* Use pb.Reply instead of []byte with Reply.GetMessage() in llama grpc to get the proper usage data in reply streaming mode at the last [DONE] frame
* Fix 'hang' on empty message from the start
Seems like that empty message marker trick was unnecessary
---------
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* Read jinja templates as fallback
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Move templating out of model loader
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Test TemplateMessages
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Set role and content from transformers
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Tests: be more flexible
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* More jinja
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Small refactoring and adaptations
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Use pb.Reply instead of []byte with Reply.GetMessage() in llama grpc to get the proper usage data in reply streaming mode at the last [DONE] frame
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* feat(backends): Drop bert.cpp
use llama.cpp 3.2 as a drop-in replacement for bert.cpp
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore(tests): make test more robust
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Instead of trying to derive it from the model file. In backends that
specify HF url this results in a fragile logic.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This is in order to identify also builds which are not using
alternatives based on capabilities.
For instance, there are cases when we build the backend only natively in
the host.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(llama-cpp): consistently select fallback
We didn't took in consideration the case where the host has the CPU
flagset, but the binaries were not actually present in the asset dir.
This made possible for instance for models that specified the llama-cpp
backend directly in the config to not eventually pick-up the fallback
binary in case the optimized binaries were not present.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore: adjust and simplify selection
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix: move failure recovery to BackendLoader()
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* comments
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* minor fixups
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
If the LLM does not implement any logic for PredictStream, we close the
channel immediately to not leave the process hanging.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
We default to a soft kill, however, we might want to force killing
backends after a while to avoid hanging requests (which may hallucinate
indefinetly)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore(refactor): track internally started models by ID
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Just extend options, no need to copy
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Improve debugging for rerankers failures
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Simplify model loading with rerankers
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Be more consistent when generating model options
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Uncommitted code
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Make deleteProcess more idiomatic
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Adapt CLI for sound generation
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Fixup threads definition
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Handle corner case where c.Seed is nil
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Consistently use ModelOptions
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Adapt new code to refactoring
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Dave <dave@gray101.com>
* Add Get Token Metrics to GRPC server
Signed-off-by: Siddharth More <siddimore@gmail.com>
* Expose LocalAI endpoint
Signed-off-by: Siddharth More <siddimore@gmail.com>
---------
Signed-off-by: Siddharth More <siddimore@gmail.com>
* chore(refactor): track grpcProcess in the model structure
This avoids to have to handle in two parts the data relative to the same
model. It makes it easier to track and use mutex with.
This also fixes races conditions while accessing to the model.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore(tests): run protogen-go before starting aio tests
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore(tests): install protoc in aio tests
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* add api key to existing app tests, add preliminary auth test
Signed-off-by: Dave Lee <dave@gray101.com>
* small fix, run test
Signed-off-by: Dave Lee <dave@gray101.com>
* status on non-opaque
Signed-off-by: Dave Lee <dave@gray101.com>
* tweak auth error
Signed-off-by: Dave Lee <dave@gray101.com>
* exp
Signed-off-by: Dave Lee <dave@gray101.com>
* quick fix on real laptop
Signed-off-by: Dave Lee <dave@gray101.com>
* add downloader version that allows providing an auth header
Signed-off-by: Dave Lee <dave@gray101.com>
* stash some devcontainer fixes during testing
Signed-off-by: Dave Lee <dave@gray101.com>
* s2
Signed-off-by: Dave Lee <dave@gray101.com>
* s
Signed-off-by: Dave Lee <dave@gray101.com>
* done with experiment
Signed-off-by: Dave Lee <dave@gray101.com>
* done with experiment
Signed-off-by: Dave Lee <dave@gray101.com>
* after merge fix
Signed-off-by: Dave Lee <dave@gray101.com>
* rename and fix
Signed-off-by: Dave Lee <dave@gray101.com>
---------
Signed-off-by: Dave Lee <dave@gray101.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
This prepares the API to receive videos as well for video understanding.
