Compare commits
7
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 hermes
|
cf6ba1d32b | ||
|
hermes
|
938ca2b268 | ||
|
hermes
|
6e311050e5 | ||
|
hermes
|
ebc420656a | ||
|
hermes
|
e39fabd31c | ||
|
hermes
|
350d55c434 | ||
|
hermes
|
99e0eebc29 |
No files matched your search
+40
-37
@@ -80,6 +80,9 @@ if ($TotalRamGb -lt 3.5) {
|
||||
}
|
||||
Ok "RAM: $TotalRamGb GB"
|
||||
|
||||
# --- Tumbar deploy previo (antes de detectar puertos) -----------------------
|
||||
cmd /c docker rm -f d0a1-hermes-ollama '>' NUL '2>&1'
|
||||
|
||||
# --- Auto-detect Ollama port ------------------------------------------------
|
||||
$OllamaPort = Find-FreePort 11434
|
||||
|
||||
@@ -96,10 +99,9 @@ Write-Host ''
|
||||
|
||||
# --- 1. Arrancar Ollama (Docker) -------------------------------------------
|
||||
Warn '[1/3] Arrancando Ollama (IA local)...'
|
||||
cmd /c docker rm -f d0a1-hermes-ollama '>' NUL '2>&1'
|
||||
$running = docker ps --format '{{.Names}}' | Select-String -Quiet 'd0a1-hermes-ollama'
|
||||
if (-not $running) {
|
||||
docker run -d --name d0a1-hermes-ollama `
|
||||
docker run -d --name d0a1-hermes-ollama --memory 6g `
|
||||
-p "${OllamaPort}:11434" `
|
||||
-v d0a1_hermes_ollama:/root/.ollama `
|
||||
-e OLLAMA_HOST=0.0.0.0 `
|
||||
@@ -125,45 +127,46 @@ Warn ' Descargando modelo (llama3.2:3b, ~2 GB)...'
|
||||
# Si el usuario define $env:HTTPS_PROXY, Ollama lo usa para el pull (doc oficial):
|
||||
$ProxyEnv = @()
|
||||
if ($env:HTTPS_PROXY) { $ProxyEnv = @('-e', "HTTPS_PROXY=$env:HTTPS_PROXY", '-e', "HTTP_PROXY=$env:HTTP_PROXY") }
|
||||
$PullOk = $false
|
||||
foreach ($Attempt in 1..3) {
|
||||
if ($Attempt -gt 1) { Warn "Reintento $Attempt de 3..." }
|
||||
# --- Modelo: HF primero (CDN propio, rapido) y registry de Ollama como ultimo recurso ---
|
||||
$Gguf = Join-Path $ScriptDir 'llama3.2-3b-q4.gguf'
|
||||
$HfUrls = @(
|
||||
'https://huggingface.co/bartowski/Llama-3.2-3B-Instruct-GGUF/resolve/main/Llama-3.2-3B-Instruct-Q4_K_M.gguf',
|
||||
'https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-GGUF/resolve/main/Llama-3.2-3B-Instruct-Q4_K_M.gguf'
|
||||
)
|
||||
Info 'Descargando modelo de IA (llama3.2:3b, ~2 GB)...'
|
||||
foreach ($Url in $HfUrls) {
|
||||
curl.exe -# -L --retry 3 --max-time 1800 -o "$Gguf" $Url
|
||||
if ($LASTEXITCODE -eq 0 -and (Test-Path $Gguf) -and (Get-Item $Gguf).Length -gt 1900000000) { break }
|
||||
Remove-Item "$Gguf" -Force -ErrorAction SilentlyContinue
|
||||
if ($Url -ne $HfUrls[-1]) { Warn 'Mirror no accesible, probando el siguiente...' }
|
||||
}
|
||||
if ((Test-Path $Gguf) -and (Get-Item $Gguf).Length -gt 1900000000) {
|
||||
Info 'Importando modelo en Ollama...'
|
||||
docker cp "$Gguf" d0a1-hermes-ollama:/root/.ollama/import.gguf
|
||||
docker exec d0a1-hermes-ollama sh -c 'printf "FROM /root/.ollama/import.gguf\\nPARAMETER num_ctx 16384\\n" > /tmp/mf && ollama create llama3.2:3b -f /tmp/mf'
|
||||
$CreateOk = ($LASTEXITCODE -eq 0)
|
||||
docker exec d0a1-hermes-ollama rm -f /root/.ollama/import.gguf | Out-Null
|
||||
Remove-Item "$Gguf" -Force -ErrorAction SilentlyContinue
|
||||
$PullOk = $CreateOk
|
||||
if (-not $CreateOk) { Err 'Fallo al importar el modelo desde el GGUF.' }
|
||||
} else {
|
||||
# Ultimo recurso: pull directo (1 intento, ya sin esperar 3 rondas)
|
||||
Warn 'HuggingFace no accesible. Probando el registry de Ollama (ultimo recurso)...'
