LocalAI/core/p2p/p2p.go

439 lines
11 KiB
Go
Raw Normal View History

feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
//go:build p2p
// +build p2p
package p2p
import (
"context"
"errors"
"fmt"
"io"
"net"
"os"
"sync"
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
"time"
"github.com/ipfs/go-log"
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
"github.com/libp2p/go-libp2p/core/peer"
"github.com/mudler/LocalAI/pkg/utils"
"github.com/mudler/edgevpn/pkg/config"
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
"github.com/mudler/edgevpn/pkg/node"
"github.com/mudler/edgevpn/pkg/protocol"
"github.com/mudler/edgevpn/pkg/services"
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
"github.com/mudler/edgevpn/pkg/types"
eutils "github.com/mudler/edgevpn/pkg/utils"
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
"github.com/phayes/freeport"
zlog "github.com/rs/zerolog/log"
"github.com/mudler/edgevpn/pkg/logger"
)
func generateNewConnectionData(DHTInterval, OTPInterval int) *node.YAMLConnectionConfig {
maxMessSize := 20 << 20 // 20MB
keyLength := 43
if DHTInterval == 0 {
DHTInterval = 360
}
if OTPInterval == 0 {
OTPInterval = 9000
}
return &node.YAMLConnectionConfig{
MaxMessageSize: maxMessSize,
RoomName: eutils.RandStringRunes(keyLength),
Rendezvous: eutils.RandStringRunes(keyLength),
MDNS: eutils.RandStringRunes(keyLength),
OTP: node.OTP{
DHT: node.OTPConfig{
Key: eutils.RandStringRunes(keyLength),
Interval: DHTInterval,
Length: keyLength,
},
Crypto: node.OTPConfig{
Key: eutils.RandStringRunes(keyLength),
Interval: OTPInterval,
Length: keyLength,
},
},
}
}
func GenerateToken(DHTInterval, OTPInterval int) string {
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
// Generates a new config and exit
return generateNewConnectionData(DHTInterval, OTPInterval).Base64()
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
}
func IsP2PEnabled() bool {
return true
}
func nodeID(s string) string {
hostname, _ := os.Hostname()
return fmt.Sprintf("%s-%s", hostname, s)
}
func nodeAnnounce(ctx context.Context, node *node.Node) {
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
ledger, _ := node.Ledger()
// Announce ourselves so nodes accepts our connection
ledger.Announce(
ctx,
10*time.Second,
func() {
updatedMap := map[string]interface{}{}
updatedMap[node.Host().ID().String()] = &types.User{
PeerID: node.Host().ID().String(),
Timestamp: time.Now().String(),
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
}
ledger.Add(protocol.UsersLedgerKey, updatedMap)
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
},
)
}
func proxyP2PConnection(ctx context.Context, node *node.Node, serviceID string, conn net.Conn) {
ledger, _ := node.Ledger()
// Retrieve current ID for ip in the blockchain
existingValue, found := ledger.GetKey(protocol.ServicesLedgerKey, serviceID)
service := &types.Service{}
existingValue.Unmarshal(service)
// If mismatch, update the blockchain
if !found {
zlog.Error().Msg("Service not found on blockchain")
conn.Close()
// ll.Debugf("service '%s' not found on blockchain", serviceID)
return
}
// Decode the Peer
d, err := peer.Decode(service.PeerID)
if err != nil {
zlog.Error().Msg("cannot decode peer")
conn.Close()
// ll.Debugf("could not decode peer '%s'", service.PeerID)
return
}
// Open a stream
stream, err := node.Host().NewStream(ctx, d, protocol.ServiceProtocol.ID())
if err != nil {
zlog.Error().Err(err).Msg("cannot open stream peer")
conn.Close()
// ll.Debugf("could not open stream '%s'", err.Error())
return
}
// ll.Debugf("(service %s) Redirecting", serviceID, l.Addr().String())
zlog.Info().Msgf("Redirecting %s to %s", conn.LocalAddr().String(), stream.Conn().RemoteMultiaddr().String())
closer := make(chan struct{}, 2)
go copyStream(closer, stream, conn)
go copyStream(closer, conn, stream)
<-closer
stream.Close()
conn.Close()
}
func allocateLocalService(ctx context.Context, node *node.Node, listenAddr, service string) error {
zlog.Info().Msgf("Allocating service '%s' on: %s", service, listenAddr)
// Open local port for listening
l, err := net.Listen("tcp", listenAddr)
if err != nil {
zlog.Error().Err(err).Msg("Error listening")
return err
}
go func() {
<-ctx.Done()
l.Close()
}()
nodeAnnounce(ctx, node)
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
defer l.Close()
for {
select {
case <-ctx.Done():
return errors.New("context canceled")
default:
zlog.Debug().Msg("New for connection")
// Listen for an incoming connection.