It works similarly to images, where the request should be in the form:
{
"type": "video_url",
"video_url": { "url": "url or base64 data" }
}
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore(refactor): drop duplicated shutdown logics
- Handle locking in Shutdown and CheckModelIsLoaded in a more go-idiomatic way
- Drop duplicated code and re-organize shutdown code
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix: drop leftover
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore: improve logging and add missing locks
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(shutdown): do not shutdown immediately busy backends
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore(refactor): avoid duplicate functions
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix: multiplicative backoff for shutdown (#3547)
* multiplicative backoff for shutdown
Rather than always retry every two seconds, back off the shutdown attempt rate?
Signed-off-by: Dave <dave@gray101.com>
* Update loader.go
Signed-off-by: Dave <dave@gray101.com>
* add clamp of 2 minutes
Signed-off-by: Dave Lee <dave@gray101.com>
---------
Signed-off-by: Dave <dave@gray101.com>
Signed-off-by: Dave Lee <dave@gray101.com>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Signed-off-by: Dave <dave@gray101.com>
Signed-off-by: Dave Lee <dave@gray101.com>
Co-authored-by: Dave <dave@gray101.com>
* feat: add endpoint to list system informations
For now, it lists the available backends, but can be expanded later on
to include more system informations (such as GPU devices detected, RAM,
threads configured, and so on so forth).
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* show also external backends
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* add test
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Due to a previous refactor we moved the client constructor tight to the
model address, however that was just a string which we would use to
build the client each time.
With this change we make the loader to return a *Model which carries a
constructor for the client and stores the client on the first
connection.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* initial version of elevenlabs compatible soundgeneration api and cli command
Signed-off-by: Dave Lee <dave@gray101.com>
* minor cleanup
Signed-off-by: Dave Lee <dave@gray101.com>
* restore TTS, add test
Signed-off-by: Dave Lee <dave@gray101.com>
* remove stray s
Signed-off-by: Dave Lee <dave@gray101.com>
* fix
Signed-off-by: Dave Lee <dave@gray101.com>
---------
Signed-off-by: Dave Lee <dave@gray101.com>
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* specify workdir when launching external backend for safety / relative paths, bump version, logs
Signed-off-by: Dave Lee <dave@gray101.com>
* sneak in a devcontainer fix
Signed-off-by: Dave Lee <dave@gray101.com>
---------
Signed-off-by: Dave Lee <dave@gray101.com>
chore: drop gpt4all
gpt4all is already supported in llama.cpp - the backend was kept for
keeping compatibility with old gpt4all models (prior to gguf format).
It is good time now to clean up and remove it to slim the compilation
process.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(openai): add json_schema and strict mode
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* handle err vs _
security scanners prefer if we put these branches in, and I tend to agree.
Signed-off-by: Dave <dave@gray101.com>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Signed-off-by: Dave <dave@gray101.com>
Co-authored-by: Dave <dave@gray101.com>
* fix(downloader): be consistent in downloading files
This PR puts some order in the downloader such as functions are re-used
across several places.
This fixes an issue with having uri's inside the model YAML file, it
would resolve to MD5 rather then using the filename
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(scanner): do raise error only if unsafeFiles are found
Fixes: https://github.com/mudler/LocalAI/issues/3114
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* wip
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* get rid of panics
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* expose it properly from the config
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Simplify
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* forgot to commit
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Remove focus on test
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Small fixups
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* refactor: break down json grammar parser in different files
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix: patch to `refactor_grammars` - propagate errors (#3006)
propagate errors around
Signed-off-by: Dave Lee <dave@gray101.com>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Signed-off-by: Dave Lee <dave@gray101.com>
Co-authored-by: Dave <dave@gray101.com>
* fix(cuda): downgrade to 12.0 to increase compatibility range
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* improve messaging
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(functions): enhance parsing with broken JSON when we parse the raw results
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* breaking: make function name by default
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(grammar): dynamically generate grammars with mutating keys
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* refactor: simplify condition
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Update docs
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(models): pull models from urls
When using `run` now we can point directly to hf models via URL, for
instance:
```bash
local-ai run
huggingface://TheBloke/TinyLlama-1.1B-Chat-v0.3-GGUF/tinyllama-1.1b-chat-v0.3.Q2_K.gguf
```
Will pull the gguf model and place it in the models folder - of course
this depends on the fact that the gguf file should be automatically
detected by our guesser mechanism in order to this to make effective.