|
||||
docker exec @ProxyEnv d0a1-hermes-ollama ollama pull llama3.2:3b
|
||||
if ($LASTEXITCODE -eq 0) { $PullOk = $true; break }
|
||||
Warn 'Descarga interrumpida (red). Reintentando en 5 s...'
|
||||
Start-Sleep -Seconds 5
|
||||
if ($LASTEXITCODE -eq 0) {
|
||||
$PullOk = $true
|
||||
# Contexto ampliado (el default 4096 da 400 en Open WebUI con prompts largos)
|
||||
docker exec d0a1-hermes-ollama sh -c 'printf "FROM llama3.2:3b\\nPARAMETER num_ctx 16384\\n" > /tmp/mf && ollama create llama3.2:3b -f /tmp/mf'
|
||||
}
|
||||
}
|
||||
if (-not $PullOk) {
|
||||
# --- Fallback: mismo modelo via HuggingFace (otro CDN, no el registry de Ollama) ---
|
||||
Warn 'Registry de Ollama no accesible. Probando via HuggingFace (mismo modelo)...'
|
||||
$Gguf = Join-Path $ScriptDir 'llama3.2-3b-q4.gguf'
|
||||
$Urls = @(
|
||||
'https://huggingface.co/bartowski/Llama-3.2-3B-Instruct-GGUF/resolve/main/Llama-3.2-3B-Instruct-Q4_K_M.gguf',
|
||||
'https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-GGUF/resolve/main/Llama-3.2-3B-Instruct-Q4_K_M.gguf'
|
||||
)
|
||||
$DlOk = $false
|
||||
foreach ($Url in $Urls) {
|
||||
curl.exe -sL --retry 3 --max-time 1800 -o "$Gguf" $Url
|
||||
if ($LASTEXITCODE -eq 0 -and (Test-Path $Gguf) -and (Get-Item $Gguf).Length -gt 1900000000) { $DlOk = $true; break }
|
||||
Warn "Mirror no accesible, probando el siguiente..."
|
||||
}
|
||||
if ($DlOk) {
|
||||
docker cp "$Gguf" d0a1-hermes-ollama:/root/.ollama/import.gguf
|
||||
docker exec d0a1-hermes-ollama sh -c 'echo FROM /root/.ollama/import.gguf > /tmp/mf && ollama create llama3.2:3b -f /tmp/mf'
|
||||
$CreateOk = ($LASTEXITCODE -eq 0)
|
||||
docker exec d0a1-hermes-ollama rm -f /root/.ollama/import.gguf | Out-Null
|
||||
Remove-Item "$Gguf" -Force -ErrorAction SilentlyContinue
|
||||
if ($CreateOk) { $PullOk = $true }
|
||||
else { Err 'Fallo al importar el modelo desde el GGUF.' }
|
||||
} else {
|
||||
Err 'No se pudo descargar el modelo (ni registry ni HuggingFace).'
|
||||
if (-not $env:HTTPS_PROXY) {
|
||||
Write-Host ' Tu red bloquea ambos. Si tienes proxy/VPN:'
|
||||
Write-Host ' $env:HTTPS_PROXY = "http://127.0.0.1:7890" # (puerto de tu proxy)'
|
||||
Write-Host ' .\deploy.ps1 vps'
|
||||
}
|
||||
exit 1
|
||||
Err 'No se pudo descargar el modelo (ni HuggingFace ni registry).'