conn, err := l.Accept()
if err != nil {
fmt.Println("Error accepting: ", err.Error())
continue
}
// Handle connections in a new goroutine, forwarding to the p2p service
go func() {
proxyP2PConnection(ctx, node, service, conn)
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
}()
}
}
}
// This is the main of the server (which keeps the env variable updated)
// This starts a goroutine that keeps LLAMACPP_GRPC_SERVERS updated with the discovered services
func ServiceDiscoverer(ctx context.Context, n *node.Node, token, servicesID string, discoveryFunc func(serviceID string, node NodeData), allocate bool) error {
if servicesID == "" {
servicesID = defaultServicesID
}
tunnels, err := discoveryTunnels(ctx, n, token, servicesID, allocate)
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
if err != nil {
return err
}
// TODO: discoveryTunnels should return all the nodes that are available?
// In this way we updated availableNodes here instead of appending
// e.g. we have a LastSeen field in NodeData that is updated in discoveryTunnels
// each time the node is seen
// In this case the below function should be idempotent and just keep track of the nodes
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
go func() {
for {
select {
case <-ctx.Done():
zlog.Error().Msg("Discoverer stopped")
return
case tunnel := <-tunnels:
AddNode(servicesID, tunnel)
if discoveryFunc != nil {
discoveryFunc(servicesID, tunnel)
}
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
}
}
}()
return nil
}
func discoveryTunnels(ctx context.Context, n *node.Node, token, servicesID string, allocate bool) (chan NodeData, error) {
tunnels := make(chan NodeData)
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
ledger, err := n.Ledger()
if err != nil {
return nil, fmt.Errorf("getting the ledger: %w", err)
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
}
// get new services, allocate and return to the channel
// TODO:
// a function ensureServices that:
// - starts a service if not started, if the worker is Online
// - checks that workers are Online, if not cancel the context of allocateLocalService
// - discoveryTunnels should return all the nodes and addresses associated with it
// - the caller should take now care of the fact that we are always returning fresh informations
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
go func() {
for {
select {
case <-ctx.Done():
zlog.Error().Msg("Discoverer stopped")
return
default:
time.Sleep(5 * time.Second)
data := ledger.LastBlock().Storage[servicesID]
if logLevel == logLevelDebug {
// We want to surface this debugging data only if p2p logging is set to debug
// (and not generally the whole application, as this can be really noisy)
zlog.Debug().Any("data", ledger.LastBlock().Storage).Msg("Ledger data")
}
for k, v := range data {
// New worker found in the ledger data as k (worker id)
nd := &NodeData{}
if err := v.Unmarshal(nd); err != nil {
zlog.Error().Msg("cannot unmarshal node data")
continue
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
}
ensureService(ctx, n, nd, k, allocate)
muservice.Lock()
if _, ok := service[nd.Name]; ok {
tunnels <- service[nd.Name].NodeData
}
muservice.Unlock()
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
}
}
}
}()
return tunnels, err
}
type nodeServiceData struct {
NodeData NodeData
CancelFunc context.CancelFunc
}
var service = map[string]nodeServiceData{}
var muservice sync.Mutex
func ensureService(ctx context.Context, n *node.Node, nd *NodeData, sserv string, allocate bool) {
muservice.Lock()
defer muservice.Unlock()
nd.ServiceID = sserv
if ndService, found := service[nd.Name]; !found {
if !nd.IsOnline() {
// if node is offline and not present, do nothing
// Node nd.ID is offline
return
}
newCtxm, cancel := context.WithCancel(ctx)
if allocate {
// Start the service
port, err := freeport.GetFreePort()
if err != nil {
zlog.Error().Err(err).Msgf("Could not allocate a free port for %s", nd.ID)
return
}
tunnelAddress := fmt.Sprintf("127.0.0.1:%d", port)
nd.TunnelAddress = tunnelAddress
go allocateLocalService(newCtxm, n, tunnelAddress, sserv)
zlog.Debug().Msgf("Starting service %s on %s", sserv, tunnelAddress)
}
service[nd.Name] = nodeServiceData{
NodeData: *nd,
CancelFunc: cancel,
}
} else {
// Check if the service is still alive
// if not cancel the context
if !nd.IsOnline() && !ndService.NodeData.IsOnline() {
ndService.CancelFunc()
delete(service, nd.Name)
zlog.Info().Msgf("Node %s is offline, deleting", nd.ID)
} else if nd.IsOnline() {
// update last seen inside service
nd.TunnelAddress = ndService.NodeData.TunnelAddress
service[nd.Name] = nodeServiceData{
NodeData: *nd,
CancelFunc: ndService.CancelFunc,
}
zlog.Debug().Msgf("Node %s is still online", nd.ID)
}
}
}
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
// This is the P2P worker main
func ExposeService(ctx context.Context, host, port, token, servicesID string) (*node.Node, error) {
if servicesID == "" {
servicesID = defaultServicesID
}
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
llger := logger.New(log.LevelFatal)
nodeOpts, err := newNodeOpts(token)
if err != nil {
return nil, err
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
}
// generate a random string for the name
name := utils.RandString(10)
// Register the service
nodeOpts = append(nodeOpts,
services.RegisterService(llger, time.Duration(60)*time.Second, name, fmt.Sprintf("%s:%s", host, port))...)