Similarly now galleries can refer to single files in the API requests.
This also changes the download code and `yaml` files now are treated in
the same way, so now config files are saved with the appropriate name
(and not hashed anymore).
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Adapt tests
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
fix(model-list): be consistent, skip known files from listing
This changeset does two things:
- Removes the dependency of listing models from the OpenAI schema.
- Tries to reduce confusion between ListModels() in model loader and in
the service - now there is only one ListModels which is in services
and does not depend anymore on the OpenAI schema
- The OpenAI-schema functions were moved nearby the OpenAI specific
endpoints that needs the schema
- Drops the ListModel Service structure as there was no real need for
it.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* start by checking /scan during the checksum update
Signed-off-by: Dave Lee <dave@gray101.com>
* add back in golang side features: downloader/uri gets struct and scan function, gallery uses it, and secscan/models calls it.
Signed-off-by: Dave Lee <dave@gray101.com>
* add a param to scan specific urls - useful for debugging
Signed-off-by: Dave Lee <dave@gray101.com>
* helpful printouts
Signed-off-by: Dave Lee <dave@gray101.com>
* fix offsets
Signed-off-by: Dave Lee <dave@gray101.com>
* fix error and naming
Signed-off-by: Dave Lee <dave@gray101.com>
* expose error
Signed-off-by: Dave Lee <dave@gray101.com>
* fix json tags
Signed-off-by: Dave Lee <dave@gray101.com>
* slight wording change
Signed-off-by: Dave Lee <dave@gray101.com>
* go mod tidy - getting warnings
Signed-off-by: Dave Lee <dave@gray101.com>
* split out python to make editing easier, add some simple code to delete contaminated entries from gallery
Signed-off-by: Dave Lee <dave@gray101.com>
* o7 to my favorite part of our old name, go-skynet
Signed-off-by: Dave Lee <dave@gray101.com>
* merge fix
Signed-off-by: Dave Lee <dave@gray101.com>
* merge fix
Signed-off-by: Dave Lee <dave@gray101.com>
* merge fix
Signed-off-by: Dave Lee <dave@gray101.com>
* address review comments
Signed-off-by: Dave Lee <dave@gray101.com>
* forgot secscan could accept multiple URL at once
Signed-off-by: Dave Lee <dave@gray101.com>
* invert naming and actually use it
Signed-off-by: Dave Lee <dave@gray101.com>
* missed cli/models.go
Signed-off-by: Dave Lee <dave@gray101.com>
* Update .github/check_and_update.py
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Signed-off-by: Dave <dave@gray101.com>
---------
Signed-off-by: Dave Lee <dave@gray101.com>
Signed-off-by: Dave <dave@gray101.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* refactor(gallery): move under core/
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(unarchive): do not allow symlinks
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
contains simple fixes to warnings and errors, removes a broken / outdated test, runs go mod tidy, and as the actual change, centralizes base64 image handling
Signed-off-by: Dave Lee <dave@gray101.com>
* Support specifying oci:// and ollama:// for model URLs
Fixes: https://github.com/mudler/LocalAI/issues/2527
Fixes: https://github.com/mudler/LocalAI/issues/1028
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Lower watcher warnings
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Allow to install ollama models from CLI
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fixup tests
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Do not keep file ownership
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Skip test on darwin
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
When offering fallback libs, use the proper env var for darwin
Note: this does not include the libraries itself, but only sets the
proper env var for the libs to be picked up on darwin.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* WIP
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* gen a static page instead (we force DNS redirects to it)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(gallery): install models from CLI, unify install
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Uniform graphic of model page
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Makefile: update targets
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Slightly enhance gallery view
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* ci: try to build for arm64
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Allow to skip hipblas on make dist
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* use arm64 cross compiler
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* correctly target go arm64
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* create a separate target
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* cross-compile grpc
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Add Protobuf include dirs
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* temp disable CUDA build
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* aarch64 builds: Reduce backends
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Even less backends
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Even less backends
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(startup): allow to load libs from extracted assets
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* makefile: set arch
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(amdgpu): try to build in single binary
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Release space from worker
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* pass basePath down to pkg/downloader
Signed-off-by: Dave Lee <dave@gray101.com>
* enforce
Signed-off-by: Dave Lee <dave@gray101.com>
---------
Signed-off-by: Dave Lee <dave@gray101.com>
* models(gallery): add mistral-0.3 and command-r, update functions
Add also disable_parallel_new_lines to disable newlines in the JSON
output when forcing parallel tools. Some models (like mistral) might be
very sensible to that when being used for function calling.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* models(gallery): add aya-23-8b
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(functions): relax mixedgrammars
Extend even more the functionalities and when mixed mode is enabled,
tolerate also both strings and JSON in the result - in this case we make
sure that the JSON can be correctly parsed.
