPT4All is made possible by our compute partner <a href="https://www.paperspace.com/">Paperspace</a>.
 </p>
 
-<p align="center">
- <a href="https://www.phorm.ai/query?projectId=755eecd3-24ad-49cc-abf4-0ab84caacf63"><img src="https://img.shields.io/badge/Phorm-Ask_AI-%23F2777A.svg?&logo=data:image/svg+xml;base64,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" alt="phorm.ai"></a>
+## Download Links
+
+<p>
+  &mdash; <a href="https://gpt4all.io/installers/gpt4all-installer-win64.exe">
+    <img src="docs/assets/windows.png" style="height: 1em; width: auto" /> Windows Installer
+  </a> &mdash;
+</p>
+<p>
+  &mdash; <a href="https://gpt4all.io/installers/gpt4all-installer-win64-arm.exe">
+    <img src="gpt4all-bindings/python/docs/assets/windows.png" style="height: 1em; width: auto" /> Windows ARM Installer
+  </a> &mdash;
+</p>
+<p>
+  &mdash; <a href="https://gpt4all.io/installers/gpt4all-installer-darwin.dmg">
+    <img src="docs/assets/mac.png" style="height: 1em; width: auto" /> macOS Installer
+  </a> &mdash;
+</p>
+<p>
+  &mdash; <a href="https://gpt4all.io/installers/gpt4all-installer-linux.run">
+    <img src="docs/assets/ubuntu.svg" style="height: 1em; width: auto" /> Ubuntu Installer
+  </a> &mdash;
+</p>
+<p>
+  The Windows and Linux builds require Intel Core i3 2nd Gen / AMD Bulldozer, or better.
+</p>
+<p>
+  The Windows ARM build supports Qualcomm Snapdragon and Microsoft SQ1/SQ2 processors.
+</p>
+<p>
+  The Linux build is x86-64 only (no ARM).
+</p>
+<p>
+  The macOS build requires Monterey 12.6 or newer. Best results with Apple Silicon M-series processors.
 </p>
 
-<p align="center">
-  <img width="600" height="365" src="https://user-images.githubusercontent.com/13879686/231876409-e3de1934-93bb-4b4b-9013-b491a969ebbc.gif">
-</p>
-<p align="center">
-Run on an M1 macOS Device (not sped up!)
+See the full [System Requirements](gpt4all-chat/system_requirements.md) for more details.
+
+<br/>
+<br/>
+<p>
+  <a href='https://flathub.org/apps/io.gpt4all.gpt4all'>
+    <img style="height: 2em; width: auto" alt='Get it on Flathub' src='https://flathub.org/api/badge'><br/>
+    Flathub (community maintained)
+  </a>
 </p>
 
-## GPT4All: An ecosystem of open-source on-edge large language models.
+## Integrations
 
-GPT4All is an ecosystem to run **powerful** and **customized** large language models that work locally on consumer grade CPUs and any GPU. Note that your CPU needs to support [AVX or AVX2 instructions](https://en.wikipedia.org/wiki/Advanced_Vector_Extensions).
+:parrot::link: [Langchain](https://python.langchain.com/v0.2/docs/integrations/providers/gpt4all/)
+:card_file_box: [Weaviate Vector Database](https://github.com/weaviate/weaviate) - [module docs](https://weaviate.io/developers/weaviate/modules/retriever-vectorizer-modules/text2vec-gpt4all)
+:telescope: [OpenLIT (OTel-native Monitoring)](https://github.com/openlit/openlit) - [Docs](https://docs.openlit.io/latest/integrations/gpt4all)
 
-Learn more in the [documentation](https://docs.gpt4all.io).
-
-A GPT4All model is a 3GB - 8GB file that you can download and plug into the GPT4All open-source ecosystem software. **Nomic AI** supports and maintains this software ecosystem to enforce quality and security alongside spearheading the effort to allow any person or enterprise to easily train and deploy their own on-edge large language models.
-
-### What's New ([Issue Tracker](https://github.com/orgs/nomic-ai/projects/2))
-- [Latest Release ](https://github.com/nomic-ai/gpt4all/releases)
+## Release History
+- **July 2nd, 2024**: V3.0.0 Release
+    - Fresh redesign of the chat application UI
+    - Improved user workflow for LocalDocs
+    - Expanded access to more model architectures
 - **October 19th, 2023**: GGUF Support Launches with Support for:
-    - Mistral 7b base model, an updated model gallery on [gpt4all.io](https://gpt4all.io), several new local code models including Rift Coder v1.5
+    - Mistral 7b base model, an updated model gallery on our website, several new local code models including Rift Coder v1.5
     - [Nomic Vulkan](https://blog.nomic.ai/posts/gpt4all-gpu-inference-with-vulkan) support for Q4\_0 and Q4\_1 quantizations in GGUF.
     - Offline build support for running old versions of the GPT4All Local LLM Chat Client.
-- **September 18th, 2023**: [Nomic Vulkan](https://blog.nomic.ai/posts/gpt4all-gpu-inference-with-vulkan) launches supporting local LLM inference on AMD, Intel, Samsung, Qualcomm and NVIDIA GPUs.
-- **August 15th, 2023**: GPT4All API launches allowing inference of local LLMs from docker containers.
-- **July 2023**: Stable support for LocalDocs, a GPT4All Plugin that allows you to privately and locally chat with your data.
+- **September 18th, 2023**: [Nomic Vulkan](https://blog.nomic.ai/posts/gpt4all-gpu-inference-with-vulkan) launches supporting local LLM inference on NVIDIA and AMD GPUs.
+- **July 2023**: Stable support for LocalDocs, a feature that allows you to privately and locally chat with your data.
+- **June 28th, 2023**: [Docker-based API server] launches allowing inference of local LLMs from an OpenAI-compatible HTTP endpoint.
 
-
-### Chat Client
-Run any GPT4All model natively on your home desktop with the auto-updating desktop chat client. See <a href="https://gpt4all.io">GPT4All Website</a> for a full list of open-source models you can run with this powerful desktop application.
-
-Direct Installer Links:
-
-* [macOS](https://gpt4all.io/installers/gpt4all-installer-darwin.dmg)
-
-* [Windows](https://gpt4all.io/installers/gpt4all-installer-win64.exe)
-
-* [Ubuntu](https://gpt4all.io/installers/gpt4all-installer-linux.run)
-
-Find the most up-to-date information on the [GPT4All Website](https://gpt4all.io/)
-
-### Chat Client building and running
-
-* Follow the visual instructions on the chat client [build_and_run](gpt4all-chat/build_and_run.md) page
-
-### Bindings
-
-* <a href="https://github.com/nomic-ai/gpt4all/tree/main/gpt4all-bindings/python/README.md">:snake: Official Python Bindings</a> [![Downloads](https://static.pepy.tech/badge/gpt4all/week)](https://pepy.tech/project/gpt4all)
-* <a href="https://github.com/nomic-ai/gpt4all/tree/main/gpt4all-bindings/typescript">:computer: Official Typescript Bindings</a>
-* <a href="https://github.com/nomic-ai/gpt4all/tree/main/gpt4all-bindings/golang">:computer: Official GoLang Bindings</a>
-* <a href="https://github.com/nomic-ai/gpt4all/tree/main/gpt4all-bindings/csharp">:computer: Official C# Bindings</a>
-* <a href="https://github.com/nomic-ai/gpt4all/tree/main/gpt4all-bindings/java">:computer: Official Java Bindings</a>
-
-### Integrations
-
-* 🗃️ [Weaviate Vector Database](https://github.com/weaviate/weaviate) - [module docs](https://weaviate.io/developers/weaviate/modules/retriever-vectorizer-modules/text2vec-gpt4all)
+[Docker-based API server]: https://github.com/nomic-ai/gpt4all/tree/cef74c2be20f5b697055d5b8b506861c7b997fab/gpt4all-api
 
 ## Contributing
 GPT4All welcomes contributions, involvement, and discussion from the open source community!
@@ -80,73 +101,7 @@ Please see CONTRIBUTING.md and follow the issues, bug reports, and PR markdown t
 
 Check project discord, with project owners, or through existing issues/PRs to avoid duplicate work.
 Please make sure to tag all of the above with relevant project identifiers or your contribution could potentially get lost.
-Example tags: `backend`, `bindings`, `python-bindings`, `documentation`, etc.
-
-
-## GPT4All 2024 Roadmap
-To contribute to the development of any of the below roadmap items, make or find the corresponding issue and cross-reference the [in-progress task](https://github.com/orgs/nomic-ai/projects/2/views/1).
-
-Each item should have an issue link below.
-
-- Chat UI Language Localization (localize UI into the native languages of users)
-    - [ ] Chinese
-    - [ ] German
-    - [ ] French
-    - [ ] Portuguese
-    - [ ] Your native language here. 
-- UI Redesign: an internal effort at Nomic to improve the UI/UX of gpt4all for all users.
-    - [ ] Design new user interface and gather community feedback
-    - [ ] Implement the new user interface and experience.
-- Installer and Update Improvements
-    - [ ] Seamless native installation and update process on OSX
-    - [ ] Seamless native installation and update process on Windows
-    - [ ] Seamless native installation and update process on Linux
-- Model discoverability improvements:
-    - [x] Support huggingface model discoverability
-    - [ ] Support Nomic hosted model discoverability
-- LocalDocs (towards a local perplexity)
-    - Multilingual LocalDocs Support
-        - [ ] Create a multilingual experience
-        - [ ] Incorporate a multilingual embedding model
-        - [ ] Specify a preferred multilingual LLM for localdocs
-    - Improved RAG techniques
-        - [ ] Query augmentation and re-writing
-        - [ ] Improved chunking and text extraction from arbitrary modalities
-            - [ ] Custom PDF extractor past the QT default (charts, tables, text)
-        - [ ] Faster indexing and local exact search with v1.5 hamming embeddings and reranking (skip ANN index construction!)
-    - Support queries like 'summarize X document'
-    - Multimodal LocalDocs support with Nomic Embed
-    - Nomic Dataset Integration with real-time LocalDocs
-        - [ ] Include an option to allow the export of private LocalDocs collections to Nomic Atlas for debugging data/chat quality
-        - [ ] Allow optional sharing of LocalDocs collections between users.
-        - [ ] Allow the import of a LocalDocs collection from an Atlas Datasets
-            - Chat with live version of Wikipedia, Chat with Pubmed, chat with the latest snapshot of world news.
-- First class Multilingual LLM Support
-    - [ ] Recommend and set a default LLM for German
-    - [ ] Recommend and set a default LLM for English
-    - [ ] Recommend and set a default LLM for Chinese
-    - [ ] Recommend and set a default LLM for Spanish
-
-- Server Mode improvements
-    - Improved UI and new requested features:
-        - [ ] Fix outstanding bugs and feature requests around networking configurations.
-        - [ ] Support Nomic Embed inferencing
-        - [ ] First class documentation
-        - [ ] Improving developer use and quality of server mode (e.g. support larger batches)
-
-## Technical Reports
-
-<p align="center">
-<a href="https://gpt4all.io/reports/GPT4All_Technical_Report_3.pdf">:green_book: Technical Report 3: GPT4All Snoozy and Groovy </a>
-</p>
-
-<p align="center">
-<a href="https://static.nomic.ai/gpt4all/2023_GPT4All-J_Technical_Report_2.pdf">:green_book: Technical Report 2: GPT4All-J </a>
-</p>
-
-<p align="center">
-<a href="https://s3.amazonaws.com/static.nomic.ai/gpt4all/2023_GPT4All_Technical_Report.pdf">:green_book: Technical Report 1: GPT4All</a>
-</p>
+Example tags: `backend`, `documentation`, etc.
 
