Skip to content

WIP: Replace llama.cpp with ollama #3542

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
wants to merge 40 commits into
base: main
Choose a base branch
from
Draft

WIP: Replace llama.cpp with ollama #3542

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
40 commits
Select commit Hold shift + click to select a range
8e94409
WIP: gpt4all backend stub
cebtenzzre Feb 13, 2025
9bfab99
WIP: remove bindings and all references to them
cebtenzzre Feb 13, 2025
b194d71
WIP: backend dependencies
cebtenzzre Feb 18, 2025
c6d0a1f
enable color diagnostics with ninja
cebtenzzre Feb 18, 2025
f4a350d
WIP: working fmt dep
cebtenzzre Feb 18, 2025
729a5b0
ollama-hpp immediately segfaulted. will try something else
cebtenzzre Feb 18, 2025
196c387
WIP: bring back old backend so we can test the gpt4all-chat build
cebtenzzre Feb 20, 2025
97a2e18
WIP: fix import order and enable module scanning
cebtenzzre Feb 20, 2025
98a27c9
WIP: update llama.cpp submodule for -Werror workaround
cebtenzzre Feb 20, 2025
bca31e6
WIP: fork fmt to fix missing string_view support
cebtenzzre Feb 20, 2025
ebe6352
WIP (hit a clang bug causing an incorrect compiler error)
cebtenzzre Feb 21, 2025
1699e77
WIP: get build working on macOS
cebtenzzre Feb 21, 2025
39102d8
fix .gitmodules
cebtenzzre Feb 21, 2025
407cb81
stop using C++20 modules
cebtenzzre Feb 24, 2025
e592a58
fix test
cebtenzzre Feb 25, 2025
daf48a5
fix test harder (it works now)
cebtenzzre Feb 25, 2025
b5144de
fix #includes
cebtenzzre Feb 25, 2025
927e963
parse the JSON response
cebtenzzre Feb 25, 2025
06475dd
WIP: use Boost::json for incremental parsing and reflection
cebtenzzre Feb 26, 2025
4c5dcf5
rename the class to "OllamaClient"
cebtenzzre Feb 26, 2025
86de26e
implement and test /api/tags
cebtenzzre Feb 26, 2025
e872f1d
undercores to dashes
cebtenzzre Feb 26, 2025
85eaa41
base url should include /api/
cebtenzzre Feb 26, 2025
7ce2ea5
implement /api/show (not tested)
cebtenzzre Feb 27, 2025
d4e9a61
finished initial impl of /show and tested -> hangs!
cebtenzzre Feb 27, 2025
cc6f995
fix #includes
cebtenzzre Feb 27, 2025
9f130b0
fix qcoro infinite recursion
cebtenzzre Feb 27, 2025
ea2ced8
fix json EOF handling
cebtenzzre Feb 27, 2025
068845e
don't duplicate QCoro's exception passing
cebtenzzre Feb 27, 2025
d20cfbb
stuff is working now
cebtenzzre Feb 27, 2025
1ba555a
fix handling of responses that come in chunks, and non-200 status codes
cebtenzzre Feb 28, 2025
1dc9f22
WIP
cebtenzzre Mar 3, 2025
7745f20
WIP (clang is crashing)
cebtenzzre Mar 11, 2025
f7cd880
make it build - still plenty of TODOs
cebtenzzre Mar 11, 2025
bcbbe51
WIP (fixing compile errors)
cebtenzzre Mar 12, 2025
371971e
WIP: fix build
cebtenzzre Mar 12, 2025
8294a5c
WIP: need to run rr on a real computer since this bug is confusing
cebtenzzre Mar 17, 2025
9772027
WIP: provider page in the "add models" view
cebtenzzre Mar 19, 2025
b359c92
WIP
cebtenzzre Mar 19, 2025
f71f857
WIP: provider types are recongized properly in qml
cebtenzzre Mar 19, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 0 additions & 2 deletions .circleci/config.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,4 @@ workflows:
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-chat/.* run-chat-workflow true
Loading