GitLab

If someone checks out the ollama repo and doesn't install the CUDA
library, this will ensure they can build a CPU only version

- remove ggml runner
- automatically pull gguf models when ggml detected
- tell users to update to gguf in the case automatic pull fails
Co-Authored-By: Jeffrey Morgan <jmorganca@gmail.com>

this info has not been returned from these endpoints in some time

* add multimodal docs

* add chat api docs

* consistency between `/api/generate` and `/api/chat`

* simplify docs

---------
Co-authored-by: Matt Apperson <mattapperson@Matts-MacBook-Pro.local>

Signed-off-by: Xe Iaso <xe@camellia.finch-kitefin.ts.net>

Thank you @calderonsamuel 

This reverts commit 7a0899d6.

Signed-off-by: Matt Williams <m@technovangelist.com>

- update chat docs
- add messages chat endpoint
- remove deprecated context and template generate parameters from docs
- context and template are still supported for the time being and will continue to work as expected
- add partial response to chat history

* Add OllamaEmbeddings to python LangChain example

* typo

---------
Co-authored-by: Alec Hammond <alechammond@fb.com>

Fix a typo in the CA update command

* Documented viewing Modelfiles in ollama.ai/library

* Moved Modelfile in ollama.ai down per request

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>