 ## Citation
 

common/common.cmake

@@ -0,0 +1,46 @@
+# enable color diagnostics with ninja
+if (CMAKE_GENERATOR STREQUAL Ninja AND CMAKE_CXX_COMPILER_ID MATCHES "GNU|Clang")
+    add_compile_options(-fdiagnostics-color=always)
+endif()
+
+function(gpt4all_add_warning_options target)
+    if (MSVC)
+        return()
+    endif()
+    target_compile_options("${target}" PRIVATE
+        # base options
+        -Wall
+        -Wextra
+        # extra options
+        -Wcast-align
+        -Wextra-semi
+        -Wformat=2
+        -Wmissing-include-dirs
+        -Wsuggest-override
+        -Wvla
+        # errors
+        -Werror=format-security
+        -Werror=init-self
+        -Werror=pointer-arith
+        -Werror=undef
+        # disabled warnings
+        -Wno-sign-compare
+        -Wno-unused-parameter
+    )
+    if (CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
+        target_compile_options("${target}" PRIVATE
+            -Wduplicated-branches
+            -Wduplicated-cond
+            -Wlogical-op
+            -Wno-reorder
+            -Wno-null-dereference
+        )
+    elseif (CMAKE_CXX_COMPILER_ID MATCHES "^(Apple)?Clang$")
+        target_compile_options("${target}" PRIVATE
+            -Wunreachable-code-break
+            -Wunreachable-code-return
+            -Werror=pointer-integer-compare
+            -Wno-reorder-ctor
+        )
+    endif()
+endfunction()

deps/CMakeLists.txt

@@ -0,0 +1,22 @@
+set(BUILD_SHARED_LIBS OFF)
+
+set(FMT_INSTALL OFF)
+add_subdirectory(fmt)
+
+set(BUILD_TESTING           OFF)
+set(QCORO_BUILD_EXAMPLES    OFF)
+set(QCORO_WITH_QTDBUS       OFF)
+set(QCORO_WITH_QTWEBSOCKETS OFF)
+set(QCORO_WITH_QTQUICK      OFF)
+set(QCORO_WITH_QTTEST       OFF)
+add_subdirectory(qcoro)
+
+set(GPT4ALL_BOOST_TAG 1.87.0)
+FetchContent_Declare(
+    boost
+    URL "https://github.com/boostorg/boost/releases/download/boost-${GPT4ALL_BOOST_TAG}/boost-${GPT4ALL_BOOST_TAG}-cmake.tar.xz"
+    URL_HASH "SHA256=7da75f171837577a52bbf217e17f8ea576c7c246e4594d617bfde7fafd408be5"
+)
+
+set(BOOST_INCLUDE_LIBRARIES json describe system)
+FetchContent_MakeAvailable(boost)

docs/assets/ubuntu.svg

@@ -0,0 +1,5 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<svg xmlns="http://www.w3.org/2000/svg" width="285" height="285" viewBox="-142.5 -142.5 285 285" xmlns:xlink="http://www.w3.org/1999/xlink">
+<circle fill="#FFFFFF" r="141.732"/><g id="U" fill="#DD4814"><circle cx="-96.3772" r="18.9215"/>
+<path d="M-45.6059,68.395C-62.1655,57.3316-74.4844,40.4175-79.6011,20.6065-73.623,15.7354-69.8047,8.3164-69.8047,0-69.8047-8.3164-73.623-15.7354-79.6011-20.6065-74.4844-40.4175-62.1655-57.3316-45.6059-68.395L-31.7715-45.2212C-45.9824-35.2197-55.2754-18.7026-55.2754,0-55.2754,18.7026-45.9824,35.2197-31.7715,45.2212Z"/></g>
+<use xlink:href="#U" transform="rotate(120)"/><use xlink:href="#U" transform="rotate(240)"/></svg>

docs/css/custom.css

@@ -0,0 +1,5 @@
+.md-content h1,
+.md-content h2 {
+  margin-top: 0.5em;
+  margin-bottom: 0.5em;
+}

docs/gpt4all_api_server/home.md

@@ -0,0 +1,86 @@
+# GPT4All API Server
+
+GPT4All provides a local API server that allows you to run LLMs over an HTTP API. 
+
+## Key Features
+
+- **Local Execution**: Run models on your own hardware for privacy and offline use.
+- **LocalDocs Integration**: Run the API with relevant text snippets provided to your LLM from a [LocalDocs collection](../gpt4all_desktop/localdocs.md).
+- **OpenAI API Compatibility**: Use existing OpenAI-compatible clients and tools with your local models.
+
+## Activating the API Server
+
+1. Open the GPT4All Chat Desktop Application.
+2. Go to `Settings` > `Application` and scroll down to `Advanced`.
+3. Check the box for the `"Enable Local API Server"` setting.
+4. The server listens on port 4891 by default. You can choose another port number in the `"API Server Port"` setting.
+
+## Connecting to the API Server
+
+The base URL used for the API server is `http://localhost:4891/v1` (or `http://localhost:<PORT_NUM>/v1` if you are using a different port number). 
+
+The server only accepts HTTP connections (not HTTPS) and only listens on localhost (127.0.0.1) (e.g. not to the IPv6 localhost address `::1`.)
+
+## Examples
+
+!!! note "Example GPT4All API calls"
+
+    === "cURL"
+
+        ```bash
+        curl -X POST http://localhost:4891/v1/chat/completions -d '{
+        "model": "Phi-3 Mini Instruct",
+        "messages": [{"role":"user","content":"Who is Lionel Messi?"}],
+        "max_tokens": 50,
+        "temperature": 0.28
+        }'
+        ```
+
+    === "PowerShell"
+
+        ```powershell
+        Invoke-WebRequest -URI http://localhost:4891/v1/chat/completions -Method POST -ContentType application/json -Body '{
+        "model": "Phi-3 Mini Instruct",
+        "messages": [{"role":"user","content":"Who is Lionel Messi?"}],
+        "max_tokens": 50,
+        "temperature": 0.28
+        }'
+        ```
+
+## API Endpoints
+
+| Method | Path | Description |
+|--------|------|-------------|
+| GET | `/v1/models` | List available models |
+| GET | `/v1/models/<name>` | Get details of a specific model |
+| POST | `/v1/completions` | Generate text completions |
+| POST | `/v1/chat/completions` | Generate chat completions |
+
+## LocalDocs Integration
+
+You can use LocalDocs with the API server:
+
+1. Open the Chats view in the GPT4All application.
+2. Scroll to the bottom of the chat history sidebar.
+3. Select the server chat (it has a different background color).
+4. Activate LocalDocs collections in the right sidebar.
+
+(Note: LocalDocs can currently only be activated through the GPT4All UI, not via the API itself).
+
+Now, your API calls to your local LLM will have relevant references from your LocalDocs collection retrieved and placed in the input message for the LLM to respond to.
+
+The references retrieved for your API call can be accessed in the API response object at 
+
+`response["choices"][0]["references"]`
+
+The data included in the `references` are:
+
+- `text`: the actual text content from the snippet that was extracted from the reference document
+
+- `author`: the author of the reference document (if available)
+
+- `date`: the date of creation of the reference document (if available)
+
+- `page`: the page number the snippet is from (only available for PDF documents for now)
+
+- `title`: the title of the reference document (if available)

docs/gpt4all_desktop/chat_templates.md

@@ -0,0 +1,206 @@
+## What are chat templates?
+Natively, large language models only know how to complete plain text and do not know the difference between their input and their output. In order to support a chat with a person, LLMs are designed to use a template to convert the conversation to plain text using a specific format.
+
+For a given model, it is important to use an appropriate chat template, as each model is designed to work best with a specific format. The chat templates included with the built-in models should be sufficient for most purposes.
+
+There are two reasons you would want to alter the chat template:
+
+- You are sideloading a model and there is no chat template available,
+- You would like to have greater control over the input to the LLM than a system message provides.
+
+
+## What is a system message?
+A system message is a message that controls the responses from the LLM in a way that affects the entire conversation. System messages can be short, such as "Speak like a pirate.", or they can be long and contain a lot of context for the LLM to keep in mind.
+
+Not all models are designed to use a system message, so they work with some models better than others.
+
+
+## How do I customize the chat template or system message?
+To customize the chat template or system message, go to Settings > Model. Make sure to select the correct model at the top. If you clone a model, you can use a different chat template or system message from the base model, enabling you to use different settings for each conversation.
+
+These settings take effect immediately. After changing them, you can click "Redo last response" in the chat view, and the response will take the new settings into account.
+
+
+## Do I need to write a chat template?
+You typically do not need to write your own chat template. The exception is models that are not in the official model list and do not come with a chat template built-in. These will show a "Clear" option above the chat template field in the Model Settings page instead of a "Reset" option. See the section on [finding] or [creating] a chat template.
+
+[finding]: #how-do-i-find-a-chat-template
+[creating]: #advanced-how-do-chat-templates-work
+
+
+## What changed in GPT4All v3.5?
+GPT4All v3.5 overhauled the chat template system. There are three crucial differences:
+
+- The chat template now formats an entire conversation instead of a single pair of messages,
+- The chat template now uses Jinja syntax instead of `%1` and `%2` placeholders,
+- And the system message should no longer contain control tokens or trailing whitespace.
+
+If you are using any chat templates or system messages that had been added or altered from the default before upgrading to GPT4All v3.5 or newer, these will no longer work. See below for how to solve common errors you may see after upgrading.
+
+
+## Error/Warning: System message is not plain text.
+This is easy to fix. Go to the model's settings and look at the system prompt. There are three things to look for:
+
+- Control tokens such as `<|im_start|>`, `<|start_header_id|>`, or `<|system|>`
+- A prefix such as `### System` or `SYSTEM:`
+- Trailing whitespace, such as a space character or blank line.
+
+If you see any of these things, remove them. For example, this legacy system prompt:
+```
+<|start_header_id|>system<|end_header_id|>
+You are a helpful assistant.<|eot_id|>
+```
+
+Should become this:
+```
+You are a helpful assistant.
+```
+
+If you do not see anything that needs to be changed, you can dismiss the error by making a minor modification to the message and then changing it back.
+
+If you see a warning, your system message does not appear to be plain text. If you believe this warning is incorrect, it can be safely ignored. If in doubt, ask on the [Discord].
+
+[Discord]: https://discord.gg/mGZE39AS3e
+
+
+## Error: Legacy system prompt needs to be updated in Settings.
+This is the same as [above][above-1], but appears on the chat page.
+
+[above-1]: #errorwarning-system-message-is-not-plain-text
+
+
+## Error/Warning: Chat template is not in Jinja format.
+This is the result of attempting to use an old-style template (possibly from a previous version) in GPT4All 3.5+.
+
+Go to the Model Settings page and select the affected model. If you see a "Reset" button, and you have not intentionally modified the prompt template, you can click "Reset". Otherwise, this is what you can do:
+
+1. Back up your chat template by copying it safely to a text file and saving it. In the next step, it will be removed from GPT4All.
+2. Click "Reset" or "Clear".
+3. If you clicked "Clear", the chat template is now gone. Follow the steps to [find][finding] or [create][creating] a basic chat template for your model.
+4. Customize the chat template to suit your needs. For help, read the section about [creating] a chat template.
+
+
+## Error: Legacy prompt template needs to be updated in Settings.
+This is the same as [above][above-2], but appears on the chat page.
+
+[above-2]: #errorwarning-chat-template-is-not-in-jinja-format
+
+
+## The chat template has a syntax error.
+If there is a syntax error while editing the chat template, the details will be displayed in an error message above the input box. This could be because the chat template is not actually in Jinja format (see [above][above-2]).
+
+Otherwise, you have either typed something correctly, or the model comes with a template that is incompatible with GPT4All. See [the below section][creating] on creating chat templates and make sure that everything is correct. When in doubt, ask on the [Discord].
+
+
+## Error: No chat template configured.
+This may appear for models that are not from the official model list and do not include a chat template. Older versions of GPT4All picked a poor default in this case. You will get much better results if you follow the steps to [find][finding] or [create][creating] a chat template for your model.
+
+
+## Error: The chat template cannot be blank.
+If the button above the chat template on the Model Settings page says "Clear", see [above][above-3]. If you see "Reset", click that button to restore a reasonable default. Also see the section on [syntax errors][chat-syntax-error].
+
+[above-3]: #error-no-chat-template-configured
+[chat-syntax-error]: #the-chat-template-has-a-syntax-error
+
+
+## How do I find a chat template?
+When in doubt, you can always ask the [Discord] community for help. Below are the instructions to find one on your own.
+
+The authoritative source for a model's chat template is the HuggingFace repo that the original (non-GGUF) model came from. First, you should find this page. If you just have a model file, you can try a google search for the model's name. If you know the page you downloaded the GGUF model from, its README usually links to the original non-GGUF model.
+
+Once you have located the original model, there are two methods you can use to extract its chat template. Pick whichever one you are most comfortable with.
+
+### Using the CLI (all models)
+1. Install `jq` using your preferred package manager - e.g. Chocolatey (Windows), Homebrew (macOS), or apt (Ubuntu).
+2. Download `tokenizer_config.json` from the model's "Files and versions" tab.
+3. Open a command prompt in the directory which you have downloaded the model file.
+4. Run `jq -r ".chat_template" tokenizer_config.json`. This shows the chat template in a human-readable form. You can copy this and paste it into the settings page.
+5. (Optional) You can save the output to a text file like this: `jq -r ".chat_template" tokenizer_config.json >chat_template.txt`
+
+If the output is "null", the model does not provide a chat template. See the [below instructions][creating] on creating a chat template.
+
+### Python (open models)
+1. Install `transformers` using your preferred python package manager, e.g. `pip install transformers`. Make sure it is at least version v4.43.0.
+2. Copy the ID of the HuggingFace model, using the clipboard icon next to the name. For example, if the URL is `https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B`, the ID is `NousResearch/Hermes-2-Pro-Llama-3-8B`.
+3. Open a python interpreter (`python`) and run the following commands. Change the model ID in the example to the one you copied.
+```
+>>> from transformers import AutoTokenizer
+>>> tokenizer = AutoTokenizer.from_pretrained('NousResearch/Hermes-2-Pro-Llama-3-8B')
+>>> print(tokenizer.get_chat_template())
+```
+You can copy the output and paste it into the settings page.
+4. (Optional) You can save the output to a text file like this:
+```
+>>> open('chat_template.txt', 'w').write(tokenizer.get_chat_template())
+```
+
+If you get a ValueError exception, this model does not provide a chat template. See the [below instructions][creating] on creating a chat template.
+
+
+### Python (gated models)
+Some models, such as Llama and Mistral, do not allow public access to their chat template. You must either use the CLI method above, or follow the following instructions to use Python:
+
+1. For these steps, you must have git and git-lfs installed.
+2. You must have a HuggingFace account and be logged in.
+3. You must already have access to the gated model. Otherwise, request access.
+4. You must have an SSH key configured for git access to HuggingFace.
+5. `git clone` the model's HuggingFace repo using the SSH clone URL. There is no need to download the entire model, which is very large. A good way to do this on Linux is:
+```console
+$ GIT_LFS_SKIP_SMUDGE=1 git clone hf.co:meta-llama/Llama-3.1-8B-Instruct.git
+$ cd Llama-3.1-8B-Instruct
+$ git lfs pull -I "tokenizer.*"
+```
+6. Follow the above instructions for open models, but replace the model ID with the path to the directory containing `tokenizer\_config.json`:
+```
+>>> tokenizer = AutoTokenizer.from_pretrained('.')
+```
+
+
+## Advanced: How do chat templates work?
+The chat template is applied to the entire conversation you see in the chat window. The template loops over the list of messages, each containing `role` and `content` fields. `role` is either `user`, `assistant`, or `system`.
+
+GPT4All also supports the special variables `bos_token`, `eos_token`, and `add_generation_prompt`. See the [HuggingFace docs] for what those do.
+
+[HuggingFace docs]: https://huggingface.co/docs/transformers/v4.46.3/en/chat_templating#special-variables
+
+
+## Advanced: How do I make a chat template?
+The best way to create a chat template is to start by using an existing one as a reference. Then, modify it to use the format documented for the given model. Its README page may explicitly give an example of its template. Or, it may mention the name of a well-known standard template, such as ChatML, Alpaca, Vicuna. GPT4All does not yet include presets for these templates, so they will have to be found in other models or taken from the community.
+
+For more information, see the very helpful [HuggingFace guide]. Some of this is not applicable, such as the information about tool calling and RAG - GPT4All implements those features differently.
+
+Some models use a prompt template that does not intuitively map to a multi-turn chat, because it is more intended for single instructions. The [FastChat] implementation of these templates is a useful reference for the correct way to extend them to multiple messages.
+
+[HuggingFace guide]: https://huggingface.co/docs/transformers/v4.46.3/en/chat_templating#advanced-template-writing-tips
+[FastChat]: https://github.com/lm-sys/FastChat/blob/main/fastchat/conversation.py
+
+
+# Advanced: What are GPT4All v1 templates?
+GPT4All supports its own template syntax, which is nonstandard but provides complete control over the way LocalDocs sources and file attachments are inserted into the conversation. These templates begin with `{# gpt4all v1 #}` and look similar to the example below.
+
+For standard templates, GPT4All combines the user message, sources, and attachments into the `content` field. For GPT4All v1 templates, this is not done, so they must be used directly in the template for those features to work correctly.
+
+```jinja
+{# gpt4all v1 #}
+{%- for message in messages %}
+    {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n' }}
+    {%- if message['role'] == 'user' %}
+        {%- for source in message['sources'] %}
+            {%- if loop.first %}
+                {{- '### Context:\n' }}
+            {%- endif %}
+            {{- 'Collection: ' + source['collection'] + '\n'   +
+                'Path: '       + source['path']       + '\n'   +
+                'Excerpt: '    + source['text']       + '\n\n' }}
+        {%- endfor %}
+    {%- endif %}
+    {%- for attachment in message['prompt_attachments'] %}
+        {{- attachment['processed_content'] + '\n\n' }}
+    {%- endfor %}
+    {{- message['content'] | trim }}
+    {{- '<|eot_id|>' }}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}
+```

