这是indexloc提供的服务，不要输入任何密码
Skip to content

2749 ollama client auth token #3005

New issue

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

Sign up for GitHub

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

Already on GitHub? Sign in to your account

Merged
merged 15 commits into from
Feb 19, 2025
Merged

2749 ollama client auth token #3005

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
15 commits
Select commit Hold shift + click to select a range
b7ebcbf
ollama auth token provision
ssbodapati Jan 23, 2025
815e74b
auth token provision
ssbodapati Jan 23, 2025
7875a9b
ollama auth provision
ssbodapati Jan 23, 2025
8e6e14f
ollama auth token
ssbodapati Jan 23, 2025
e3a40e1
ollama auth provision
ssbodapati Jan 23, 2025
db5cf98
token input field css fix
ssbodapati Jan 23, 2025
51ed3eb
Fix provider handler not using key
timothycarambat Jan 24, 2025
d7e1434
apply header and auth to agent invocations
timothycarambat Jan 24, 2025
98c5a4c
Merge branch 'master' into 2749-ollama-client-auth-token
timothycarambat Jan 24, 2025
159fb3f
upgrading to ollama 5.10 for passing headers to constructor
ssbodapati Jan 25, 2025
b87c7d8
sync with master HEAD
timothycarambat Feb 18, 2025
e514dd9
rename Auth systemSetting key to be more descriptive
timothycarambat Feb 18, 2025
f65e7be
remove untracked files + update gitignore
timothycarambat Feb 18, 2025
5a5d415
remove debug
timothycarambat Feb 18, 2025
baaec4f
patch lockfile
timothycarambat Feb 18, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions docker/.env.example
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,6 +42,7 @@ GID='1000'
# OLLAMA_BASE_PATH='http://host.docker.internal:11434'
# OLLAMA_MODEL_PREF='llama2'
# OLLAMA_MODEL_TOKEN_LIMIT=4096
# OLLAMA_AUTH_TOKEN='your-ollama-auth-token-here (optional, only for ollama running behind auth - Bearer token)'

# LLM_PROVIDER='togetherai'
# TOGETHER_AI_API_KEY='my-together-ai-key'
Expand Down
260 changes: 149 additions & 111 deletions frontend/src/components/LLMSelection/OllamaLLMOptions/index.jsx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,12 +11,15 @@ export default function OllamaLLMOptions({ settings }) {
autoDetecting: loading,
basePath,
basePathValue,
authToken,
authTokenValue,
showAdvancedControls,
setShowAdvancedControls,
handleAutoDetectClick,
} = useProviderEndpointAutoDiscovery({
provider: "ollama",
initialBasePath: settings?.OllamaLLMBasePath,
initialAuthToken: settings?.OllamaLLMAuthToken,
ENDPOINTS: OLLAMA_COMMON_URLS,
});
const [performanceMode, setPerformanceMode] = useState(
Expand All @@ -32,6 +35,7 @@ export default function OllamaLLMOptions({ settings }) {
<OllamaLLMModelSelection
settings={settings}
basePath={basePath.value}
authToken={authToken.value}
/>
<div className="flex flex-col w-60">
<label className="text-white text-sm font-semibold block mb-2">
Expand Down Expand Up @@ -73,128 +77,158 @@ export default function OllamaLLMOptions({ settings }) {
</div>

<div hidden={!showAdvancedControls}>
<div className="w-full flex items-start gap-4">
<div className="flex flex-col w-60">
<div className="flex justify-between items-center mb-2">
<label className="text-white text-sm font-semibold">
Ollama Base URL
</label>
{loading ? (
<PreLoader size="6" />
) : (
<>
{!basePathValue.value && (
<button
onClick={handleAutoDetectClick}
className="bg-primary-button text-xs font-medium px-2 py-1 rounded-lg hover:bg-secondary hover:text-white shadow-[0_4px_14px_rgba(0,0,0,0.25)]"
>
Auto-Detect
</button>
)}
</>
)}
<div className="flex flex-col">
<div className="w-full flex items-start gap-4">
<div className="flex flex-col w-60">
<div className="flex justify-between items-center mb-2">
<label className="text-white text-sm font-semibold">
Ollama Base URL
</label>
{loading ? (
<PreLoader size="6" />
) : (
<>
{!basePathValue.value && (
<button
onClick={handleAutoDetectClick}
className="bg-primary-button text-xs font-medium px-2 py-1 rounded-lg hover:bg-secondary hover:text-white shadow-[0_4px_14px_rgba(0,0,0,0.25)]"
>
Auto-Detect
</button>
)}
</>
)}
</div>
<input
type="url"
name="OllamaLLMBasePath"
className="border-none bg-theme-settings-input-bg text-white placeholder:text-theme-settings-input-placeholder text-sm rounded-lg focus:outline-primary-button active:outline-primary-button outline-none block w-full p-2.5"
placeholder="http://127.0.0.1:11434"
value={basePathValue.value}
required={true}
autoComplete="off"
spellCheck={false}
onChange={basePath.onChange}
onBlur={basePath.onBlur}
/>
<p className="text-xs leading-[18px] font-base text-white text-opacity-60 mt-2">
Enter the URL where Ollama is running.
</p>
</div>
<input
type="url"
name="OllamaLLMBasePath"
className="border-none bg-theme-settings-input-bg text-white placeholder:text-theme-settings-input-placeholder text-sm rounded-lg focus:outline-primary-button active:outline-primary-button outline-none block w-full p-2.5"
placeholder="http://127.0.0.1:11434"
value={basePathValue.value}
required={true}
autoComplete="off"
spellCheck={false}
onChange={basePath.onChange}
onBlur={basePath.onBlur}
/>
<p className="text-xs leading-[18px] font-base text-white text-opacity-60 mt-2">
Enter the URL where Ollama is running.
</p>
</div>

