dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-20 02:24:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 21

feat(p2p): Federation and AI swarms (#2723)

Browse source 
* Wip p2p enhancements

* get online state

* Pass-by token to show in the dashboard

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Style

* Minor fixups

* parametrize SearchID

* Refactoring

* Allow to expose/bind more services

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Add federation

* Display federated mode in the WebUI

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Small fixups

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* make federated nodes visible from the WebUI

* Fix version display

* improve web page

* live page update

* visual enhancements

* enhancements

* visual enhancements

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-07-08 22:04:06 +02:00 • committed by GitHub
parent dd95ae130f
commit cca881ec49
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
23 changed files with 815 additions and 82 deletions
Download patch file Download diff file Expand all files Collapse all files

52
core/cli/run.go
View file

@ -3,6 +3,8 @@ package cli
import (
"context"
"fmt"
"net"
"os"
"strings"
"time"
@ -50,7 +52,7 @@ type RunCMD struct {
DisableWebUI bool `env:"LOCALAI_DISABLE_WEBUI,DISABLE_WEBUI" default:"false" help:"Disable webui" group:"api"`
OpaqueErrors bool `env:"LOCALAI_OPAQUE_ERRORS" default:"false" help:"If true, all error responses are replaced with blank 500 errors. This is intended only for hardening against information leaks and is normally not recommended." group:"api"`
Peer2Peer bool `env:"LOCALAI_P2P,P2P" name:"p2p" default:"false" help:"Enable P2P mode" group:"p2p"`
Peer2PeerToken string `env:"LOCALAI_P2P_TOKEN,P2P_TOKEN" name:"p2ptoken" help:"Token for P2P mode (optional)" group:"p2p"`
Peer2PeerToken string `env:"LOCALAI_P2P_TOKEN,P2P_TOKEN,TOKEN" name:"p2ptoken" help:"Token for P2P mode (optional)" group:"p2p"`
ParallelRequests bool `env:"LOCALAI_PARALLEL_REQUESTS,PARALLEL_REQUESTS" help:"Enable backends to handle multiple requests in parallel if they support it (e.g.: llama.cpp or vllm)" group:"backends"`
SingleActiveBackend bool `env:"LOCALAI_SINGLE_ACTIVE_BACKEND,SINGLE_ACTIVE_BACKEND" help:"Allow only one backend to be run at a time" group:"backends"`
PreloadBackendOnly bool `env:"LOCALAI_PRELOAD_BACKEND_ONLY,PRELOAD_BACKEND_ONLY" default:"false" help:"Do not launch the API services, only the preloaded models / backends are started (useful for multi-node setups)" group:"backends"`
@ -59,6 +61,7 @@ type RunCMD struct {
WatchdogIdleTimeout string `env:"LOCALAI_WATCHDOG_IDLE_TIMEOUT,WATCHDOG_IDLE_TIMEOUT" default:"15m" help:"Threshold beyond which an idle backend should be stopped" group:"backends"`
EnableWatchdogBusy bool `env:"LOCALAI_WATCHDOG_BUSY,WATCHDOG_BUSY" default:"false" help:"Enable watchdog for stopping backends that are busy longer than the watchdog-busy-timeout" group:"backends"`
WatchdogBusyTimeout string `env:"LOCALAI_WATCHDOG_BUSY_TIMEOUT,WATCHDOG_BUSY_TIMEOUT" default:"5m" help:"Threshold beyond which a busy backend should be stopped" group:"backends"`
Federated bool `env:"LOCALAI_FEDERATED,FEDERATED" help:"Enable federated instance" group:"federated"`
}
func (r *RunCMD) Run(ctx *cliContext.Context) error {
@ -91,9 +94,10 @@ func (r *RunCMD) Run(ctx *cliContext.Context) error {
config.WithOpaqueErrors(r.OpaqueErrors),
}
token := ""
if r.Peer2Peer || r.Peer2PeerToken != "" {
log.Info().Msg("P2P mode enabled")
token := r.Peer2PeerToken
token = r.Peer2PeerToken
if token == "" {
// IF no token is provided, and p2p is enabled,
// we generate one and wait for the user to pick up the token (this is for interactive)
@ -104,14 +108,46 @@ func (r *RunCMD) Run(ctx *cliContext.Context) error {
log.Info().Msg("To use the token, you can run the following command in another node or terminal:")
fmt.Printf("export TOKEN=\"%s\"\nlocal-ai worker p2p-llama-cpp-rpc\n", token)
// Ask for user confirmation
log.Info().Msg("Press a button to proceed")
var input string
fmt.Scanln(&input)
}
opts = append(opts, config.WithP2PToken(token))
node, err := p2p.NewNode(token)
if err != nil {
return err
}
log.Info().Msg("Starting P2P server discovery...")
if err := p2p.LLamaCPPRPCServerDiscoverer(context.Background(), token); err != nil {
if err := p2p.ServiceDiscoverer(context.Background(), node, token, "", func() {
var tunnelAddresses []string
for _, v := range p2p.GetAvailableNodes("") {
if v.IsOnline() {
tunnelAddresses = append(tunnelAddresses, v.TunnelAddress)
} else {
log.Info().Msgf("Node %s is offline", v.ID)
}
}
tunnelEnvVar := strings.Join(tunnelAddresses, ",")
os.Setenv("LLAMACPP_GRPC_SERVERS", tunnelEnvVar)
log.Debug().Msgf("setting LLAMACPP_GRPC_SERVERS to %s", tunnelEnvVar)
}); err != nil {
return err
}
}
if r.Federated {
_, port, err := net.SplitHostPort(r.Address)
if err != nil {
return err
}
if err := p2p.ExposeService(context.Background(), "localhost", port, token, p2p.FederatedID); err != nil {
return err
}
node, err := p2p.NewNode(token)
if err != nil {
return err
}
if err := p2p.ServiceDiscoverer(context.Background(), node, token, p2p.FederatedID, nil); err != nil {
return err
}
}