docs/gpt4all_desktop/chats.md

@@ -0,0 +1,124 @@
+# Chats
+
+Chats are conversations with [language models](models.md) that run locally on your device.
+
+!!! note "Example Chats"
+
+    === "Llama 3"
+        Download `Llama 3` and prompt:
+        ```
+        explain why the sky is blue in a way that is correct and makes sense to a child
+        ```
+
+        With the default sampling settings, you should see text resembling the following:
+
+        ```
+        What a great question!
+        So, you know how we can see different colors like red, yellow, green, and orange? Well, when sunlight enters Earth's atmosphere, it starts to interact with tiny particles called molecules of gases like nitrogen (N2) and oxygen (02). These molecules are really small, but they're all around us!
+        Now, here's the cool part: these molecules scatter, or bounce off, shorter wavelengths of light more than longer wavelengths. Think of it like a game of pool where the cue ball hits other balls with different sizes and speeds.
+        The shortest wavelength of visible light is violet (about 400 nanometers), followed by blue (around 450-495 nanometers). These shorter wavelengths are scattered in all directions, kind of like how a basketball player might bounce the ball around on the court. This scattering effect makes the sky appear blue to our eyes!
+        Here's why it doesn't look as bright or intense as a blue crayon: there are many more molecules in the atmosphere that scatter longer wavelengths (like red and orange) than shorter ones, so those colors get spread out and become less noticeable.
+        To sum it up:
+        1. Sunlight enters Earth's atmosphere.
+        2. Tiny gas molecule particles interact with light, scattering shorter wavelengths like blue and violet.
+        3. This scattered blue light reaches our eyes from all directions, making the sky appear blue!
+        Now, go outside and enjoy that beautiful blue sky!
+        ```
+
+    === "Nous Hermes 2 Mistral DPO"
+        Download `Nous Hermes 2 Mistral DPO` and prompt:
+        ```
+        write me a react app i can run from the command line to play a quick game
+        ```
+
+        With the default sampling settings, you should see text and code blocks resembling the following:
+        
+        ```
+        I'll provide you with a simple React app that allows you to play a guessing game. This app will generate a random number between 1 and 10, and ask you to guess it. You can run this app locally using Create React App. Follow the steps below:
+        Open your terminal or command line interface.
+        Navigate to the directory where you want to create the project (e.g., cd Documents/Projects).
+        Run the following commands:
+        ```
+
+        ```bash
+        npx create-react-app guessing-game
+        cd guessing-game
+        ```
+
+        ```
+        Open the project in your preferred code editor by running code . (for VS Code) or any other command to open the folder with your text editor.
+        Replace the content of the src/App.js file with the following code:
+        ```
+
+        ```javascript
+        import React, { useState } from 'react';
+
+        function App() {
+        const [guess, setGuess] = useState('');
+        const [message, setMessage] = useState('');
+        const [numberToGuess, setNumberToGuess] = useState(Math.floor(Math.random() * 10) + 1);
+
+        function handleChange(e) {
+            setGuess(e.target.value);
+        }
+
+        function handleSubmit(e) {
+            e.preventDefault();
+            if (parseInt(guess) === numberToGuess) {
+            setMessage('You guessed it right!');
+            } else {
+            setMessage(`Wrong guess, the correct number was ${numberToGuess}. Try again next time.`);
+            }
+        }
+
+        return (
+            <div>
+            <h1>Guess a Number</h1>
+            <p>{message}</p>
+            <form onSubmit={handleSubmit}>
+                <input type="number" value={guess} onChange={handleChange} />
+                <button type="submit">Submit</button>
+            </form>
+            </div>
+        );
+        }
+
+        export default App;
+        ```
+
+        ```
+        Save the file and go back to your terminal or command line interface. Run npm start. This will start a local development server, and you can access the app in your browser at http://localhost:3000.
+        Play the guessing game by entering a number between 1 and 10 into the input field and clicking "Submit". The app will tell you if your guess is correct or not.
+        Remember that this is just a simple example, and you can expand upon it to make the game more interesting with additional features like high scores, multiple difficulty levels, etc.
+        ```
+
+## New Chat
+
+Choose a model with the dropdown at the top of the Chats page
+
+If you don't have any models, [download one](models.md#download-models). Once you have models, you can start chats by loading your default model, which you can configure in [settings](settings.md#application-settings)
+
+![Choose a model](../assets/three_model_options.png)
+
+## LocalDocs
+
+Open the [LocalDocs](localdocs.md) panel with the button in the top-right corner to bring your files into the chat. With LocalDocs, your chats are enhanced with semantically related snippets from your files included in the model's context.
+
+![Open LocalDocs](../assets/open_local_docs.png)
+
+## Chat History
+
+View your chat history with the button in the top-left corner of the Chats page.
+
+<table>
+<tr>
+    <td>
+    <img src="../assets/closed_chat_panel.png" alt="Close chats" style="width:100%">
+    </td>
+    <td>
+    <img src="../assets/open_chat_panel.png" alt="Open chats" style="width:100%">
+    </td>
+</tr>
+</table>
+
+You can change a chat name or delete it from your chat history at any time.

docs/gpt4all_desktop/cookbook/use-local-ai-models-to-privately-chat-with-Obsidian.md

@@ -0,0 +1,106 @@
+# Using GPT4All to Privately Chat with your Obsidian Vault
+
+Obsidian for Desktop is a powerful management and note-taking software designed to create and organize markdown notes. This tutorial allows you to sync and access your Obsidian note files directly on your computer. By connecting it to LocalDocs, you can integrate these files into your LLM chats for private access and enhanced context.
+
+## Download Obsidian for Desktop
+
+!!! note "Download Obsidian for Desktop"
+
+      1. **Download Obsidian for Desktop**:
+         - Visit the [Obsidian website](https://obsidian.md) and create an account account.
+         - Click the Download button in the center of the homepage
+         - For more help with installing Obsidian see [Getting Started with Obsidian](https://help.obsidian.md/Getting+started/Download+and+install+Obsidian)
+      
+      2. **Set Up Obsidian**:
+         - Launch Obsidian from your Applications folder (macOS), Start menu (Windows), or equivalent location (Linux).
+         - On the welcome screen, you can either create a new vault (a collection of notes) or open an existing one.
+         - To create a new vault, click Create a new vault, name your vault, choose a location on your computer, and click Create.
+   
+   
+      3. **Sign in and Sync**:
+            - Once installed, you can start adding and organizing notes.
+            - Choose the folders you want to sync to your computer.
+   
+
+
+## Connect Obsidian to LocalDocs
+
+!!! note "Connect Obsidian to LocalDocs"
+
+      1. **Open LocalDocs**:
+         - Navigate to the LocalDocs feature within GPT4All.
+
+         <table>
+            <tr>
+               <td>
+                  <!-- Screenshot of LocalDocs interface -->
+                  <img width="1348" alt="LocalDocs interface" src="https://github.com/nomic-ai/gpt4all/assets/132290469/d8fb2d79-2063-45d4-bcce-7299fb75b144">
+               </td>
+            </tr>
+         </table>
+   
+      2. **Add Collection**:
+         - Click on **+ Add Collection** to begin linking your Obsidian Vault.
+      
+         <table>
+            <tr>
+               <td>
+                  <!-- Screenshot of adding collection in LocalDocs -->
+                  <img width="1348" alt="Screenshot of adding collection" src="https://raw.githubusercontent.com/nomic-ai/gpt4all/main/docs/assets/obsidian_adding_collection.png">
+               </td>
+            </tr>
+         </table>
+   
+         - Name your collection
+   
+   
+      3. **Create Collection**:
+         - Click **Create Collection** to initiate the embedding process. Progress will be displayed within the LocalDocs interface.
+   
+      4. **Access Files in Chats**:
+         - Load a model to chat with your files (Llama 3 Instruct is the fastest)
+         - In your chat, open 'LocalDocs' with the button in the top-right corner to provide context from your synced Obsidian notes.
+      
+         <table>
+            <tr>
+               <td>
+                  <!-- Screenshot of accessing LocalDocs in chats -->
+                  <img width="1447" alt="Accessing LocalDocs in chats" src="https://raw.githubusercontent.com/nomic-ai/gpt4all/main/docs/assets/obsidian_docs.png">
+               </td>
+            </tr>
+         </table>
+   
+      5. **Interact With Your Notes:**
+         - Use the model to interact with your files
+         <table>
+            <tr>
+               <td>
+                  <!-- Screenshot of interacting sources -->
+                  <img width="662" alt="osbsidian user interaction" src="https://raw.githubusercontent.com/nomic-ai/gpt4all/main/docs/assets/osbsidian_user_interaction.png">
+               </td>
+            </tr>
+         </table>
+         <table>
+            <tr>
+               <td>
+                  <!-- Screenshot of viewing sources -->
+                  <img width="662" alt="osbsidian GPT4ALL response" src="https://raw.githubusercontent.com/nomic-ai/gpt4all/main/docs/assets/obsidian_response.png">
+               </td>
+            </tr>
+         </table>
+   
+      6. **View Referenced Files**:
+         - Click on **Sources** below LLM responses to see which Obsidian Notes were referenced.
+      
+         <table>
+            <tr>
+               <td>
+                  <!-- Referenced Files  -->
+                  <img width="643" alt="Referenced Files" src="https://raw.githubusercontent.com/nomic-ai/gpt4all/main/docs/assets/obsidian_sources.png">
+               </td>
+            </tr>
+         </table>
+
+## How It Works
+
+Obsidian for Desktop syncs your Obsidian notes to your computer, while LocalDocs integrates these files into your LLM chats using embedding models. These models find semantically similar snippets from your files to enhance the context of your interactions.