|
||||
if (-not $env:HTTPS_PROXY) {
|
||||
Write-Host ' Tu red bloquea ambos. Si tienes proxy/VPN:'
|
||||
Write-Host ' $env:HTTPS_PROXY = "http://127.0.0.1:7890" # (puerto de tu proxy)'
|
||||
Write-Host ' .\deploy.ps1 vps'
|
||||
}
|
||||
exit 1
|
||||
}
|
||||
Ok "Ollama corriendo en http://localhost:${OllamaPort}"
|
||||
|
||||
|
||||
+40
-37
@@ -80,6 +80,9 @@ if ($TotalRamGb -lt 3.5) {
|
||||
}
|
||||
Ok "RAM: $TotalRamGb GB"
|
||||
|
||||
# --- Tumbar deploy previo (antes de detectar puertos) -----------------------
|
||||
cmd /c docker rm -f d0a1-openclaw-ollama '>' NUL '2>&1'
|
||||
|
||||
# --- Auto-detect Ollama port ------------------------------------------------
|
||||
$OllamaPort = Find-FreePort 11434
|
||||
|
||||
@@ -96,10 +99,9 @@ Write-Host ''
|
||||
|
||||
# --- 1. Arrancar Ollama (Docker) -------------------------------------------
|
||||
Warn '[1/3] Arrancando Ollama (IA local)...'
|
||||
cmd /c docker rm -f d0a1-openclaw-ollama '>' NUL '2>&1'
|
||||
$running = docker ps --format '{{.Names}}' | Select-String -Quiet 'd0a1-openclaw-ollama'
|
||||
if (-not $running) {
|
||||
docker run -d --name d0a1-openclaw-ollama `
|
||||
docker run -d --name d0a1-openclaw-ollama --memory 6g `
|
||||
-p "${OllamaPort}:11434" `
|
||||
-v d0a1_openclaw_ollama:/root/.ollama `
|
||||
-e OLLAMA_HOST=0.0.0.0 `
|
||||
@@ -125,45 +127,46 @@ Warn ' Descargando modelo (llama3.2:3b, ~2 GB)...'
|
||||
# Si el usuario define $env:HTTPS_PROXY, Ollama lo usa para el pull (doc oficial):
|
||||
$ProxyEnv = @()
|
||||
if ($env:HTTPS_PROXY) { $ProxyEnv = @('-e', "HTTPS_PROXY=$env:HTTPS_PROXY", '-e', "HTTP_PROXY=$env:HTTP_PROXY") }
|
||||
$PullOk = $false
|
||||
foreach ($Attempt in 1..3) {
|
||||
if ($Attempt -gt 1) { Warn "Reintento $Attempt de 3..." }
|
||||
# --- Modelo: HF primero (CDN propio, rapido) y registry de Ollama como ultimo recurso ---
|
||||
$Gguf = Join-Path $ScriptDir 'llama3.2-3b-q4.gguf'
|
||||
$HfUrls = @(
|
||||
'https://huggingface.co/bartowski/Llama-3.2-3B-Instruct-GGUF/resolve/main/Llama-3.2-3B-Instruct-Q4_K_M.gguf',
|
||||
'https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-GGUF/resolve/main/Llama-3.2-3B-Instruct-Q4_K_M.gguf'
|
||||
)
|
||||
Info 'Descargando modelo de IA (llama3.2:3b, ~2 GB)...'
|
||||
foreach ($Url in $HfUrls) {
|
||||
curl.exe -# -L --retry 3 --max-time 1800 -o "$Gguf" $Url
|
||||
if ($LASTEXITCODE -eq 0 -and (Test-Path $Gguf) -and (Get-Item $Gguf).Length -gt 1900000000) { break }
|
||||
Remove-Item "$Gguf" -Force -ErrorAction SilentlyContinue
|
||||
if ($Url -ne $HfUrls[-1]) { Warn 'Mirror no accesible, probando el siguiente...' }
|
||||
}
|
||||
if ((Test-Path $Gguf) -and (Get-Item $Gguf).Length -gt 1900000000) {
|
||||
Info 'Importando modelo en Ollama...'
|
||||
docker cp "$Gguf" d0a1-openclaw-ollama:/root/.ollama/import.gguf
|
||||
docker exec d0a1-openclaw-ollama sh -c 'printf "FROM /root/.ollama/import.gguf\\nPARAMETER num_ctx 16384\\n" > /tmp/mf && ollama create llama3.2:3b -f /tmp/mf'
|
||||
$CreateOk = ($LASTEXITCODE -eq 0)
|
||||
docker exec d0a1-openclaw-ollama rm -f /root/.ollama/import.gguf | Out-Null
|
||||
Remove-Item "$Gguf" -Force -ErrorAction SilentlyContinue
|
||||
$PullOk = $CreateOk
|
||||
if (-not $CreateOk) { Err 'Fallo al importar el modelo desde el GGUF.' }
|
||||
} else {
|
||||
# Ultimo recurso: pull directo (1 intento, ya sin esperar 3 rondas)
|
||||
Warn 'HuggingFace no accesible. Probando el registry de Ollama (ultimo recurso)...'
