github/gpt4all
1
0
Fork 0
mirror of https://github.com/nomic-ai/gpt4all.git synced 2025-09-03 17:44:34 +00:00
Code Issues Packages Projects Releases Wiki Activity

V3 docs max (#2488)

Browse Source 
* new skeleton

Signed-off-by: Max Cembalest <max@nomic.ai>

* v3 docs

Signed-off-by: Max Cembalest <max@nomic.ai>

---------

Signed-off-by: Max Cembalest <max@nomic.ai>
This commit is contained in:
mcembalest
2024-07-01 13:00:14 -04:00
committed by GitHub
parent bd307abfe6
commit 5306595176
57 changed files with 865 additions and 170 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
gpt4all-bindings/python/docs/gpt4all_help/faq.md Normal file
View File

@@ -0,0 +1,49 @@
# Frequently Asked Questions
## Models
### Which language models are supported?
Our backend supports models with a `llama.cpp` implementation which have been uploaded to [HuggingFace](https://huggingface.co/).
### Which embedding models are supported?
The following embedding models can be used within the application and with the `Embed4All` class from the `gpt4all` Python library. The default context length as GGUF files is 2048 but can be [extended](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5-GGUF#description).
| Name | Initializing with `Embed4All` | Context Length | Embedding Length | File Size |
|--------------------|------------------------------------------------------|---------------:|-----------------:|----------:|
| [SBert](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2)| ```pythonemb = Embed4All("all-MiniLM-L6-v2.gguf2.f16.gguf")```| 512 | 384 | 44 MiB |
| [Nomic Embed v1](https://huggingface.co/nomic-ai/nomic-embed-text-v1-GGUF) | nomic&#x2011;embed&#x2011;text&#x2011;v1.f16.gguf| 2048 | 768 | 262 MiB |
| [Nomic Embed v1.5](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5-GGUF) | nomic&#x2011;embed&#x2011;text&#x2011;v1.5.f16.gguf| 2048 | 64-768 | 262 MiB |
## Software
### What software do I need?
All you need is to [install GPT4all](../index.md) onto you Windows, Mac, or Linux computer.
### Which SDK languages are supported?
Our SDK is in Python for usability, but these are light bindings around [`llama.cpp`](https://github.com/ggerganov/llama.cpp) implementations that we contribute to for efficiency and accessibility on everyday computers.
### 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)
### Can I monitor a GPT4All deployment?
Yes, GPT4All [integrates](../gpt4all_python/monitoring.md) with [OpenLIT](https://github.com/openlit/openlit) so you can deploy LLMs with user interactions and hardware usage automatically monitored for full observability.
### Is there a command line interface (CLI)?
[Yes](https://github.com/nomic-ai/gpt4all/tree/main/gpt4all-bindings/cli), we have a lightweight use of the Python client as a CLI. We welcome further contributions!
## 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. If the

27
gpt4all-bindings/python/docs/gpt4all_help/troubleshooting.md Normal file
View File

@@ -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-bindings).
Try downloading one of the officially supported models mentioned our [website](https://gpt4all.io/). 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.