docs/gpt4all_desktop/cookbook/use-local-ai-models-to-privately-chat-with-One-Drive.md

@@ -0,0 +1,112 @@
+# Using GPT4All to Privately Chat with your OneDrive Data
+
+Local and Private AI Chat with your OneDrive Data
+
+OneDrive for Desktop allows you to sync and access your OneDrive files directly on your computer. By connecting your synced directory to LocalDocs, you can start using GPT4All to privately chat with data stored in your OneDrive.
+
+## Download OneDrive for Desktop
+
+!!! note "Download OneDrive for Desktop"
+
+    1. **Download OneDrive for Desktop**:
+    - Visit [Microsoft OneDrive](https://www.microsoft.com/en-us/microsoft-365/onedrive/download).
+    - Press 'download' for your respective device type.
+    - Download the OneDrive for Desktop application.
+    
+    2. **Install OneDrive for Desktop**
+    - Run the installer file you downloaded.
+    - Follow the prompts to complete the installation process.
+    
+    3. **Sign in and Sync**
+    - Once installed, sign in to OneDrive for Desktop with your Microsoft account credentials.
+    - Choose the folders you want to sync to your computer.
+
+## Connect OneDrive to LocalDocs
+
+!!! note "Connect OneDrive to LocalDocs"
+
+    1. **Install GPT4All and Open LocalDocs**:
+    
+        - Go to [nomic.ai/gpt4all](https://nomic.ai/gpt4all) to install GPT4All for your operating system.
+        
+        - Navigate to the LocalDocs feature within GPT4All to configure it to use your synced OneDrive directory.
+
+        <table>
+        <tr>
+            <td>
+                <!-- Placeholder for screenshot of LocalDocs interface -->
+                <img width="1348" alt="Screenshot 2024-07-10 at 10 55 41 AM" src="https://github.com/nomic-ai/gpt4all/assets/132290469/54254bc0-d9a0-40c4-9fd1-5059abaad583">
+            </td>
+        </tr>
+        </table>
+
+    2. **Add Collection**:
+    
+        - Click on **+ Add Collection** to begin linking your OneDrive folders.
+
+        <table>
+        <tr>
+            <td>
+                <!-- Placeholder for screenshot of adding collection in LocalDocs -->
+               <img width="1348" alt="Screenshot 2024-07-10 at 10 56 29 AM" src="https://github.com/nomic-ai/gpt4all/assets/132290469/7f12969a-753a-4757-bb9e-9b607cf315ca">
+            </td>
+        </tr>
+        </table>
+
+        - Name the Collection and specify the OneDrive folder path.
+
+    3. **Create Collection**:
+    
+        - Click **Create Collection** to initiate the embedding process. Progress will be displayed within the LocalDocs interface.
+
+    4. **Access Files in Chats**:
+    
+        - Load a model within GPT4All to chat with your files.
+        
+        - In your chat, open 'LocalDocs' using the button in the top-right corner to provide context from your synced OneDrive files.
+
+        <table>
+        <tr>
+            <td>
+                <!-- Placeholder for screenshot of accessing LocalDocs in chats -->
+                <img width="1447" alt="Screenshot 2024-07-10 at 10 58 55 AM" src="https://github.com/nomic-ai/gpt4all/assets/132290469/b5a67fe6-0d6a-42ae-b3b8-cc0f91cbf5b1">
+            </td>
+        </tr>
+        </table>
+
+    5. **Interact With Your OneDrive**:
+    
+        - Use the model to interact with your files directly from OneDrive.
+        
+        <table>
+        <tr>
+            <td>
+                <!-- Placeholder for screenshot of interacting with sources -->
+                <img width="662" alt="Screenshot 2024-07-10 at 11 04 55 AM" src="https://github.com/nomic-ai/gpt4all/assets/132290469/2c9815b8-3d1c-4179-bf76-3ddbafb193bf">
+            </td>
+        </tr>
+        </table>
+        
+        <table>
+        <tr>
+            <td>
+                <img width="662" alt="Screenshot 2024-07-11 at 11 21 46 AM" src="https://github.com/nomic-ai/gpt4all/assets/132290469/ce8be292-b025-415a-bd54-f11868e0cd0a">
+            </td>
+        </tr>
+        </table>
+
+    6. **View Referenced Files**:
+    
+        - Click on **Sources** below responses to see which OneDrive files were referenced.
+
+        <table>
+        <tr>
+            <td>
+              <img width="643" alt="Screenshot 2024-07-11 at 11 22 49 AM" src="https://github.com/nomic-ai/gpt4all/assets/132290469/6fe3f10d-2791-4153-88a7-2198ab3ac945">
+            </td>
+        </tr>
+        </table>
+
+## How It Works
+
+OneDrive for Desktop syncs your OneDrive files to your computer, while LocalDocs maintains a database of these synced files for use by your local GPT4All model. As your OneDrive updates, LocalDocs will automatically detect file changes and stay up to date. LocalDocs leverages [Nomic Embedding](https://docs.nomic.ai/atlas/capabilities/embeddings) models to find semantically similar snippets from your files, enhancing the context of your interactions.

docs/gpt4all_desktop/cookbook/use-local-ai-models-to-privately-chat-with-google-drive.md

@@ -0,0 +1,113 @@
+# Using GPT4All to Privately Chat with your Google Drive Data
+Local and Private AI Chat with your Google Drive Data
+
+Google Drive for Desktop allows you to sync and access your Google Drive files directly on your computer. By connecting your synced directory to LocalDocs, you can start using GPT4All to privately chat with data stored in your Google Drive.
+
+## Download Google Drive for Desktop
+
+!!! note "Download Google Drive for Desktop"
+
+    1. **Download Google Drive for Desktop**:
+    - Visit [drive.google.com](https://drive.google.com) and sign in with your Google account.
+    - Navigate to the **Settings** (gear icon) and select **Settings** from the dropdown menu.
+    - Scroll down to **Google Drive for desktop** and click **Download**.
+
+    2. **Install Google Drive for Desktop**
+    - Run the installer file you downloaded.
+    - Follow the prompts to complete the installation process.
+
+    3. **Sign in and Sync**
+    - Once installed, sign in to Google Drive for Desktop with your Google account credentials.
+    - Choose the folders you want to sync to your computer.
+
+For advanced help, see [Setting up Google Drive for Desktop](https://support.google.com/drive/answer/10838124?hl=en)
+## Connect Google Drive to LocalDocs
+
+!!! note "Connect Google Drive to LocalDocs"
+
+    1. **Install GPT4All and Open LocalDocs**:
+    
+        - Go to [nomic.ai/gpt4all](https://nomic.ai/gpt4all) to install GPT4All for your operating system.
+        
+        - Navigate to the LocalDocs feature within GPT4All to configure it to use your synced directory.
+
+        <table>
+        <tr>
+            <td>
+                <!-- Screenshot of LocalDocs interface -->
+                <img width="1348" alt="Screenshot 2024-07-09 at 3 15 35 PM" src="https://github.com/nomic-ai/gpt4all/assets/132290469/d8fb2d79-2063-45d4-bcce-7299fb75b144">
+            </td>
+        </tr>
+        </table>
+
+    2. **Add Collection**:
+    
+        - Click on **+ Add Collection** to begin linking your Google Drive folders.
+
+        <table>
+        <tr>
+            <td>
+                <!-- Screenshot of adding collection in LocalDocs -->
+                <img width="1348" alt="Screenshot 2024-07-09 at 3 17 24 PM" src="https://github.com/nomic-ai/gpt4all/assets/132290469/39063615-9eb6-4c47-bde7-c9f04f9b168b">
+            </td>
+        </tr>
+        </table>
+
+        - Name Collection
+
+
+    3. **Create Collection**:
+    
+        - Click **Create Collection** to initiate the embedding process. Progress will be displayed within the LocalDocs interface.
+
+    4. **Access Files in Chats**:
+    
+        - Load a model to chat with your files (Llama 3 Instruct performs best)
+        
+        - In your chat, open 'LocalDocs' with the button in the top-right corner to provide context from your synced Google Drive files.
+
+        <table>
+        <tr>
+            <td>
+                <!-- Screenshot of accessing LocalDocs in chats -->
+                <img width="1447" alt="Screenshot 2024-07-09 at 3 20 53 PM" src="https://github.com/nomic-ai/gpt4all/assets/132290469/ce68811f-9abd-451b-ac0a-fb941e185d7a">
+            </td>
+        </tr>
+        </table>
+
+    5. **Interact With Your Drive:**
+    
+        - Use the model to interact with your files
+        
+        <table>
+        <tr>
+            <td>
+                <!-- Screenshot of interacting sources -->
+                <img width="662" alt="Screenshot 2024-07-09 at 3 36 51 PM" src="https://github.com/nomic-ai/gpt4all/assets/132290469/bc55bc36-e613-419d-a568-adb1cd993854">
+            </td>
+        </tr>
+        </table>
+
+        <table>
+        <tr>
+            <td>
+              <img width="662" alt="Screenshot 2024-07-11 at 11 34 00 AM" src="https://github.com/nomic-ai/gpt4all/assets/132290469/1c0fd19a-5a22-4726-a841-d26c1bea81fc">
+            </td>
+        </tr>
+        </table>
+    
+    6. **View Referenced Files**:
+    
+        - Click on **Sources** below LLM responses to see which Google Drive files were referenced.
+
+        <table>
+        <tr>
+            <td>  
+           <img width="643" alt="Screenshot 2024-07-11 at 11 34 37 AM" src="https://github.com/nomic-ai/gpt4all/assets/132290469/78527d30-8d24-4b4c-8311-b611a2d66fcd">
+            </td>
+        </tr>
+        </table>
+
+## How It Works
+
+Google Drive for Desktop syncs your Google Drive files to your computer, while LocalDocs maintains a database of these synced files for use by your local LLM. As your Google Drive updates, LocalDocs will automatically detect file changes and get up to date. LocalDocs is powered by [Nomic Embedding](https://docs.nomic.ai/atlas/capabilities/embeddings) models which find semantically similar snippets from your files to enhance the context of your interactions.

docs/gpt4all_desktop/cookbook/use-local-ai-models-to-privately-chat-with-microsoft-excel.md

@@ -0,0 +1,85 @@
+# Using GPT4All to Privately Chat with your Microsoft Excel Spreadsheets
+Local and Private AI Chat with your Microsoft Excel Spreadsheets
+
+Microsoft Excel allows you to create, manage, and analyze data in spreadsheet format. By attaching your spreadsheets directly to GPT4All, you can privately chat with the AI to query and explore the data, enabling you to summarize, generate reports, and glean insights from your files—all within your conversation.
+
+<div style="position: relative; padding-bottom: 56.25%; height: 0; overflow: hidden;">
+  <iframe src="../../assets/gpt4all_xlsx_attachment.mp4" style="position: absolute; top: 0; left: 0; width: 100%; height: 100%; border:0;" allowfullscreen title="YouTube Video"></iframe>
+</div>
+
+
+## Attach Microsoft Excel to your GPT4All Conversation
+
+!!! note "Attach Microsoft Excel to your GPT4All Conversation"
+
+    1. **Install GPT4All and Open **:
+
+        - Go to [nomic.ai/gpt4all](https://nomic.ai/gpt4all) to install GPT4All for your operating system.
+
+        - Navigate to the Chats view within GPT4All.
+
+        <table>
+            <tr>
+               <td>
+                  <!-- Screenshot of Chat view -->
+                  <img width="1348" alt="Chat view" src="../../assets/chat_window.png">
+               </td>
+            </tr>
+         </table>
+
+    2. **Example Spreadsheet **:
+
+        <table>
+            <tr>
+               <td>
+                  <!-- Screenshot of Spreadsheet view -->
+                  <img width="1348" alt="Spreadsheet view" src="../../assets/disney_spreadsheet.png">
+               </td>
+            </tr>
+         </table>
+
+    3. **Attach to GPT4All conversration**
+        <table>
+            <tr>
+               <td>
+                  <!-- Screenshot of Attach view -->
+                  <img width="1348" alt="Attach view" src="../../assets/attach_spreadsheet.png">
+               </td>
+            </tr>
+         </table>
+
+    4. **Have GPT4All Summarize and Generate a Report**
+        <table>
+            <tr>
+               <td>
+                  <!-- Screenshot of Attach view -->
+                  <img width="1348" alt="Attach view" src="../../assets/spreadsheet_chat.png">
+               </td>
+            </tr>
+         </table>
+
+
+## How It Works
+
+GPT4All parses your attached excel spreadsheet into Markdown, a format understandable to LLMs, and adds the markdown text to the context for your LLM chat. You can view the code that converts `.xslx` to Markdown [here](https://github.com/nomic-ai/gpt4all/blob/main/gpt4all-chat/src/xlsxtomd.cpp) in the GPT4All github repo.
+
+For example, the above spreadsheet titled `disney_income_stmt.xlsx` would be formatted the following way:
+
+```markdown
+## disney_income_stmt
+
+|Walt Disney Co.|||||||
+|---|---|---|---|---|---|---|
+|Consolidated Income Statement|||||||
+|||||||||
+|US$ in millions|||||||
+|12 months ended:|2023-09-30 00:00:00|2022-10-01 00:00:00|2021-10-02 00:00:00|2020-10-03 00:00:00|2019-09-28 00:00:00|2018-09-29 00:00:00|
+|Services|79562|74200|61768|59265|60542|50869|
+...
+...
+...
+```
+
+## Limitations
+
+It is important to double-check the claims LLMs make about the spreadsheets you provide. LLMs can make mistakes about the data they are presented, particularly for the LLMs with smaller parameter counts (~8B) that fit within the memory of consumer hardware.