This also updates the examples and the gallery model to configure the
grammar.
The changeset also breaks current function/grammar configuration as it
reserves now a stanza in the YAML config.
For example:
```yaml
function:
grammar:
# This allows the grammar to also return messages
mixed_mode: true
# Suffix to add to the grammar
# prefix: '<tool_call>\n'
# Force parallel calls in the grammar
# parallel_calls: true
```
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* refactor, add a way to disable mixed json and freestring
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Fix linting issues
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(llama.cpp): Enable decentralized, distributed inference
As https://github.com/mudler/LocalAI/pull/2324 introduced distributed inferencing thanks to
@rgerganov implementation in https://github.com/ggerganov/llama.cpp/pull/6829 in upstream llama.cpp, now
it is possible to distribute the workload to remote llama.cpp gRPC server.
This changeset now uses mudler/edgevpn to establish a secure, distributed network between the nodes using a shared token.
The token is generated automatically when starting the server with the `--p2p` flag, and can be used by starting the workers
with `local-ai worker p2p-llama-cpp-rpc` by passing the token via environment variable (TOKEN) or with args (--token).
As per how mudler/edgevpn works, a network is established between the server and the workers with dht and mdns discovery protocols,
the llama.cpp rpc server is automatically started and exposed to the underlying p2p network so the API server can connect on.
When the HTTP server is started, it will discover the workers in the network and automatically create the port-forwards to the service locally.
Then llama.cpp is configured to use the services.
This feature is behind the "p2p" GO_FLAGS
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* go mod tidy
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* ci: add p2p tag
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* better message
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(functions): allow to use JSONRegexMatch unconditionally
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(functions): make json_regex_match a list
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
feat(functions): support mixed JSON BNF grammar
This PR provides new options to control how functions are extracted from
the LLM, and also provides more control on how JSON grammars can be used
(also in conjunction).
New YAML settings introduced:
- `grammar_message`: when enabled, the generated grammar can also decide
to push strings and not only JSON objects. This allows the LLM to pick
to either respond freely or using JSON.
- `grammar_prefix`: Allows to prefix a string to the JSON grammar
definition.
- `replace_results`: Is a map that allows to replace strings in the LLM
result.
As an example, consider the following settings for Hermes-2-Pro-Mistral,
which allow extracting both JSON results coming from the model, and the
ones coming from the grammar:
```yaml
function:
# disable injecting the "answer" tool
disable_no_action: true
# This allows the grammar to also return messages
grammar_message: true
# Suffix to add to the grammar
grammar_prefix: '<tool_call>\n'