|
||||
docker exec @ProxyEnv d0a1-openclaw-ollama ollama pull llama3.2:3b
|
||||
if ($LASTEXITCODE -eq 0) { $PullOk = $true; break }
|
||||
Warn 'Descarga interrumpida (red). Reintentando en 5 s...'
|
||||
Start-Sleep -Seconds 5
|
||||
if ($LASTEXITCODE -eq 0) {
|
||||
$PullOk = $true
|
||||
# Contexto ampliado (el default 4096 da 400 en Open WebUI con prompts largos)
|
||||
docker exec d0a1-openclaw-ollama sh -c 'printf "FROM llama3.2:3b\\nPARAMETER num_ctx 16384\\n" > /tmp/mf && ollama create llama3.2:3b -f /tmp/mf'
|
||||
}
|
||||
}
|
||||
if (-not $PullOk) {
|
||||
# --- Fallback: mismo modelo via HuggingFace (otro CDN, no el registry de Ollama) ---
|
||||
Warn 'Registry de Ollama no accesible. Probando via HuggingFace (mismo modelo)...'
|
||||
$Gguf = Join-Path $ScriptDir 'llama3.2-3b-q4.gguf'
|
||||
$Urls = @(
|
||||
'https://huggingface.co/bartowski/Llama-3.2-3B-Instruct-GGUF/resolve/main/Llama-3.2-3B-Instruct-Q4_K_M.gguf',
|
||||
'https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-GGUF/resolve/main/Llama-3.2-3B-Instruct-Q4_K_M.gguf'
|
||||
)
|
||||
$DlOk = $false
|
||||
foreach ($Url in $Urls) {
|
||||
curl.exe -sL --retry 3 --max-time 1800 -o "$Gguf" $Url
|
||||
if ($LASTEXITCODE -eq 0 -and (Test-Path $Gguf) -and (Get-Item $Gguf).Length -gt 1900000000) { $DlOk = $true; break }
|
||||
Warn "Mirror no accesible, probando el siguiente..."
|
||||
}
|
||||
if ($DlOk) {
|
||||
docker cp "$Gguf" d0a1-openclaw-ollama:/root/.ollama/import.gguf
|
||||
docker exec d0a1-openclaw-ollama sh -c 'echo FROM /root/.ollama/import.gguf > /tmp/mf && ollama create llama3.2:3b -f /tmp/mf'
|
||||
$CreateOk = ($LASTEXITCODE -eq 0)
|
||||
docker exec d0a1-openclaw-ollama rm -f /root/.ollama/import.gguf | Out-Null
|
||||
Remove-Item "$Gguf" -Force -ErrorAction SilentlyContinue
|
||||
if ($CreateOk) { $PullOk = $true }
|
||||
else { Err 'Fallo al importar el modelo desde el GGUF.' }
|
||||
} else {
|
||||
Err 'No se pudo descargar el modelo (ni registry ni HuggingFace).'
|
||||
if (-not $env:HTTPS_PROXY) {
|
||||
Write-Host ' Tu red bloquea ambos. Si tienes proxy/VPN:'
|
||||
Write-Host ' $env:HTTPS_PROXY = "http://127.0.0.1:7890" # (puerto de tu proxy)'
|
||||
Write-Host ' .\deploy.ps1 vps'
|
||||
}
|
||||
exit 1
|
||||
Err 'No se pudo descargar el modelo (ni HuggingFace ni registry).'
|
||||
if (-not $env:HTTPS_PROXY) {
|
||||
Write-Host ' Tu red bloquea ambos. Si tienes proxy/VPN:'
|
||||
Write-Host ' $env:HTTPS_PROXY = "http://127.0.0.1:7890" # (puerto de tu proxy)'
|
||||
Write-Host ' .\deploy.ps1 vps'
|
||||
}
|
||||
exit 1
|
||||
}
|
||||
Ok "Ollama corriendo en http://localhost:${OllamaPort}"
|
||||
|
||||
|
||||
+42
-39
@@ -86,6 +86,11 @@ if ($TotalRamGb -lt 3.5) {
|
||||
}
|
||||
Ok "RAM: $TotalRamGb GB"