n, err := node.New(nodeOpts...)
if err != nil {
return nil, fmt.Errorf("creating a new node: %w", err)
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
}
err = n.Start(ctx)
if err != nil {
return n, fmt.Errorf("creating a new node: %w", err)
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
}
ledger, err := n.Ledger()
if err != nil {
return n, fmt.Errorf("creating a new node: %w", err)
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
}
ledger.Announce(
ctx,
20*time.Second,
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
func() {
updatedMap := map[string]interface{}{}
updatedMap[name] = &NodeData{
Name: name,
LastSeen: time.Now(),
ID: nodeID(name),
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
}
ledger.Add(servicesID, updatedMap)
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
},
)
return n, err
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
}
func NewNode(token string) (*node.Node, error) {
nodeOpts, err := newNodeOpts(token)
if err != nil {
return nil, err
}
n, err := node.New(nodeOpts...)
if err != nil {
return nil, fmt.Errorf("creating a new node: %w", err)
}
return n, nil
}
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
func newNodeOpts(token string) ([]node.Option, error) {
llger := logger.New(log.LevelFatal)
defaultInterval := 10 * time.Second
// TODO: move this up, expose more config options when creating a node
noDHT := os.Getenv("LOCALAI_P2P_DISABLE_DHT") == "true"
feat(p2p): add network explorer and community pools (#3125) * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Wire up a simple explorer DB Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * wip Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor: group services id so can be identified easily in the ledger table Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(discovery): discovery service now gather worker informations correctly Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(explorer): display network token Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(explorer): display form to add new networks Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(explorer): stop from overwriting networks Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(explorer): display only networks with active workers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(explorer): list only clusters in a network if it has online workers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * remove invalid and inactive networks if networks have no workers delete them from the database, similarly, if invalid. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * ci: add workflow to deploy new explorer versions automatically Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * build-api: build with p2p tag Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Allow to specify a connection timeout Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * logging Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Better p2p defaults Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Set loglevel Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix dht enable Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Default to info for loglevel Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add navbar Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Slightly improve rendering Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Allow to copy the token easily Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * ci fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-09 18:12:01 +00:00
noLimits := os.Getenv("LOCALAI_P2P_ENABLE_LIMITS") == "true"
libp2ploglevel := os.Getenv("LOCALAI_LIBP2P_LOGLEVEL")
if libp2ploglevel == "" {
libp2ploglevel = "fatal"
}
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
c := config.Config{
Limit: config.ResourceLimit{
feat(p2p): add network explorer and community pools (#3125) * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Wire up a simple explorer DB Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * wip Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor: group services id so can be identified easily in the ledger table Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(discovery): discovery service now gather worker informations correctly Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(explorer): display network token Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(explorer): display form to add new networks Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(explorer): stop from overwriting networks Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(explorer): display only networks with active workers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(explorer): list only clusters in a network if it has online workers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * remove invalid and inactive networks if networks have no workers delete them from the database, similarly, if invalid. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * ci: add workflow to deploy new explorer versions automatically Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * build-api: build with p2p tag Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Allow to specify a connection timeout Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * logging Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Better p2p defaults Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Set loglevel Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix dht enable Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Default to info for loglevel Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add navbar Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Slightly improve rendering Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Allow to copy the token easily Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * ci fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-09 18:12:01 +00:00
Enable: noLimits,
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
MaxConns: 100,
},
NetworkToken: token,
LowProfile: false,
LogLevel: logLevel,
Libp2pLogLevel: libp2ploglevel,
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
Ledger: config.Ledger{
SyncInterval: defaultInterval,
AnnounceInterval: defaultInterval,
},
NAT: config.NAT{
Service: true,
Map: true,
RateLimit: true,
feat(p2p): add network explorer and community pools (#3125) * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Wire up a simple explorer DB Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * wip Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor: group services id so can be identified easily in the ledger table Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(discovery): discovery service now gather worker informations correctly Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(explorer): display network token Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(explorer): display form to add new networks Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(explorer): stop from overwriting networks Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(explorer): display only networks with active workers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(explorer): list only clusters in a network if it has online workers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * remove invalid and inactive networks if networks have no workers delete them from the database, similarly, if invalid. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * ci: add workflow to deploy new explorer versions automatically Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * build-api: build with p2p tag Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Allow to specify a connection timeout Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * logging Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Better p2p defaults Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Set loglevel Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix dht enable Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Default to info for loglevel Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add navbar Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Slightly improve rendering Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Allow to copy the token easily Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * ci fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-09 18:12:01 +00:00