return_name_in_function_response: true
# Without grammar uncomment the lines below
# Warning: this is relying only on the capability of the
# LLM model to generate the correct function call.
# no_grammar: true
# json_regex_match: "(?s)<tool_call>(.*?)</tool_call>"
replace_results:
"<tool_call>": ""
"\'": "\""
```
Note: To disable entirely grammars usage in the example above, uncomment the
`no_grammar` and `json_regex_match`.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* auto select cpu variant
Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
* remove cuda target for now
Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
* fix metal
Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
* fix path
Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
* cuda
Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
* auto select cuda
Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
* update test
Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
* select CUDA backend only if present
Signed-off-by: mudler <mudler@localai.io>
* ci: keep cuda bin in path
Signed-off-by: mudler <mudler@localai.io>
* Makefile: make dist now builds also cuda
Signed-off-by: mudler <mudler@localai.io>
* Keep pushing fallback in case auto-flagset/nvidia fails
There could be other reasons for which the default binary may fail. For example we might have detected an Nvidia GPU,
however the user might not have the drivers/cuda libraries installed in the system, and so it would fail to start.
We keep the fallback of llama.cpp at the end of the llama.cpp backends to try to fallback loading in case things go wrong
Signed-off-by: mudler <mudler@localai.io>
* Do not build cuda on MacOS
Signed-off-by: mudler <mudler@localai.io>
* cleanup
Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
* Apply suggestions from code review
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
---------
Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Signed-off-by: mudler <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Co-authored-by: mudler <mudler@localai.io>
When enabling grammar with functions, it might be useful to
allow more flexibility to support models that are fine-tuned against returning
function calls of the form of { "name": "function_name", "arguments" {...} }
rather then { "function": "function_name", "arguments": {..} }.
This might call out to a more generic approach later on, but for the moment being we can easily support both
as we have just to specific different types.
If needed we can expand on this later on
Signed-off-by: mudler <mudler@localai.io>
* feat(ui): allow to set system prompt for chat
Make also the models in the index clickable, and display as table
Fixes#2257
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(vision): support also png with base64 input
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(ui): support vision and upload of files
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* display the processed image
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* make trust remote code stand out
Signed-off-by: mudler <mudler@localai.io>
* feat(ui): track in progress job across index/model gallery
Signed-off-by: mudler <mudler@localai.io>
* minor fixups
Signed-off-by: mudler <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Signed-off-by: mudler <mudler@localai.io>
* ux: change welcome when there are no models installed
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* ux: filter
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* ux: show tags in filter
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* wip
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* make tags clickable
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* allow to delete models from the list
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* ui: display icon of installed models
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* gallery: remove gallery file when removing model
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(gallery): show a re-install button
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* make filter buttons, rename Gallery field
Signed-off-by: mudler <mudler@localai.io>
* show again buttons at end of operations
Signed-off-by: mudler <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Signed-off-by: mudler <mudler@localai.io>
* feat(initializer): do not specify backends to autoload
We can simply try to autoload the backends extracted in the asset dir.
This will allow to build variants of the same backend (for e.g. with different instructions sets),
so to have a single binary for all the variants.
Signed-off-by: mudler <mudler@localai.io>
* refactor(prepare): refactor out llama.cpp prepare steps
Make it so are idempotent and that we can re-build
Signed-off-by: mudler <mudler@localai.io>
* [TEST] feat(build): build noavx version along
Signed-off-by: mudler <mudler@localai.io>
* build: make build parallel
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* build: do not override CMAKE_ARGS
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* build: add fallback variant
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Fixups
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(huggingface-langchain): fail if no token is set
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(huggingface-langchain): rename
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix: do not autoload local-store
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix: give priority between the listed backends
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: mudler <mudler@localai.io>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* start breaking up the giant channel refactor now that it's better understood - easier to merge bites
Signed-off-by: Dave Lee <dave@gray101.com>
* add concurrency and base64 back in, along with new base64 tests.
Signed-off-by: Dave Lee <dave@gray101.com>
* Automatic rename of whisper.go's Result to TranscriptResult
Signed-off-by: Dave Lee <dave@gray101.com>
* remove pkg/concurrency - significant changes coming in split 2
Signed-off-by: Dave Lee <dave@gray101.com>
* fix comments
Signed-off-by: Dave Lee <dave@gray101.com>
* add list_model service as another low-risk service to get it out of the way
Signed-off-by: Dave Lee <dave@gray101.com>
* split backend config loader into seperate file from the actual config struct. No changes yet, just reduce cognative load with smaller files of logical blocks
Signed-off-by: Dave Lee <dave@gray101.com>
* rename state.go ==> application.go
Signed-off-by: Dave Lee <dave@gray101.com>
* fix lost import?