docs/gpt4all_desktop/localdocs.md

@@ -0,0 +1,46 @@
+# LocalDocs
+
+LocalDocs brings the information you have from files on-device into your LLM chats - **privately**.
+
+## Create LocalDocs
+
+!!! note "Create LocalDocs"
+
+    1. Click `+ Add Collection`.
+    
+    2. Name your collection and link it to a folder.
+
+        <table>
+        <tr>
+            <td>
+            <img src="../assets/new_docs_annotated.png" alt="new GOT Docs" style="width:100%">
+            </td>
+            <td>
+            <img src="../assets/new_docs_annotated_filled.png" alt="new GOT Docs filled out" style="width:100%">
+            </td>
+        </tr>
+        </table>
+
+    3. Click `Create Collection`. Progress for the collection is displayed on the LocalDocs page. 
+
+        ![Embedding in progress](../assets/baelor.png)
+
+        You will see a green `Ready` indicator when the entire collection is ready. 
+
+        Note: you can still chat with the files that are ready before the entire collection is ready.
+
+        ![Embedding complete](../assets/got_done.png)
+
+        Later on if you modify your LocalDocs settings you can rebuild your collections with your new settings.
+
+    4. In your chats, open `LocalDocs` with button in top-right corner to give your LLM context from those files.
+
+        ![LocalDocs result](../assets/syrio_snippets.png)
+
+    5. See which files were referenced by clicking `Sources` below the LLM responses.
+
+        ![Sources](../assets/open_sources.png)
+
+## How It Works
+
+A LocalDocs collection uses Nomic AI's free and fast on-device embedding models to index your folder into text snippets that each get an **embedding vector**. These vectors allow us to find snippets from your files that are semantically similar to the questions and prompts you enter in your chats. We then include those semantically similar snippets in the prompt to the LLM.

docs/gpt4all_desktop/models.md

@@ -0,0 +1,79 @@
+# Models
+
+GPT4All is optimized to run LLMs in the 3-13B parameter range on consumer-grade hardware.
+
+LLMs are downloaded to your device so you can run them locally and privately. With our backend anyone can interact with LLMs efficiently and securely on their own hardware.
+
+## Download Models
+
+!!! note "Download Models"
+
+    <div style="text-align: center; margin-top: 20px;">
+        <table style="margin-left: auto; margin-right: auto;">
+            <tr>
+                <td style="text-align: right; padding-right: 10px;">1.</td>
+                <td style="text-align: left;">Click `Models` in the menu on the left (below `Chats` and above `LocalDocs`)</td>
+                <td><img src="../assets/models_page_icon.png" alt="Models Page Icon" style="width: 80px; height: auto;"></td>
+            </tr>
+            <tr>
+                <td style="text-align: right; padding-right: 10px;">2.</td>
+                <td style="text-align: left;">Click `+ Add Model` to navigate to the `Explore Models` page</td>
+                <td><img src="../assets/add.png" alt="Add Model button" style="width: 100px; height: auto;"></td>
+            </tr>
+            <tr>
+                <td style="text-align: right; padding-right: 10px;">3.</td>
+                <td style="text-align: left;">Search for models available online</td>
+                <td><img src="../assets/explore.png" alt="Explore Models search" style="width: 120px; height: auto;"></td>
+            </tr>
+            <tr>
+                <td style="text-align: right; padding-right: 10px;">4.</td>
+                <td style="text-align: left;">Hit `Download` to save a model to your device</td>
+                <td><img src="../assets/download.png" alt="Download Models button" style="width: 120px; height: auto;"></td>
+            </tr>
+            <tr>
+                <td style="text-align: right; padding-right: 10px;">5.</td>
+                <td style="text-align: left;">Once the model is downloaded you will see it in `Models`.</td>
+                <td><img src="../assets/installed_models.png" alt="Download Models button" style="width: 120px; height: auto;"></td>
+            </tr>
+        </table>
+    </div>
+
+## Explore Models
+
+GPT4All connects you with LLMs from HuggingFace with a [`llama.cpp`](https://github.com/ggerganov/llama.cpp) backend so that they will run efficiently on your hardware. Many of these models can be identified by the file type `.gguf`.
+
+![Explore models](../assets/search_mistral.png)
+
+## Example Models
+
+Many LLMs are available at various sizes, quantizations, and licenses. 
+
+- LLMs with more parameters tend to be better at coherently responding to instructions
+
+- LLMs with a smaller quantization (e.g. 4bit instead of 16bit) are much faster and less memory intensive, and tend to have slightly worse performance
+
+- Licenses vary in their terms for personal and commercial use
+
+Here are a few examples:
+
+| Model| Filesize| RAM Required| Parameters| Quantization| Developer| License| MD5 Sum (Unique Hash)|
+|------|---------|-------------|-----------|-------------|----------|--------|----------------------|
+| Llama 3 Instruct  | 4.66 GB| 8 GB| 8 Billion| q4_0| Meta| [Llama 3 License](https://llama.meta.com/llama3/license/)| c87ad09e1e4c8f9c35a5fcef52b6f1c9|
+| Nous Hermes 2 Mistral DPO| 4.11 GB| 8 GB| 7 Billion| q4_0| Mistral & Nous Research | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)| Coa5f6b4eabd3992da4d7fb7f020f921eb|
+| Phi-3 Mini Instruct | 2.18 GB| 4 GB| 4 billion| q4_0| Microsoft| [MIT](https://opensource.org/license/mit)| f8347badde9bfc2efbe89124d78ddaf5|
+| Mini Orca (Small)| 1.98 GB| 4 GB| 3 billion| q4_0| Microsoft | [CC-BY-NC-SA-4.0](https://spdx.org/licenses/CC-BY-NC-SA-4.0)| 0e769317b90ac30d6e09486d61fefa26|
+| GPT4All Snoozy| 7.37 GB| 16 GB| 13 billion| q4_0| Nomic AI| [GPL](https://www.gnu.org/licenses/gpl-3.0.en.html)| 40388eb2f8d16bb5d08c96fdfaac6b2c|
+
+### Search Results
+
+You can click the gear icon in the search bar to sort search results by their # of likes, # of downloads, or date of upload (all from HuggingFace).
+
+![Sort search results](../assets/search_settings.png)
+
+## Connect Model APIs
+
+You can add your API key for remote model providers.
+
+**Note**: this does not download a model file to your computer to use securely. Instead, this way of interacting with models has your prompts leave your computer to the API provider and returns the response to your computer.
+
+![Connect APIs](../assets/add_model_gpt4.png)

docs/gpt4all_desktop/quickstart.md

@@ -0,0 +1,42 @@
+# GPT4All Desktop
+
+The GPT4All Desktop Application allows you to download and run large language models (LLMs) locally & privately on your device.
+
+With GPT4All, you can chat with models, turn your local files into information sources for models [(LocalDocs)](localdocs.md), or browse models available online to download onto your device.
+
+[Official Video Tutorial](https://www.youtube.com/watch?v=gQcZDXRVJok)
+
+## Quickstart
+
+!!! note "Quickstart"
+
+    1. Install GPT4All for your operating system and open the application.
+
+        <div style="text-align: center; margin-top: 20px;">
+            [Download for Windows](https://gpt4all.io/installers/gpt4all-installer-win64.exe) &nbsp;&nbsp;&nbsp;&nbsp;
+            [Download for Mac](https://gpt4all.io/installers/gpt4all-installer-darwin.dmg) &nbsp;&nbsp;&nbsp;&nbsp;
+            [Download for Linux](https://gpt4all.io/installers/gpt4all-installer-linux.run)
+        </div>
+
+    2. Hit `Start Chatting`. ![GPT4All home page](../assets/gpt4all_home.png)
+
+    3. Click `+ Add Model`.
+
+    4. Download a model. We recommend starting with Llama 3, but you can [browse more models](models.md). ![Download a model](../assets/download_llama.png)
+
+    5. Once downloaded, go to Chats (below Home and above Models in the menu on the left).  
+
+    6. Click "Load Default Model" (will be Llama 3 or whichever model you downloaded). 
+
+        <table>
+        <tr>
+            <td>
+            <img src="../assets/before_first_chat.png" alt="Before first chat" style="width:100%">
+            </td>
+            <td>
+            <img src="../assets/new_first_chat.png" alt="New first chat" style="width:100%">
+            </td>
+        </tr>
+        </table>
+
+    7. Try the [example chats](chats.md) or your own prompts!

docs/gpt4all_desktop/settings.md

@@ -0,0 +1,78 @@
+# Settings
+
+## Application Settings
+
+!!! note "General Application Settings"
+
+    | Setting | Description | Default Value |
+    | --- | --- | --- |
+    | **Theme** | Color theme for the application. Options are `Light`, `Dark`, and `LegacyDark` | `Light` |
+    | **Font Size** | Font size setting for text throughout the application. Options are Small, Medium, and Large | Small |
+    | **Language and Locale** | The language and locale of that language you wish to use | System Locale |
+    | **Device** | Device that will run your models. Options are `Auto` (GPT4All chooses), `Metal` (Apple Silicon M1+), `CPU`, and `GPU` | `Auto` |
+    | **Default Model** | Choose your preferred LLM to load by default on startup| Auto |
+    | **Suggestion Mode** | Generate suggested follow up questions at the end of responses | When chatting with LocalDocs | 
+    | **Download Path** | Select a destination on your device to save downloaded models | Windows: `C:\Users\{username}\AppData\Local\nomic.ai\GPT4All`<br><br>Mac: `/Users/{username}/Library/Application Support/nomic.ai/GPT4All/`<br><br>Linux: `/home/{username}/.local/share/nomic.ai/GPT4All` |
+    | **Enable Datalake** | Opt-in to sharing interactions with GPT4All community (**anonymous** and **optional**) | Off |
+
+!!! note "Advanced Application Settings"
+
+    | Setting | Description | Default Value |
+    | --- | --- | --- |
+    | **CPU Threads** | Number of concurrently running CPU threads (more can speed up responses) | 4 |
+    | **Enable System Tray** | The application will minimize to the system tray / taskbar when the window is closed | Off |
+    | **Enable Local Server** | Allow any application on your device to use GPT4All via an OpenAI-compatible GPT4All API | Off |
+    | **API Server Port** | Local HTTP port for the local API server | 4891 |
+
+## Model Settings
+
+!!! note "Model / Character Settings"
+
+    | Setting | Description | Default Value |
+    | --- | --- | --- |
+    | **Name** | Unique name of this model / character| set by model uploader |
+    | **Model File** | Filename (.gguf) of the model | set by model uploader |
+    | **System Message** | General instructions for the chats this model will be used for | set by model uploader |
+    | **Chat Template** | Format of user <-> assistant interactions for the chats this model will be used for | set by model uploader |
+    | **Chat Name Prompt** | Prompt used to automatically generate chat names | Describe the above conversation in seven words or less. |
+    | **Suggested FollowUp Prompt** | Prompt used to automatically generate follow up questions after a chat response | Suggest three very short factual follow-up questions that have not been answered yet or cannot be found inspired by the previous conversation and excerpts. |
+
+### Clone
+
+You can **clone** an existing model, which allows you to save a configuration of a model file with different prompt templates and sampling settings.
+
+### Sampling Settings
+
+!!! note "Model Sampling Settings"
+
+    | Setting             | Description                          | Default Value |
+    |----------------------------|------------------------------------------|-----------|
+    | **Context Length**         | Maximum length of input sequence in tokens        | 2048      |
+    | **Max Length**             | Maximum length of response in tokens     | 4096      |
+    | **Temperature**            | Lower temperature gives more likely generations | 0.7       |
+    | **Top P**                  | Prevents choosing highly unlikely tokens  | 0.4       |
+    | **Top K**                  | Size of selection pool for tokens         | 40        |
+    | **Min P**                  | Minimum relative probability              | 0         |
+    | **Repeat Penalty Tokens**  | Length to apply penalty                   | 64        |
+    | **Repeat Penalty**         | Penalize repetitiveness                   | 1.18      |
+    | **GPU Layers**             | How many model layers to load into VRAM     | 32        |
+
+## LocalDocs Settings
+
+!!! note "General LocalDocs Settings"
+
+    | Setting | Description | Default Value |
+    | --- | --- | --- |
+    | **Allowed File Extensions** | Choose which file types will be indexed into LocalDocs collections as text snippets with embedding vectors | `.txt`, `.pdf`, `.md`, `.rst` |
+    | **Use Nomic Embed API** | Use Nomic API to create LocalDocs collections fast and off-device; [Nomic API Key](https://atlas.nomic.ai/) required | Off |
+    | **Embeddings Device** | Device that will run embedding models. Options are `Auto` (GPT4All chooses), `Metal` (Apple Silicon M1+), `CPU`, and `GPU` | `Auto` |
+    | **Show Sources** | Titles of source files retrieved by LocalDocs will be displayed directly in your chats.| On |
+
+!!! note "Advanced LocalDocs Settings"
+
+    Note that increasing these settings can increase the likelihood of factual responses, but may result in slower generation times.
+
+    | Setting | Description | Default Value |
+    | --- | --- | --- |
+    | **Document Snippet Size** | Number of string characters per document snippet | 512 |
+    | **Maximum Document Snippets Per Prompt** | Upper limit for the number of snippets from your files LocalDocs can retrieve for LLM context | 3 |