RateLimitGlobal: 100,
RateLimitPeer: 100,
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
RateLimitInterval: defaultInterval,
},
Discovery: config.Discovery{
feat(p2p): add network explorer and community pools (#3125) * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Wire up a simple explorer DB Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * wip Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor: group services id so can be identified easily in the ledger table Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(discovery): discovery service now gather worker informations correctly Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(explorer): display network token Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(explorer): display form to add new networks Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(explorer): stop from overwriting networks Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(explorer): display only networks with active workers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(explorer): list only clusters in a network if it has online workers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * remove invalid and inactive networks if networks have no workers delete them from the database, similarly, if invalid. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * ci: add workflow to deploy new explorer versions automatically Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * build-api: build with p2p tag Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Allow to specify a connection timeout Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * logging Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Better p2p defaults Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Set loglevel Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix dht enable Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Default to info for loglevel Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add navbar Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Slightly improve rendering Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Allow to copy the token easily Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * ci fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-09 18:12:01 +00:00
DHT: !noDHT,
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
MDNS: true,
feat(p2p): add network explorer and community pools (#3125) * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Wire up a simple explorer DB Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * wip Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor: group services id so can be identified easily in the ledger table Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(discovery): discovery service now gather worker informations correctly Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(explorer): display network token Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(explorer): display form to add new networks Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(explorer): stop from overwriting networks Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(explorer): display only networks with active workers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(explorer): list only clusters in a network if it has online workers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * remove invalid and inactive networks if networks have no workers delete them from the database, similarly, if invalid. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * ci: add workflow to deploy new explorer versions automatically Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * build-api: build with p2p tag Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Allow to specify a connection timeout Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * logging Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Better p2p defaults Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Set loglevel Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix dht enable Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Default to info for loglevel Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add navbar Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Slightly improve rendering Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Allow to copy the token easily Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * ci fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-09 18:12:01 +00:00
Interval: 10 * time.Second,
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
},
Connection: config.Connection{
HolePunch: true,
AutoRelay: true,
feat(p2p): add network explorer and community pools (#3125) * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Wire up a simple explorer DB Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * wip Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor: group services id so can be identified easily in the ledger table Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(discovery): discovery service now gather worker informations correctly Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(explorer): display network token Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(explorer): display form to add new networks Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(explorer): stop from overwriting networks Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(explorer): display only networks with active workers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(explorer): list only clusters in a network if it has online workers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * remove invalid and inactive networks if networks have no workers delete them from the database, similarly, if invalid. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * ci: add workflow to deploy new explorer versions automatically Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * build-api: build with p2p tag Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Allow to specify a connection timeout Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * logging Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Better p2p defaults Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Set loglevel Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix dht enable Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Default to info for loglevel Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add navbar Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Slightly improve rendering Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Allow to copy the token easily Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * ci fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-09 18:12:01 +00:00
MaxConnections: 1000,
feat(llama.cpp): Totally decentralized, private, distributed, p2p inference (#2343) * 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>
2024-05-20 17:17:59 +00:00
},
}
nodeOpts, _, err := c.ToOpts(llger)
if err != nil {
return nil, fmt.Errorf("parsing options: %w", err)
}
nodeOpts = append(nodeOpts, services.Alive(30*time.Second, 900*time.Second, 15*time.Minute)...)
return nodeOpts, nil
}
func copyStream(closer chan struct{}, dst io.Writer, src io.Reader) {
defer func() { closer <- struct{}{} }() // connection is closed, send signal to stop proxy
io.Copy(dst, src)
}