Signed-off-by: Dave Lee <dave@gray101.com>
---------
Signed-off-by: Dave Lee <dave@gray101.com>
* feat(gallery): op now supports deletion of models
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Wire things with WebUI(WIP)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* minor improvements
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* refactor(template): isolate and add tests
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Signed-off-by: Dave <dave@gray101.com>
Co-authored-by: Dave <dave@gray101.com>
* fix: initial work towards not committing generated files to the repository
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* feat: improve build docs
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: remove unused folder from .dockerignore and .gitignore
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: attempt to fix extra backend tests
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: attempt to fix other tests
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: more test fixes
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: fix apple tests
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: more extras tests fixes
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: add GOBIN to PATH in docker build
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: extra tests and Dockerfile corrections
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: remove build dependency checks
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: add golang protobuf compilers to tests-linux action
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: ensure protogen is run for extra backend installs
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: use newer protobuf
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: more missing protoc binaries
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: missing dependencies during docker build
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: don't install grpc compilers in the final stage if they aren't needed
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: python-grpc-tools in 22.04 repos is too old
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: add a couple of extra build dependencies to Makefile
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: unbreak container rebuild functionality
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
---------
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* Initial implementation of assistants api
* Move load/save configs to utils
* Save assistant and assistantfiles config to disk.
* Add tsets for assistant api
* Fix models path spelling mistake.
* Remove personal go.mod information
---------
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* fix(go-llama): use llama-cpp as default
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* fix(backends): drop obsoleted lines
---------
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* feat(elevenlabs): map elevenlabs API support to TTS
This allows elevenlabs Clients to work automatically with LocalAI by
supporting the elevenlabs API.
The elevenlabs server endpoint is implemented such as it is wired to the
TTS endpoints.
Fixes: https://github.com/mudler/LocalAI/issues/1809
* feat(openai/tts): compat layer with openai tts
Fixes: #1276
* fix: adapt tts CLI
* feat(intel): add diffusers support
* try to consume upstream container image
* Debug
* Manually install deps
* Map transformers/hf cache dir to modelpath if not specified
* fix(compel): update initialization, pass by all gRPC options
* fix: add dependencies, implement transformers for xpu
* base it from the oneapi image
* Add pillow
* set threads if specified when launching the API
* Skip conda install if intel
* defaults to non-intel
* ci: add to pipelines
* prepare compel only if enabled
* Skip conda install if intel
* fix cleanup
* Disable compel by default
* Install torch 2.1.0 with Intel
* Skip conda on some setups
* Detect python
* Quiet output
* Do not override system python with conda
* Prefer python3
* Fixups
* exllama2: do not install without conda (overrides pytorch version)
* exllama/exllama2: do not install if not using cuda
* Add missing dataset dependency
* Small fixups, symlink to python, add requirements
* Add neural_speed to the deps
* correctly handle model offloading
* fix: device_map == xpu
* go back at calling python, fixed at dockerfile level
* Exllama2 restricted to only nvidia gpus
* Tokenizer to xpu
* core 1
* api/openai/files fix
* core 2 - core/config
* move over core api.go and tests to the start of core/http
* move over localai specific endpoints to core/http, begin the service/endpoint split there
* refactor big chunk on the plane
* refactor chunk 2 on plane, next step: port and modify changes to request.go
* easy fixes for request.go, major changes not done yet
* lintfix
* json tag lintfix?
* gitignore and .keep files
* strange fix attempt: rename the config dir?
This PR specifically introduces a `core` folder and moves the following packages over, without any other changes:
- `api/backend`
- `api/config`
- `api/options`
- `api/schema`
Once this is merged and we confirm there's no regressions, I can migrate over the remaining changes piece by piece to split up application startup, backend services, http, and mqtt as was the goal of the earlier PRs!
* Initial implementation of upload files api.
* Move sanitize method to utils.