|
||||
|
||||
# --- Tumbar deploy previo (antes de detectar puertos) ----------------------
|
||||
# Mantiene los volumenes (el modelo ya descargado no se re-descarga) y libera
|
||||
# los puertos para que Find-FreePort vea el estado REAL tras el down.
|
||||
cmd /c docker compose -f $ComposeFile down '>' NUL '2>&1'
|
||||
|
||||
# --- Auto-detect ports ----------------------------------------------------
|
||||
$OllamaPort = Find-FreePort 11434
|
||||
$WebUiPort = Find-FreePort 3000
|
||||
@@ -116,9 +121,6 @@ if ($WebUiPort -ne 3000) { Warn "Puerto 3000 ocupado, usando $WebUiPort" }
|
||||
Write-Host ''
|
||||
|
||||
# --- Deploy ----------------------------------------------------------------
|
||||
# Si hay un deploy previo del pack, tumbarlo primero (mantiene los volumenes:
|
||||
# el modelo ya descargado no se re-descarga) para que los nuevos puertos apliquen.
|
||||
cmd /c docker compose -f $ComposeFile down '>' NUL '2>&1'
|
||||
Warn 'Descargando contenedores (2-3 min la primera vez)...'
|
||||
$env:OLLAMA_PORT = "$OllamaPort"
|
||||
$env:WEBUI_PORT = "$WebUiPort"
|
||||
@@ -126,7 +128,7 @@ docker compose -f $ComposeFile up -d
|
||||
if ($LASTEXITCODE -ne 0) { Err "docker compose up fallo (exit $LASTEXITCODE)."; exit 1 }
|
||||
|
||||
# --- Pull model -------------------------------------------------------------
|
||||
Warn 'Descargando modelo de IA (llama3.2:3b, ~2 GB)...'
|
||||
Info 'Esperando a que Ollama arranque...'
|
||||
$MaxWait = 60; $Waited = 0
|
||||
while ($true) {
|
||||
# Descarte de stderr via cmd /c (ver nota de PS 5.1 / PS #4002 arriba)
|
||||
@@ -142,45 +144,46 @@ while ($true) {
|
||||
# Si el usuario define $env:HTTPS_PROXY, Ollama lo usa para el pull (doc oficial):
|
||||
$ProxyEnv = @()
|
||||
if ($env:HTTPS_PROXY) { $ProxyEnv = @('-e', "HTTPS_PROXY=$env:HTTPS_PROXY", '-e', "HTTP_PROXY=$env:HTTP_PROXY") }
|
||||
$PullOk = $false
|
||||
foreach ($Attempt in 1..3) {
|
||||
if ($Attempt -gt 1) { Warn "Reintento $Attempt de 3..." }
|
||||
# --- Modelo: HF primero (CDN propio, rapido) y registry de Ollama como ultimo recurso ---
|
||||
$Gguf = Join-Path $ScriptDir 'llama3.2-3b-q4.gguf'
|
||||
$HfUrls = @(
|
||||
'https://huggingface.co/bartowski/Llama-3.2-3B-Instruct-GGUF/resolve/main/Llama-3.2-3B-Instruct-Q4_K_M.gguf',
|
||||
'https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-GGUF/resolve/main/Llama-3.2-3B-Instruct-Q4_K_M.gguf'
|
||||
)
|
||||
Info 'Descargando modelo de IA (llama3.2:3b, ~2 GB)...'
|
||||
foreach ($Url in $HfUrls) {
|
||||
curl.exe -# -L --retry 3 --max-time 1800 -o "$Gguf" $Url
|
||||
if ($LASTEXITCODE -eq 0 -and (Test-Path $Gguf) -and (Get-Item $Gguf).Length -gt 1900000000) { break }
|
||||
Remove-Item "$Gguf" -Force -ErrorAction SilentlyContinue
|
||||
if ($Url -ne $HfUrls[-1]) { Warn 'Mirror no accesible, probando el siguiente...' }
|
||||
}
|
||||
if ((Test-Path $Gguf) -and (Get-Item $Gguf).Length -gt 1900000000) {
|
||||
Info 'Importando modelo en Ollama...'
|
||||
docker cp "$Gguf" d0a1-ollama:/root/.ollama/import.gguf
|
||||
docker exec d0a1-ollama sh -c 'printf "FROM /root/.ollama/import.gguf\\nPARAMETER num_ctx 16384\\n" > /tmp/mf && ollama create llama3.2:3b -f /tmp/mf'
|
||||
$CreateOk = ($LASTEXITCODE -eq 0)
|
||||
docker exec d0a1-ollama rm -f /root/.ollama/import.gguf | Out-Null
|
||||
Remove-Item "$Gguf" -Force -ErrorAction SilentlyContinue
|
||||
$PullOk = $CreateOk
|
||||
if (-not $CreateOk) { Err 'Fallo al importar el modelo desde el GGUF.' }
|
||||
} else {
|
||||
# Ultimo recurso: pull directo (1 intento, ya sin esperar 3 rondas)
|
||||
Warn 'HuggingFace no accesible. Probando el registry de Ollama (ultimo recurso)...'