docs/gpt4all_help/faq.md

@@ -0,0 +1,27 @@
+# Frequently Asked Questions
+
+## Models
+
+### Which language models are supported?
+
+We support models with a `llama.cpp` implementation which have been uploaded to [HuggingFace](https://huggingface.co/).
+
+## Software
+
+### What software do I need?
+
+All you need is to [install GPT4all](../index.md) onto you Windows, Mac, or Linux computer.
+
+### Is there an API?
+
+Yes, you can run your model in server-mode with our [OpenAI-compatible API](https://platform.openai.com/docs/api-reference/completions), which you can configure in [settings](../gpt4all_desktop/settings.md#application-settings)
+
+## Hardware
+
+### What hardware do I need?
+
+GPT4All can run on CPU, Metal (Apple Silicon M1+), and GPU.
+
+### What are the system requirements?
+
+Your CPU needs to support [AVX or AVX2 instructions](https://en.wikipedia.org/wiki/Advanced_Vector_Extensions) and you need enough RAM to load a model into memory.

docs/gpt4all_help/troubleshooting.md

@@ -0,0 +1,27 @@
+# Troubleshooting
+
+## Error Loading Models
+
+It is possible you are trying to load a model from HuggingFace whose weights are not compatible with our [backend](https://github.com/nomic-ai/gpt4all/tree/main/gpt4all-backend).
+
+Try downloading one of the officially supported models listed on the main models page in the application. If the problem persists, please share your experience on our [Discord](https://discord.com/channels/1076964370942267462).
+
+## Bad Responses 
+
+Try the [example chats](../gpt4all_desktop/chats.md) to double check that your system is implementing models correctly.
+
+### Responses Incoherent
+
+If you are seeing something **not at all** resembling the [example chats](../gpt4all_desktop/chats.md) - for example, if the responses you are seeing look nonsensical - try [downloading a different model](../gpt4all_desktop/models.md), and please share your experience on our [Discord](https://discord.com/channels/1076964370942267462).
+
+### Responses Incorrect
+
+LLMs can be unreliable. It's helpful to know what their training data was - they are less likely to be correct when asking about data they were not trained on unless you give the necessary information in the prompt as **context**.
+
+Giving LLMs additional context, like chatting using [LocalDocs](../gpt4all_desktop/localdocs.md), can help merge the language model's ability to understand text with the files that you trust to contain the information you need. 
+
+Including information in a prompt is not a guarantee that it will be used correctly, but the more clear and concise your prompts, and the more relevant your prompts are to your files, the better.
+
+### LocalDocs Issues
+
+Occasionally a model - particularly a smaller or overall weaker LLM - may not use the relevant text snippets from the files that were referenced via LocalDocs. If you are seeing this, it can help to use phrases like "in the docs" or "from the provided files" when prompting your model.

docs/index.md

@@ -0,0 +1,14 @@
+# GPT4All Documentation
+
+GPT4All runs large language models (LLMs) privately on everyday desktops & laptops. 
+
+No API calls or GPUs required - you can just download the application and [get started](gpt4all_desktop/quickstart.md#quickstart).
+
+!!! note "Desktop Application"
+    GPT4All runs LLMs as an application on your computer. Nomic's embedding models can bring information from your local documents and files into your chats. It's fast, on-device, and completely **private**.
+
+    <div style="text-align: center; margin-top: 20px;">
+        [Download for Windows](https://gpt4all.io/installers/gpt4all-installer-win64.exe) &nbsp;&nbsp;&nbsp;&nbsp;
+        [Download for Mac](https://gpt4all.io/installers/gpt4all-installer-darwin.dmg) &nbsp;&nbsp;&nbsp;&nbsp;
+        [Download for Linux](https://gpt4all.io/installers/gpt4all-installer-linux.run)
+    </div>

gpt4all-api/.gitignore

@@ -1,112 +0,0 @@
-# Byte-compiled / optimized / DLL files
-__pycache__/
-app/__pycache__/
-gpt4all_api/__pycache__/
-gpt4all_api/app/api_v1/__pycache__/
-*.py[cod]
-*$py.class
-
-# C extensions
-*.so
-
-# VS Code
-.vscode/
-
-# Distribution / packaging
-.Python
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
-
-# PyInstaller
-#  Usually these files are written by a python script from a template
-#  before PyInstaller builds the exe, so as to inject date/other infos into it.
-*.manifest
-*.spec
-
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
-
-# Unit test / coverage reports
-htmlcov/
-.tox/
-.coverage
-.coverage.*
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-.hypothesis/
-.pytest_cache/
-
-# Translations
-*.mo
-*.pot
-
-# Django stuff:
-*.log
-local_settings.py
-db.sqlite3
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-docs/_build/
-
-# PyBuilder
-target/
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# pyenv
-.python-version
-
-# celery beat schedule file
-celerybeat-schedule
-
-# SageMath parsed files
-*.sage.py
-
-# Environments
-.env
-.venv
-env/
-venv/
-ENV/
-env.bak/
-venv.bak/
-
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
-
-# mypy
-.mypy_cache/
-
-*.lock
-*.cache

gpt4all-api/.isort.cfg

@@ -1,7 +0,0 @@
-[settings]
-known_third_party=geopy,nltk,np,numpy,pandas,pysbd,fire,torch
-
-line_length=120
-include_trailing_comma=True
-multi_line_output=3
-use_parentheses=True

gpt4all-api/LICENSE

@@ -1,13 +0,0 @@
-Copyright 2023 Nomic, Inc.
-
-Licensed under the Apache License, Version 2.0 (the "License");
-you may not use this file except in compliance with the License.
-You may obtain a copy of the License at
-
-    http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software
-distributed under the License is distributed on an "AS IS" BASIS,
-WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-See the License for the specific language governing permissions and
-limitations under the License.

gpt4all-api/README.md

@@ -1,90 +0,0 @@
-# GPT4All REST API
-
-NOTICE: We are considering to deprecate this API as it has become challenging to maintain and test. If you have any interest in maintaining this or would like to takeover and adopt or discuss the future of this API please speak up in the discord channel.
-
-This directory contains the source code to run and build docker images that run a FastAPI app
-for serving inference from GPT4All models. The API matches the OpenAI API spec.
-
-## Tutorial
-
-The following tutorial assumes that you have checked out this repo and cd'd into it.
-
-### Starting the app
-
-First change your working directory to `gpt4all/gpt4all-api`.
-
-Now you can build the FastAPI docker image. You only have to do this on initial build or when you add new dependencies to the requirements.txt file:
-```bash
-DOCKER_BUILDKIT=1 docker build -t gpt4all_api --progress plain -f gpt4all_api/Dockerfile.buildkit .
-```
-
-Then, start the backend with:
-
-```bash
-docker compose up --build
-```
-
-This will run both the API and locally hosted GPU inference server. If you want to run the API without the GPU inference server, you can run:
-
-```bash
-docker compose up --build gpt4all_api
-```
-
-To run the API with the GPU inference server, you will need to include environment variables (like the `MODEL_ID`). Edit the `.env` file and run
-```bash
-docker compose --env-file .env up --build
-```
-
-
-#### Spinning up your app
-Run `docker compose up` to spin up the backend. Monitor the logs for errors in-case you forgot to set an environment variable above.
-
-
-#### Development
-Run
-
-```bash
-docker compose up --build
-```
-and edit files in the `app` directory. The api will hot-reload on changes.
-
-You can run the unit tests with
-
-```bash
-make test
-```
-
-#### Viewing API documentation
-
-Once the FastAPI ap is started you can access its documentation and test the search endpoint by going to:
-```
-localhost:80/docs
-```
-
-This documentation should match the OpenAI OpenAPI spec located at https://github.com/openai/openai-openapi/blob/master/openapi.yaml
-
-
-#### Running inference
-```python
-import openai
-openai.api_base = "http://localhost:4891/v1"
-
-openai.api_key = "not needed for a local LLM"
-
-
-def test_completion():
-    model = "gpt4all-j-v1.3-groovy"
-    prompt = "Who is Michael Jordan?"
-    response = openai.Completion.create(
-        model=model,
-        prompt=prompt,
-        max_tokens=50,
-        temperature=0.28,
-        top_p=0.95,
-        n=1,
-        echo=True,
-        stream=False
-    )
-    assert len(response['choices'][0]['text']) > len(prompt)
-    print(response)
-```

gpt4all-api/docker-compose.gpu.yaml

@@ -1,24 +0,0 @@
-version: "3.8"
-
-services:
-  gpt4all_gpu:
-    image: ghcr.io/huggingface/text-generation-inference:0.9.3
-    container_name: gpt4all_gpu
-    restart: always #restart on error (usually code compilation from save during bad state)
-    environment:
-      - HUGGING_FACE_HUB_TOKEN=token
-      - USE_FLASH_ATTENTION=false
-      - MODEL_ID=''
-      - NUM_SHARD=1
-    command: --model-id $MODEL_ID --num-shard $NUM_SHARD
-    volumes:
-      - ./:/data
-    ports:
-      - "8080:80"
-    shm_size: 1g
-    deploy:
-      resources:
-        reservations:
-          devices:
-            - driver: nvidia
-              capabilities: [gpu]

gpt4all-api/docker-compose.yaml

@@ -1,22 +0,0 @@
-version: "3.8"
-
-services:
-  gpt4all_api:
-    image: gpt4all_api
-    container_name: gpt4all_api
-    restart: always #restart on error (usually code compilation from save during bad state)
-    ports:
-      - "4891:4891"
-    env_file:
-      - .env
-    environment:
-      - APP_ENVIRONMENT=dev
-      - WEB_CONCURRENCY=2
-      - LOGLEVEL=debug
-      - PORT=4891
-      - model=${MODEL_BIN} # using variable from .env file
-      - inference_mode=cpu
-    volumes:
-      - './gpt4all_api/app:/app'
-      - './gpt4all_api/models:/models' # models are mounted in the container
-    command: ["/start-reload.sh"]

gpt4all-api/gpt4all_api/Dockerfile.buildkit

@@ -1,17 +0,0 @@
-# syntax=docker/dockerfile:1.0.0-experimental
-FROM tiangolo/uvicorn-gunicorn:python3.11
-
-# Put first so anytime this file changes other cached layers are invalidated.
-COPY gpt4all_api/requirements.txt /requirements.txt
-
-RUN pip install --upgrade pip
-
-# Run various pip install commands with ssh keys from host machine.
-RUN --mount=type=ssh pip install -r /requirements.txt && \
-  rm -Rf /root/.cache && rm -Rf /tmp/pip-install*
-
-# Finally, copy app and client.
-COPY gpt4all_api/app /app
-
-RUN mkdir -p /models
-

gpt4all-api/gpt4all_api/README.md

@@ -1 +0,0 @@
-# FastAPI app for serving GPT4All models

gpt4all-api/gpt4all_api/app/api_v1/api.py

@@ -1,9 +0,0 @@
-from api_v1.routes import chat, completions, engines, health
-from fastapi import APIRouter
-
-router = APIRouter()
-
-router.include_router(chat.router)
-router.include_router(completions.router)
-router.include_router(engines.router)
-router.include_router(health.router)