* Save uploaded data to uploads folder.
* Avoid loop if we do not have a purpose.
* Minor cleanup of api and fix bug where deleting duplicate filename cause error.
* Revert defer of saving config
* Moved creation of directory to startup.
* Make file names unique when storing on disk.
* Add test for files api.
* Update dependencies.
* feat(tools): support Tools in the API
Co-authored-by: =?UTF-8?q?Stephan=20A=C3=9Fmus?= <stephan.assmus@sap.com>
* feat(tools): support function streaming
* Adhere to new return types when using tools instead of functions
* Keep backward compatibility with function calling
* Evaluate function names in chat templates
* Disable recovery with --debug
* Correctly stream out the entire result
* Detect when llm chooses to reply and to not perform any action in SSE
* Feedback from code review
---------
Co-authored-by: =?UTF-8?q?Stephan=20A=C3=9Fmus?= <stephan.assmus@sap.com>
* cleanup backends
* switch image to ubuntu 22.04
* adapt commands for ubuntu
* transformers cleanup
* no contrib on ubuntu
* Change test model to gguf
* ci: disable bark tests (too cpu-intensive)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* cleanup
* refinements
* use intel base image
* Makefile: Add docker targets
* Change test model
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* move downloader out
* separate startup functions for preloading configuration files
* docs: add popular model examples
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* shorteners
* Add llava
* Add mistral-openorca
* Better link to build section
* docs: update
* fixup
* Drop code dups
* Minor fixups
* Apply suggestions from code review
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* ci: try to cache gRPC build during tests
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* ci: do not build all images for tests, just necessary
* ci: cache gRPC also in release pipeline
* fixes
* Update model_preload_test.go
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* feat: allow to pass by models via args
* expose it also as an env/arg
* docs: enhancements to build/requirements
* do not display status always
* print download status
* not all mesages are debug
* feat: Allow inline templates
* feat: Allow to specify url in model config files
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* feat: support 'huggingface://' format
* style: reuse-code from gallery
---------
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* refactor: rename llama-stable to llama-ggml
* Makefile: get sources in sources/
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fixup path
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fixup sources
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fixups sd
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* update SD
* fixup
* fixup: create piper libdir also when not built
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix make target on linux test
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat: allow to run parallel requests
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fixup
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* refactor: move backends into the backends directory
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* refactor: move main close to implementation for every backend
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(llama.cpp): support lora with scale
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(llama.cpp): support yarn
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* wip
* wip
* Make it functional
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* wip
* Small fixups
* do not inject space on role encoding, encode img at beginning of messages
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Add examples/config defaults
* Add include dir of current source dir
* cleanup
* fixes
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fixups
* Revert "fixups"
This reverts commit f1a4731cca.
* fixes
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Fix backend/cpp/llama CMakeList.txt on OSX - detect OSX and use homebrew libraries
* sneak a logging fix in too for gallery debugging
* additional logging
* wip: llama.cpp c++ gRPC server
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* make it work, attach it to the build process
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* update deps
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix: add protobuf dep
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* try fix protobuf on cmake
* cmake: workarounds
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* add packages
* cmake: use fixed version of grpc
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* cmake(grpc): install locally
* install grpc
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* install required deps for grpc on debian bullseye
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* debug
* debug
* Fixups
* no need to install cmake manually
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* ci: fixup macOS
* use brew whenever possible
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* macOS fixups
* debug
* fix container build
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* workaround
* try mac
https://stackoverflow.com/questions/23905661/on-mac-g-clang-fails-to-search-usr-local-include-and-usr-local-lib-by-def
* Disable temp. arm64 docker image builds
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This PR bundles together two unrelated features:
1. Model Gallery improvements - specifically, the ability to follow
".ref" gallery links (which I made up for this specific application) to
an actual gallery yaml file (in order to have stable URLs) and the
ability to load self-contained configurations, rather than always using
a base.yaml + overrides. This is groundwork for my python-based
huggingface scraper.