|
||||
docker exec @ProxyEnv d0a1-ollama ollama pull llama3.2:3b
|
||||
if ($LASTEXITCODE -eq 0) { $PullOk = $true; break }
|
||||
Warn 'Descarga interrumpida (red). Reintentando en 5 s...'
|
||||
Start-Sleep -Seconds 5
|
||||
if ($LASTEXITCODE -eq 0) {
|
||||
$PullOk = $true
|
||||
# Contexto ampliado (el default 4096 da 400 en Open WebUI con prompts largos)
|
||||
docker exec d0a1-ollama sh -c 'printf "FROM llama3.2:3b\\nPARAMETER num_ctx 16384\\n" > /tmp/mf && ollama create llama3.2:3b -f /tmp/mf'
|
||||
}
|
||||
}
|
||||
if (-not $PullOk) {
|
||||
# --- Fallback: mismo modelo via HuggingFace (otro CDN, no el registry de Ollama) ---
|
||||
Warn 'Registry de Ollama no accesible. Probando via HuggingFace (mismo modelo)...'
|
||||
$Gguf = Join-Path $ScriptDir 'llama3.2-3b-q4.gguf'
|
||||
$Urls = @(
|
||||
'https://huggingface.co/bartowski/Llama-3.2-3B-Instruct-GGUF/resolve/main/Llama-3.2-3B-Instruct-Q4_K_M.gguf',
|
||||
'https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-GGUF/resolve/main/Llama-3.2-3B-Instruct-Q4_K_M.gguf'
|
||||
)
|
||||
$DlOk = $false
|
||||
foreach ($Url in $Urls) {
|
||||
curl.exe -sL --retry 3 --max-time 1800 -o "$Gguf" $Url
|
||||
if ($LASTEXITCODE -eq 0 -and (Test-Path $Gguf) -and (Get-Item $Gguf).Length -gt 1900000000) { $DlOk = $true; break }
|
||||
Warn "Mirror no accesible, probando el siguiente..."
|
||||
}
|
||||
if ($DlOk) {
|
||||
docker cp "$Gguf" d0a1-ollama:/root/.ollama/import.gguf
|
||||
docker exec d0a1-ollama sh -c 'echo FROM /root/.ollama/import.gguf > /tmp/mf && ollama create llama3.2:3b -f /tmp/mf'
|
||||
$CreateOk = ($LASTEXITCODE -eq 0)
|
||||
docker exec d0a1-ollama rm -f /root/.ollama/import.gguf | Out-Null
|
||||
Remove-Item "$Gguf" -Force -ErrorAction SilentlyContinue
|
||||
if ($CreateOk) { $PullOk = $true }
|
||||
else { Err 'Fallo al importar el modelo desde el GGUF.' }
|
||||
} else {
|
||||
Err 'No se pudo descargar el modelo (ni registry ni HuggingFace).'
|
||||
if (-not $env:HTTPS_PROXY) {
|
||||
Write-Host ' Tu red bloquea ambos. Si tienes proxy/VPN:'
|
||||
Write-Host ' $env:HTTPS_PROXY = "http://127.0.0.1:7890" # (puerto de tu proxy)'
|
||||
Write-Host ' .\deploy.ps1 vps'
|
||||
}
|
||||
exit 1
|
||||
Err 'No se pudo descargar el modelo (ni HuggingFace ni registry).'