gpt4all-api/gpt4all_api/app/api_v1/events.py

@@ -1,29 +0,0 @@
-import logging
-
-from api_v1.settings import settings
-from fastapi import HTTPException
-from fastapi.responses import JSONResponse
-from starlette.requests import Request
-
-log = logging.getLogger(__name__)
-
-
-startup_msg_fmt = """
- Starting up GPT4All API
-"""
-
-
-async def on_http_error(request: Request, exc: HTTPException):
-    return JSONResponse({'detail': exc.detail}, status_code=exc.status_code)
-
-
-async def on_startup(app):
-    startup_msg = startup_msg_fmt.format(settings=settings)
-    log.info(startup_msg)
-
-
-def startup_event_handler(app):
-    async def start_app() -> None:
-        await on_startup(app)
-
-    return start_app

gpt4all-api/gpt4all_api/app/api_v1/routes/chat.py

@@ -1,103 +0,0 @@
-import logging
-import time
-from typing import List
-from uuid import uuid4
-from fastapi import APIRouter, HTTPException
-from gpt4all import GPT4All
-from pydantic import BaseModel, Field
-from api_v1.settings import settings
-from fastapi.responses import StreamingResponse
-
-logger = logging.getLogger(__name__)
-logger.setLevel(logging.DEBUG)
-
-### This should follow https://github.com/openai/openai-openapi/blob/master/openapi.yaml
-class ChatCompletionMessage(BaseModel):
-    role: str
-    content: str
-
-class ChatCompletionRequest(BaseModel):
-    model: str = Field(settings.model, description='The model to generate a completion from.')
-    messages: List[ChatCompletionMessage] = Field(..., description='Messages for the chat completion.')
-    temperature: float = Field(settings.temp, description='Model temperature')
-
-class ChatCompletionChoice(BaseModel):
-    message: ChatCompletionMessage
-    index: int
-    logprobs: float
-    finish_reason: str
-
-class ChatCompletionUsage(BaseModel):
-    prompt_tokens: int
-    completion_tokens: int
-    total_tokens: int
-
-class ChatCompletionResponse(BaseModel):
-    id: str
-    object: str = 'text_completion'
-    created: int
-    model: str
-    choices: List[ChatCompletionChoice]
-    usage: ChatCompletionUsage
-
-router = APIRouter(prefix="/chat", tags=["Completions Endpoints"])
-
-@router.post("/completions", response_model=ChatCompletionResponse)
-async def chat_completion(request: ChatCompletionRequest):
-    '''
-    Completes a GPT4All model response based on the last message in the chat.
-    '''
-    # GPU is not implemented yet
-    if settings.inference_mode == "gpu":
-        raise HTTPException(status_code=400,
-              detail=f"Not implemented yet: Can only infer in CPU mode.")
-
-    # we only support the configured model
-    if request.model != settings.model:
-        raise HTTPException(status_code=400,
-              detail=f"The GPT4All inference server is booted to only infer: `{settings.model}`")
-
-    # run only of we have a message
-    if request.messages:
-        model = GPT4All(model_name=settings.model, model_path=settings.gpt4all_path)
-
-        # format system message and conversation history correctly
-        formatted_messages = ""
-        for message in request.messages:
-            formatted_messages += f"<|im_start|>{message.role}\n{message.content}<|im_end|>\n"
-
-        # the LLM will complete the response of the assistant
-        formatted_messages += "<|im_start|>assistant\n"
-        response = model.generate(
-            prompt=formatted_messages,
-            temp=request.temperature
-            )
-
-        # the LLM may continue to hallucinate the conversation, but we want only the first response
-        # so, cut off everything after first <|im_end|>
-        index = response.find("<|im_end|>")
-        response_content = response[:index].strip()
-    else:
-        response_content = "No messages received."
-
-    # Create a chat message for the response
-    response_message = ChatCompletionMessage(role="assistant", content=response_content)
-
-    # Create a choice object with the response message
-    response_choice = ChatCompletionChoice(
-        message=response_message,
-        index=0,
-        logprobs=-1.0,  # Placeholder value
-        finish_reason="length"  # Placeholder value
-    )
-
-    # Create the response object
-    chat_response = ChatCompletionResponse(
-        id=str(uuid4()),
-        created=int(time.time()),
-        model=request.model,
-        choices=[response_choice],
-        usage=ChatCompletionUsage(prompt_tokens=0, completion_tokens=0, total_tokens=0),  # Placeholder values
-    )
-
-    return chat_response

gpt4all-api/gpt4all_api/app/api_v1/routes/completions.py

@@ -1,215 +0,0 @@
-import json
-from typing import List, Dict, Iterable, AsyncIterable
-import logging
-import time
-from typing import Dict, List, Union, Optional
-from uuid import uuid4
-import aiohttp
-import asyncio
-from api_v1.settings import settings
-from fastapi import APIRouter, Depends, Response, Security, status, HTTPException
-from fastapi.responses import StreamingResponse
-from gpt4all import GPT4All
-from pydantic import BaseModel, Field
-
-logger = logging.getLogger(__name__)
-logger.setLevel(logging.DEBUG)
-
-
-### This should follow https://github.com/openai/openai-openapi/blob/master/openapi.yaml
-
-
-class CompletionRequest(BaseModel):
-    model: str = Field(settings.model, description='The model to generate a completion from.')
-    prompt: Union[List[str], str] = Field(..., description='The prompt to begin completing from.')
-    max_tokens: int = Field(None, description='Max tokens to generate')
-    temperature: float = Field(settings.temp, description='Model temperature')
-    top_p: Optional[float] = Field(settings.top_p, description='top_p')
-    top_k: Optional[int] = Field(settings.top_k, description='top_k')
-    n: int = Field(1, description='How many completions to generate for each prompt')
-    stream: bool = Field(False, description='Stream responses')
-    repeat_penalty: float = Field(settings.repeat_penalty, description='Repeat penalty')
-
-
-class CompletionChoice(BaseModel):
-    text: str
-    index: int
-    logprobs: float
-    finish_reason: str
-
-
-class CompletionUsage(BaseModel):
-    prompt_tokens: int
-    completion_tokens: int
-    total_tokens: int
-
-
-class CompletionResponse(BaseModel):
-    id: str
-    object: str = 'text_completion'
-    created: int
-    model: str
-    choices: List[CompletionChoice]
-    usage: CompletionUsage
-
-
-class CompletionStreamResponse(BaseModel):
-    id: str
-    object: str = 'text_completion'
-    created: int
-    model: str
-    choices: List[CompletionChoice]
-
-
-router = APIRouter(prefix="/completions", tags=["Completion Endpoints"])
-
-def stream_completion(output: Iterable, base_response: CompletionStreamResponse):
-    """
-    Streams a GPT4All output to the client.
-
-    Args:
-        output: The output of GPT4All.generate(), which is an iterable of tokens.
-        base_response: The base response object, which is cloned and modified for each token.
-
-    Returns:
-        A Generator of CompletionStreamResponse objects, which are serialized to JSON Event Stream format.
-    """
-    for token in output:
-        chunk = base_response.copy()
-        chunk.choices = [dict(CompletionChoice(
-            text=token,
-            index=0,
-            logprobs=-1,
-            finish_reason=''
-        ))]
-        yield f"data: {json.dumps(dict(chunk))}\n\n"
-
-async def gpu_infer(payload, header):
-    async with aiohttp.ClientSession() as session:
-        try:
-            async with session.post(
-                settings.hf_inference_server_host, headers=header, data=json.dumps(payload)
-            ) as response:
-                resp = await response.json()
-            return resp
-
-        except aiohttp.ClientError as e:
-            # Handle client-side errors (e.g., connection error, invalid URL)
-            logger.error(f"Client error: {e}")
-        except aiohttp.ServerError as e:
-            # Handle server-side errors (e.g., internal server error)
-            logger.error(f"Server error: {e}")
-        except json.JSONDecodeError as e:
-            # Handle JSON decoding errors
-            logger.error(f"JSON decoding error: {e}")
-        except Exception as e:
-            # Handle other unexpected exceptions
-            logger.error(f"Unexpected error: {e}")
-
-@router.post("/", response_model=CompletionResponse)
-async def completions(request: CompletionRequest):
-    '''
-    Completes a GPT4All model response.
-    '''
-    if settings.inference_mode == "gpu":
-        params = request.dict(exclude={'model', 'prompt', 'max_tokens', 'n'})
-        params["max_new_tokens"] = request.max_tokens
-        params["num_return_sequences"] = request.n
-
-        header = {"Content-Type": "application/json"}
-        if isinstance(request.prompt, list):
-            tasks = []
-            for prompt in request.prompt:
-                payload = {"parameters": params}
-                payload["inputs"] = prompt
-                task = gpu_infer(payload, header)
-                tasks.append(task)
-            results = await asyncio.gather(*tasks)
-
-            choices = []
-            for response in results:
-                scores = response["scores"] if "scores" in response else -1.0
-                choices.append(
-                    dict(
-                        CompletionChoice(
-                            text=response["generated_text"], index=0, logprobs=scores, finish_reason='stop'
-                        )
-                    )
-                )
-
-            return CompletionResponse(
-                id=str(uuid4()),
-                created=time.time(),
-                model=request.model,
-                choices=choices,
-                usage={'prompt_tokens': 0, 'completion_tokens': 0, 'total_tokens': 0},
-            )
-
-        else:
-            payload = {"parameters": params}
-            # If streaming, we need to return a StreamingResponse
-            payload["inputs"] = request.prompt
-
-            resp = await gpu_infer(payload, header)
-
-            output = resp["generated_text"]
-            # this returns all logprobs
-            scores = resp["scores"] if "scores" in resp else -1.0
-
-            return CompletionResponse(
-                id=str(uuid4()),
-                created=time.time(),
-                model=request.model,
-                choices=[dict(CompletionChoice(text=output, index=0, logprobs=scores, finish_reason='stop'))],
-                usage={'prompt_tokens': 0, 'completion_tokens': 0, 'total_tokens': 0},
-            )
-
-    else:
-
-        if request.model != settings.model:
-            raise HTTPException(status_code=400,
-                                detail=f"The GPT4All inference server is booted to only infer: `{settings.model}`")
-
-        if isinstance(request.prompt, list):
-            if len(request.prompt) > 1:
-                raise HTTPException(status_code=400, detail="Can only infer one inference per request in CPU mode.")
-            else:
-                request.prompt = request.prompt[0]
-
-        model = GPT4All(model_name=settings.model, model_path=settings.gpt4all_path)
-
-        output = model.generate(prompt=request.prompt,
-                                max_tokens=request.max_tokens,
-                                streaming=request.stream,
-                                top_k=request.top_k,
-                                top_p=request.top_p,
-                                temp=request.temperature,
-                                )
-
-        # If streaming, we need to return a StreamingResponse
-        if request.stream:
-            base_chunk = CompletionStreamResponse(
-                id=str(uuid4()),
-                created=time.time(),
-                model=request.model,
-                choices=[]
-            )
-            return StreamingResponse((response for response in stream_completion(output, base_chunk)),
-                                     media_type="text/event-stream")
-        else:
-            return CompletionResponse(
-                id=str(uuid4()),
-                created=time.time(),
-                model=request.model,
-                choices=[dict(CompletionChoice(
-                    text=output,
-                    index=0,
-                    logprobs=-1,
-                    finish_reason='stop'
-                ))],
-                usage={
-                    'prompt_tokens': 0,  # TODO how to compute this?
-                    'completion_tokens': 0,
-                    'total_tokens': 0
-                }
-            )

gpt4all-api/gpt4all_api/app/api_v1/routes/embeddings.py

@@ -1,65 +0,0 @@
-from typing import List, Union
-from fastapi import APIRouter
-from api_v1.settings import settings
-from gpt4all import Embed4All
-from pydantic import BaseModel, Field
-
-### This should follow https://github.com/openai/openai-openapi/blob/master/openapi.yaml
-
-
-class EmbeddingRequest(BaseModel):
-    model: str = Field(
-        settings.model, description="The model to generate an embedding from."
-    )
-    input: Union[str, List[str], List[int], List[List[int]]] = Field(
-        ..., description="Input text to embed, encoded as a string or array of tokens."
-    )
-
-
-class EmbeddingUsage(BaseModel):
-    prompt_tokens: int = 0
-    total_tokens: int = 0
-
-
-class Embedding(BaseModel):
-    index: int = 0
-    object: str = "embedding"
-    embedding: List[float]
-
-
-class EmbeddingResponse(BaseModel):
-    object: str = "list"
-    model: str
-    data: List[Embedding]
-    usage: EmbeddingUsage
-
-
-router = APIRouter(prefix="/embeddings", tags=["Embedding Endpoints"])
-
-embedder = Embed4All()
-
-
-def get_embedding(data: EmbeddingRequest) -> EmbeddingResponse:
-    """
-    Calculates the embedding for the given input using a specified model.
-
-    Args:
-        data (EmbeddingRequest): An EmbeddingRequest object containing the input data
-        and model name.
-
-    Returns:
-        EmbeddingResponse: An EmbeddingResponse object encapsulating the calculated embedding,
-        usage info, and the model name.
-    """
-    embedding = embedder.embed(data.input)
-    return EmbeddingResponse(
-        data=[Embedding(embedding=embedding)], usage=EmbeddingUsage(), model=data.model
-    )
-
-
-@router.post("/", response_model=EmbeddingResponse)
-def embeddings(data: EmbeddingRequest):
-    """
-    Creates a GPT4All embedding
-    """
-    return get_embedding(data)