2. A while ago I introduced some Insomnia request templates for people
to use. Unfortunately, Insomnia has decided to tank their product... So
I've personally switched to using
[bruno](https://github.com/usebruno/bruno/). Corresponding equivalent
files that I use for my testing have been added. Just open the folder
from bruno and everything will work. No import process required.
---------
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
This particularly useful to set AWQ
**Description**
Follow up of #1015
**Notes for Reviewers**
**[Signed
commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)**
- [ ] Yes, I signed my commits.
<!--
Thank you for contributing to LocalAI!
Contributing Conventions:
1. Include descriptive PR titles with [<component-name>] prepended.
2. Build and test your changes before submitting a PR.
3. Sign your commits
By following the community's contribution conventions upfront, the
review process will
be accelerated and your PR merged more quickly.
-->
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
**Description**
This PR fixes#1013.
It adds `draft_model` and `n_draft` to the model YAML config in order to
load models with speculative sampling. This should be compatible as well
with grammars.
example:
```yaml
backend: llama
context_size: 1024
name: my-model-name
parameters:
model: foo-bar
n_draft: 16
draft_model: model-name
```
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
**Description**
This PR fixes#985
**Notes for Reviewers**
**[Signed
commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)**
- [ ] Yes, I signed my commits.
<!--
Thank you for contributing to LocalAI!
Contributing Conventions:
1. Include descriptive PR titles with [<component-name>] prepended.
2. Build and test your changes before submitting a PR.
3. Sign your commits
By following the community's contribution conventions upfront, the
review process will
be accelerated and your PR merged more quickly.
-->
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
refactor for model gallery endpoints - bundle up resources into a
struct, make galleries mutable with some crud endpoints. This is
groundwork required for making efficient use of the new scraper - while
that PR isn't _quite_ ready yet, the goal is to have more, individually
smaller gallery files. Therefore, rather than requiring a full localai
service restart, these new endpoints have been added to make life
easier.
- Adds endpoints to add, list and remove model galleries at runtime
- Adds these endpoints to the Insomnia config
- Minor fix: loading file urls follows symbolic links now
**Description**
we were otherwise expecting absolute paths. this make it relative to the
model file (as someone would expect)
**Notes for Reviewers**
**[Signed
commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)**
- [ ] Yes, I signed my commits.
<!--
Thank you for contributing to LocalAI!
Contributing Conventions:
1. Include descriptive PR titles with [<component-name>] prepended.
2. Build and test your changes before submitting a PR.
3. Sign your commits
By following the community's contribution conventions upfront, the
review process will
be accelerated and your PR merged more quickly.
-->
**Description**
This PR fixes #
**Notes for Reviewers**
**[Signed
commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)**
- [ ] Yes, I signed my commits.
<!--
Thank you for contributing to LocalAI!
Contributing Conventions:
1. Include descriptive PR titles with [<component-name>] prepended.
2. Build and test your changes before submitting a PR.
3. Sign your commits
By following the community's contribution conventions upfront, the
review process will
be accelerated and your PR merged more quickly.
-->
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
**Description**
This PR syncs up the `llama` backend to use `gguf`
(https://github.com/go-skynet/go-llama.cpp/pull/180). It also adds
`llama-stable` to the targets so we can still load ggml. It adapts the
current tests to use the `llama-backend` for ggml and uses a `gguf`
model to run tests on the new backend.
In order to consume the new version of go-llama.cpp, it also bump go to
1.21 (images, pipelines, etc)
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Aman Karmani <aman@tmm1.net>
Lays some of the groundwork for LLAMA2 compatibility as well as other future models with complex prompting schemes.
Started small refactoring in pkg/model/loader.go regarding template loading. Currently still a part of ModelLoader, but should be easy to add template loading for situations other than overall prompt templates and the new chat-specific per-message templates
Adds support for new chat-endpoint-specific, per-message templates as an alternative to the existing Role: XYZ sprintf method.
Includes a temporary prompt template as an example, since I have a few questions before we merge in the model-gallery side changes (see )
Minor debug logging changes.
Now since gRPCs are not crashing the main thread we can just greedly
attempt all the backends we have available.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