|
||||
if (-not $env:HTTPS_PROXY) {
|
||||
Write-Host ' Tu red bloquea ambos. Si tienes proxy/VPN:'
|
||||
Write-Host ' $env:HTTPS_PROXY = "http://127.0.0.1:7890" # (puerto de tu proxy)'
|
||||
Write-Host ' .\deploy.ps1 vps'
|
||||
}
|
||||
exit 1
|
||||
}
|
||||
|
||||
# --- Done -------------------------------------------------------------------
|
||||
|
||||
@@ -26,6 +26,10 @@ services:
|
||||
timeout: 5s
|
||||
retries: 10
|
||||
start_period: 30s
|
||||
deploy:
|
||||
resources:
|
||||
limits:
|
||||
memory: 6G
|
||||
|
||||
openwebui:
|
||||
container_name: d0a1-openwebui
|
||||
|
||||
+40
-36
@@ -120,6 +120,9 @@ if (-not (Test-Path $EnvFile)) {
|
||||
}
|
||||
|
||||
# --- Auto-detect ports ----------------------------------------------------
|
||||
# --- Tumbar deploy previo (antes de detectar puertos) ----------------------
|
||||
cmd /c docker compose -f $ComposeFile down '>' NUL '2>&1'
|
||||
|
||||
$OllamaPort = Find-FreePort 11434
|
||||
$WpPort = Find-FreePort 8080
|
||||
$WebUiPort = Find-FreePort 3000
|
||||
@@ -162,7 +165,7 @@ docker compose -f $ComposeFile up -d
|
||||
if ($LASTEXITCODE -ne 0) { Err "docker compose up fallo (exit $LASTEXITCODE)."; exit 1 }
|
||||
|
||||
# --- Pull model -------------------------------------------------------------
|
||||
Warn 'Descargando modelo de IA (llama3.2:3b, ~2 GB)...'
|
||||
Info 'Esperando a que Ollama arranque...'
|
||||
$MaxWait = 60; $Waited = 0
|
||||
while ($true) {
|
||||
# Descarte de stderr via cmd /c (ver nota de PS 5.1 / PS #4002 arriba)
|
||||
@@ -178,45 +181,46 @@ while ($true) {
|
||||
# Si el usuario define $env:HTTPS_PROXY, Ollama lo usa para el pull (doc oficial):
|
||||
$ProxyEnv = @()
|
||||
if ($env:HTTPS_PROXY) { $ProxyEnv = @('-e', "HTTPS_PROXY=$env:HTTPS_PROXY", '-e', "HTTP_PROXY=$env:HTTP_PROXY") }
|
||||
$PullOk = $false
|
||||
foreach ($Attempt in 1..3) {
|
||||
if ($Attempt -gt 1) { Warn "Reintento $Attempt de 3..." }
|
||||
# --- Modelo: HF primero (CDN propio, rapido) y registry de Ollama como ultimo recurso ---
|
||||
$Gguf = Join-Path $ScriptDir 'llama3.2-3b-q4.gguf'
|
||||
$HfUrls = @(
|
||||
'https://huggingface.co/bartowski/Llama-3.2-3B-Instruct-GGUF/resolve/main/Llama-3.2-3B-Instruct-Q4_K_M.gguf',
|
||||
'https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-GGUF/resolve/main/Llama-3.2-3B-Instruct-Q4_K_M.gguf'
|
||||
)
|
||||
Info 'Descargando modelo de IA (llama3.2:3b, ~2 GB)...'
|
||||
foreach ($Url in $HfUrls) {
|
||||
curl.exe -# -L --retry 3 --max-time 1800 -o "$Gguf" $Url
|
||||
if ($LASTEXITCODE -eq 0 -and (Test-Path $Gguf) -and (Get-Item $Gguf).Length -gt 1900000000) { break }
|
||||
Remove-Item "$Gguf" -Force -ErrorAction SilentlyContinue
|
||||
if ($Url -ne $HfUrls[-1]) { Warn 'Mirror no accesible, probando el siguiente...' }
|
||||
}
|
||||
if ((Test-Path $Gguf) -and (Get-Item $Gguf).Length -gt 1900000000) {
|
||||
Info 'Importando modelo en Ollama...'
|
||||
docker cp "$Gguf" d0a1-wp-ollama:/root/.ollama/import.gguf
|
||||
docker exec d0a1-wp-ollama sh -c 'printf "FROM /root/.ollama/import.gguf\\nPARAMETER num_ctx 16384\\n" > /tmp/mf && ollama create llama3.2:3b -f /tmp/mf'
|
||||
$CreateOk = ($LASTEXITCODE -eq 0)
|
||||
docker exec d0a1-wp-ollama rm -f /root/.ollama/import.gguf | Out-Null
|
||||
Remove-Item "$Gguf" -Force -ErrorAction SilentlyContinue
|
||||
$PullOk = $CreateOk
|
||||
if (-not $CreateOk) { Err 'Fallo al importar el modelo desde el GGUF.' }
|
||||
} else {
|
||||
# Ultimo recurso: pull directo (1 intento, ya sin esperar 3 rondas)
|
||||
Warn 'HuggingFace no accesible. Probando el registry de Ollama (ultimo recurso)...'