gpt4all-api/gpt4all_api/app/api_v1/routes/engines.py

@@ -1,39 +0,0 @@
-import requests
-from fastapi import APIRouter, HTTPException
-from pydantic import BaseModel, Field
-from typing import List, Dict
-
-# Define the router for the engines module
-router = APIRouter(prefix="/engines", tags=["Search Endpoints"])
-
-# Define the models for the engines module
-class ListEnginesResponse(BaseModel):
-    data: List[Dict] = Field(..., description="All available models.")
-
-class EngineResponse(BaseModel):
-    data: List[Dict] = Field(..., description="All available models.")
-
-
-# Define the routes for the engines module
-@router.get("/", response_model=ListEnginesResponse)
-async def list_engines():
-    try:
-        response = requests.get('https://raw.githubusercontent.com/nomic-ai/gpt4all/main/gpt4all-chat/metadata/models2.json')
-        response.raise_for_status()  # This will raise an HTTPError if the HTTP request returned an unsuccessful status code
-        engines = response.json()
-        return ListEnginesResponse(data=engines)
-    except requests.RequestException as e:
-        logger.error(f"Error fetching engine list: {e}")
-        raise HTTPException(status_code=500, detail="Error fetching engine list")
-
-# Define the routes for the engines module
-@router.get("/{engine_id}", response_model=EngineResponse)
-async def retrieve_engine(engine_id: str):
-    try:
-        # Implement logic to fetch a specific engine's details
-        # This is a placeholder, replace with your actual data retrieval logic
-        engine_details = {"id": engine_id, "name": "Engine Name", "description": "Engine Description"}
-        return EngineResponse(data=[engine_details])
-    except Exception as e:
-        logger.error(f"Error fetching engine details: {e}")
-        raise HTTPException(status_code=500, detail=f"Error fetching details for engine {engine_id}")

gpt4all-api/gpt4all_api/app/api_v1/routes/health.py

@@ -1,13 +0,0 @@
-import logging
-from fastapi import APIRouter
-from fastapi.responses import JSONResponse
-
-log = logging.getLogger(__name__)
-
-router = APIRouter(prefix="/health", tags=["Health"])
-
-
-@router.get('/', response_class=JSONResponse)
-async def health_check():
-    """Runs a health check on this instance of the API."""
-    return JSONResponse({'status': 'ok'}, headers={'Access-Control-Allow-Origin': '*'})

gpt4all-api/gpt4all_api/app/api_v1/settings.py

@@ -1,19 +0,0 @@
-from pydantic import BaseSettings
-
-
-class Settings(BaseSettings):
-    app_environment = 'dev'
-    model: str = 'ggml-mpt-7b-chat.bin'
-    gpt4all_path: str = '/models'
-    inference_mode: str = "cpu"
-    hf_inference_server_host: str = "http://gpt4all_gpu:80/generate"
-    sentry_dns: str = None
-
-    temp: float = 0.18
-    top_p: float = 1.0
-    top_k: int = 50
-    repeat_penalty: float = 1.18
-
-
-
-settings = Settings()

gpt4all-api/gpt4all_api/app/docs.py

@@ -1,3 +0,0 @@
-desc = 'GPT4All API'
-
-endpoint_paths = {'health': '/health'}

gpt4all-api/gpt4all_api/app/main.py

@@ -1,84 +0,0 @@
-import logging
-import os
-
-import docs
-from api_v1 import events
-from api_v1.api import router as v1_router
-from api_v1.settings import settings
-from fastapi import FastAPI, HTTPException, Request
-from fastapi.logger import logger as fastapi_logger
-from starlette.middleware.cors import CORSMiddleware
-
-logger = logging.getLogger(__name__)
-
-app = FastAPI(title='GPT4All API', description=docs.desc)
-
-# CORS Configuration (in-case you want to deploy)
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=["*"],
-    allow_credentials=True,
-    allow_methods=["GET", "POST", "OPTIONS"],
-    allow_headers=["*"],
-)
-
-logger.info('Adding v1 endpoints..')
-
-# add v1
-app.include_router(v1_router, prefix='/v1')
-app.add_event_handler('startup', events.startup_event_handler(app))
-app.add_exception_handler(HTTPException, events.on_http_error)
-
-
-@app.on_event("startup")
-async def startup():
-    global model
-    if settings.inference_mode == "cpu":
-        logger.info(f"Downloading/fetching model: {os.path.join(settings.gpt4all_path, settings.model)}")
-        from gpt4all import GPT4All
-
-        model = GPT4All(model_name=settings.model, model_path=settings.gpt4all_path)
-
-        logger.info(f"GPT4All API is ready to infer from {settings.model} on CPU.")
-
-    else:
-        # is it possible to do this once the server is up?
-        ## TODO block until HF inference server is up.
-        logger.info(f"GPT4All API is ready to infer from {settings.model} on CPU.")
-
-
-
-@app.on_event("shutdown")
-async def shutdown():
-    logger.info("Shutting down API")
-
-
-if settings.sentry_dns is not None:
-    import sentry_sdk
-
-    def traces_sampler(sampling_context):
-        if 'health' in sampling_context['transaction_context']['name']:
-            return False
-
-    sentry_sdk.init(
-        dsn=settings.sentry_dns, traces_sample_rate=0.1, traces_sampler=traces_sampler, send_default_pii=False
-    )
-
-# This is needed to get logs to show up in the app
-if "gunicorn" in os.environ.get("SERVER_SOFTWARE", ""):
-    gunicorn_error_logger = logging.getLogger("gunicorn.error")
-    gunicorn_logger = logging.getLogger("gunicorn")
-
-    root_logger = logging.getLogger()
-    fastapi_logger.setLevel(gunicorn_logger.level)
-    fastapi_logger.handlers = gunicorn_error_logger.handlers
-    root_logger.setLevel(gunicorn_logger.level)
-
-    uvicorn_logger = logging.getLogger("uvicorn.access")
-    uvicorn_logger.handlers = gunicorn_error_logger.handlers
-else:
-    # https://github.com/tiangolo/fastapi/issues/2019
-    LOG_FORMAT2 = (
-        "[%(asctime)s %(process)d:%(threadName)s] %(name)s - %(levelname)s - %(message)s | %(filename)s:%(lineno)d"
-    )
-    logging.basicConfig(level=logging.INFO, format=LOG_FORMAT2)

gpt4all-api/gpt4all_api/app/tests/test_endpoints.py

@@ -1,93 +0,0 @@
-"""
-Use the OpenAI python API to test gpt4all models.
-"""
-from typing import List, get_args
-import os
-from dotenv import load_dotenv
-
-import openai
-
-openai.api_base = "http://localhost:4891/v1"
-openai.api_key = "not needed for a local LLM"
-
-# Load the .env file
-env_path = 'gpt4all-api/gpt4all_api/.env'
-load_dotenv(dotenv_path=env_path)
-
-# Fetch MODEL_ID from .env file
-model_id = os.getenv('MODEL_BIN', 'default_model_id')
-embedding = os.getenv('EMBEDDING', 'default_embedding_model_id')
-print (model_id)
-print (embedding)
-
-def test_completion():
-    model = model_id
-    prompt = "Who is Michael Jordan?"
-    response = openai.Completion.create(
-        model=model, prompt=prompt, max_tokens=50, temperature=0.28, top_p=0.95, n=1, echo=True, stream=False
-    )
-    assert len(response['choices'][0]['text']) > len(prompt)
-
-def test_streaming_completion():
-    model = model_id
-    prompt = "Who is Michael Jordan?"
-    tokens = []
-    for resp in openai.Completion.create(
-            model=model,
-            prompt=prompt,
-            max_tokens=50,
-            temperature=0.28,
-            top_p=0.95,
-            n=1,
-            echo=True,
-            stream=True):
-        tokens.append(resp.choices[0].text)
-
-    assert (len(tokens) > 0)
-    assert (len("".join(tokens)) > len(prompt))
-
-# Modified test batch, problems with keyerror in response
-def test_batched_completion():
-    model = model_id  # replace with your specific model ID
-    prompt = "Who is Michael Jordan?"
-    responses = []
-
-    # Loop to create completions one at a time
-    for _ in range(3):
-        response = openai.Completion.create(
-            model=model, prompt=prompt, max_tokens=50, temperature=0.28, top_p=0.95, n=1, echo=True, stream=False
-        )
-        responses.append(response)
-
-    # Assertions to check the responses
-    for response in responses:
-        assert len(response['choices'][0]['text']) > len(prompt)
-
-    assert len(responses) == 3
-
-def test_embedding():
-    model = embedding
-    prompt = "Who is Michael Jordan?"
-    response = openai.Embedding.create(model=model, input=prompt)
-    output = response["data"][0]["embedding"]
-    args = get_args(List[float])
-
-    assert response["model"] == model
-    assert isinstance(output, list)
-    assert all(isinstance(x, args) for x in output)
-
-def test_chat_completion():
-    model = model_id
-
-    response = openai.ChatCompletion.create(
-        model=model,
-        messages=[
-            {"role": "system", "content": "You are a helpful assistant."},
-            {"role": "user", "content": "Knock knock."},
-            {"role": "assistant", "content": "Who's there?"},
-            {"role": "user", "content": "Orange."},
-            ]
-    )
-
-    assert response.choices[0].message.role == "assistant"
-    assert len(response.choices[0].message.content) > 0

gpt4all-api/gpt4all_api/env

@@ -1,3 +0,0 @@
-# Add your GGUF compatible model LLM here. ie: MODEL_BIN="mistral-7b-instruct-v0.1.Q4_0", rename file ".env"
-# Make sure this LLM matches the model you placed inside the models folder
-MODEL_BIN=""

gpt4all-api/gpt4all_api/models/README.md

@@ -1 +0,0 @@
-### Drop GGUF compatible models here, make sure it matches MODEL_BIN on your .env file

gpt4all-api/gpt4all_api/requirements.txt

@@ -1,13 +0,0 @@
-aiohttp>=3.6.2
-aiofiles
-pydantic>=1.4.0,<2.0.0
-requests>=2.24.0
-ujson>=2.0.2
-fastapi>=0.95.0
-Jinja2>=3.0
-gpt4all>=1.0.0
-pytest
-openai==0.28.0
-black
-isort
-python-dotenv

gpt4all-api/makefile

@@ -1,46 +0,0 @@
-ROOT_DIR:=$(shell dirname $(realpath $(lastword $(MAKEFILE_LIST))))
-APP_NAME:=gpt4all_api
-PYTHON:=python3.8
-SHELL := /bin/bash
-
-all: dependencies
-
-fresh: clean dependencies
-
-testenv: clean_testenv test_build
-	docker compose -f docker-compose.yaml up --build
-
-testenv_gpu: clean_testenv test_build
-	docker compose -f docker-compose.yaml -f docker-compose.gpu.yaml up --build
-
-testenv_d: clean_testenv test_build
-	docker compose env up --build -d
-
-test:
-	docker compose exec $(APP_NAME) pytest -svv --disable-warnings -p no:cacheprovider /app/tests
-
-test_build:
-    DOCKER_BUILDKIT=1 docker build -t $(APP_NAME) --progress plain -f $(APP_NAME)/Dockerfile.buildkit .
-
-clean_testenv:
-	docker compose down -v
-
-fresh_testenv: clean_testenv testenv
-
-venv:
-	if [ ! -d $(ROOT_DIR)/venv ]; then $(PYTHON) -m venv $(ROOT_DIR)/venv; fi
-
-dependencies: venv
-	source $(ROOT_DIR)/venv/bin/activate; $(PYTHON) -m pip install -r $(ROOT_DIR)/$(APP_NAME)/requirements.txt
-
-clean: clean_testenv
-	# Remove existing environment
-	rm -rf $(ROOT_DIR)/venv;
-	rm -rf $(ROOT_DIR)/$(APP_NAME)/*.pyc;
-
-
-black:
-	source $(ROOT_DIR)/venv/bin/activate; black -l 120 -S --target-version py38 $(APP_NAME)
-
-isort:
-	source $(ROOT_DIR)/venv/bin/activate; isort  --ignore-whitespace --atomic -w 120 $(APP_NAME)