|
||||
docker exec @ProxyEnv d0a1-wp-ollama ollama pull llama3.2:3b
|
||||
if ($LASTEXITCODE -eq 0) { $PullOk = $true; break }
|
||||
Warn 'Descarga interrumpida (red). Reintentando en 5 s...'
|
||||
Start-Sleep -Seconds 5
|
||||
if ($LASTEXITCODE -eq 0) {
|
||||
$PullOk = $true
|
||||
# Contexto ampliado (el default 4096 da 400 en Open WebUI con prompts largos)
|
||||
docker exec d0a1-wp-ollama sh -c 'printf "FROM llama3.2:3b\\nPARAMETER num_ctx 16384\\n" > /tmp/mf && ollama create llama3.2:3b -f /tmp/mf'
|
||||
}
|
||||
}
|
||||
if (-not $PullOk) {
|
||||
# --- Fallback: mismo modelo via HuggingFace (otro CDN, no el registry de Ollama) ---
|
||||
Warn 'Registry de Ollama no accesible. Probando via HuggingFace (mismo modelo)...'
|
||||
$Gguf = Join-Path $ScriptDir 'llama3.2-3b-q4.gguf'
|
||||
$Urls = @(
|
||||
'https://huggingface.co/bartowski/Llama-3.2-3B-Instruct-GGUF/resolve/main/Llama-3.2-3B-Instruct-Q4_K_M.gguf',
|
||||
'https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-GGUF/resolve/main/Llama-3.2-3B-Instruct-Q4_K_M.gguf'
|
||||
)
|
||||
$DlOk = $false
|
||||
foreach ($Url in $Urls) {
|
||||
curl.exe -sL --retry 3 --max-time 1800 -o "$Gguf" $Url
|
||||
if ($LASTEXITCODE -eq 0 -and (Test-Path $Gguf) -and (Get-Item $Gguf).Length -gt 1900000000) { $DlOk = $true; break }
|
||||
Warn "Mirror no accesible, probando el siguiente..."
|
||||
}
|
||||
if ($DlOk) {
|
||||
docker cp "$Gguf" d0a1-wp-ollama:/root/.ollama/import.gguf
|
||||
docker exec d0a1-wp-ollama sh -c 'echo FROM /root/.ollama/import.gguf > /tmp/mf && ollama create llama3.2:3b -f /tmp/mf'
|
||||
$CreateOk = ($LASTEXITCODE -eq 0)
|
||||
docker exec d0a1-wp-ollama rm -f /root/.ollama/import.gguf | Out-Null
|
||||
Remove-Item "$Gguf" -Force -ErrorAction SilentlyContinue
|
||||
if ($CreateOk) { $PullOk = $true }
|
||||
else { Err 'Fallo al importar el modelo desde el GGUF.' }
|
||||
} else {
|
||||
Err 'No se pudo descargar el modelo (ni registry ni HuggingFace).'
|
||||
if (-not $env:HTTPS_PROXY) {
|
||||
Write-Host ' Tu red bloquea ambos. Si tienes proxy/VPN:'
|
||||
Write-Host ' $env:HTTPS_PROXY = "http://127.0.0.1:7890" # (puerto de tu proxy)'
|
||||
Write-Host ' .\deploy.ps1 vps'
|
||||
}
|
||||
exit 1
|
||||
Err 'No se pudo descargar el modelo (ni HuggingFace ni registry).'
|
||||
if (-not $env:HTTPS_PROXY) {
|
||||
Write-Host ' Tu red bloquea ambos. Si tienes proxy/VPN:'
|
||||
Write-Host ' $env:HTTPS_PROXY = "http://127.0.0.1:7890" # (puerto de tu proxy)'
|
||||
Write-Host ' .\deploy.ps1 vps'
|
||||
}
|
||||
exit 1
|
||||
}
|
||||
|
||||
# --- Done -------------------------------------------------------------------
|
||||
|
||||
@@ -59,6 +59,10 @@ services:
|
||||
timeout: 5s
|
||||
retries: 10
|
||||
start_period: 30s
|
||||
deploy:
|
||||
resources:
|
||||
limits:
|
||||
memory: 6G
|
||||
|
||||
openwebui:
|
||||
container_name: d0a1-wp-openwebui
|
||||
|
||||
Reference in new issue
Block a user