<div className="flex flex-col w-60">
<label className="text-white text-sm font-semibold block mb-2">
Ollama Keep Alive
</label>
<select
name="OllamaLLMKeepAliveSeconds"
required={true}
className="border-none bg-theme-settings-input-bg border-gray-500 text-white text-sm rounded-lg block w-full p-2.5"
defaultValue={settings?.OllamaLLMKeepAliveSeconds ?? "300"}
>
<option value="0">No cache</option>
<option value="300">5 minutes</option>
<option value="3600">1 hour</option>
<option value="-1">Forever</option>
</select>
<p className="text-xs leading-[18px] font-base text-white text-opacity-60 mt-2">
Choose how long Ollama should keep your model in memory before
unloading.
<a
className="underline text-blue-300"
href="https://github.com/ollama/ollama/blob/main/docs/faq.md#how-do-i-keep-a-model-loaded-in-memory-or-make-it-unload-immediately"
target="_blank"
rel="noreferrer"
<div className="flex flex-col w-60">
<label className="text-white text-sm font-semibold mb-2 flex items-center">
Performance Mode
<Info
size={16}
className="ml-2 text-white"
data-tooltip-id="performance-mode-tooltip"
/>
</label>
<select
name="OllamaLLMPerformanceMode"
required={true}
className="border-none bg-theme-settings-input-bg border-gray-500 text-white text-sm rounded-lg block w-full p-2.5"
value={performanceMode}
onChange={(e) => setPerformanceMode(e.target.value)}
>
{" "}
Learn more &rarr;
</a>
</p>
</div>

<div className="flex flex-col w-60">
<label className="text-white text-sm font-semibold mb-2 flex items-center">
Performance Mode
<Info
size={16}
className="ml-2 text-white"
data-tooltip-id="performance-mode-tooltip"
/>
</label>
<select
name="OllamaLLMPerformanceMode"
required={true}
className="border-none bg-theme-settings-input-bg border-gray-500 text-white text-sm rounded-lg block w-full p-2.5"
value={performanceMode}
onChange={(e) => setPerformanceMode(e.target.value)}
>
<option value="base">Base (Default)</option>
<option value="maximum">Maximum</option>
</select>
<p className="text-xs leading-[18px] font-base text-white text-opacity-60 mt-2">
Choose the performance mode for the Ollama model.
</p>
<Tooltip
id="performance-mode-tooltip"
place="bottom"
className="tooltip !text-xs max-w-xs"
>
<p className="text-red-500">
<strong>Note:</strong> Be careful with the Maximum mode. It may
increase resource usage significantly.
<option value="base">Base (Default)</option>
<option value="maximum">Maximum</option>
</select>
<p className="text-xs leading-[18px] font-base text-white text-opacity-60 mt-2">
Choose the performance mode for the Ollama model.
</p>
<br />
<p>
<strong>Base:</strong> Ollama automatically limits the context
to 2048 tokens, keeping resources usage low while maintaining
good performance. Suitable for most users and models.
<Tooltip
id="performance-mode-tooltip"
place="bottom"
className="tooltip !text-xs max-w-xs"
>
<p className="text-red-500">
<strong>Note:</strong> Be careful with the Maximum mode. It
may increase resource usage significantly.
</p>
<br />
<p>
<strong>Base:</strong> Ollama automatically limits the context
to 2048 tokens, keeping resources usage low while maintaining
good performance. Suitable for most users and models.
</p>
<br />
<p>
<strong>Maximum:</strong> Uses the full context window (up to
Max Tokens). Will result in increased resource usage but
allows for larger context conversations. <br />
<br />
This is not recommended for most users.
</p>
</Tooltip>
</div>
<div className="flex flex-col w-60">
<label className="text-white text-sm font-semibold block mb-2">
Ollama Keep Alive
</label>
<select
name="OllamaLLMKeepAliveSeconds"
required={true}
className="border-none bg-theme-settings-input-bg border-gray-500 text-white text-sm rounded-lg block w-full p-2.5"
defaultValue={settings?.OllamaLLMKeepAliveSeconds ?? "300"}
>
<option value="0">No cache</option>
<option value="300">5 minutes</option>
<option value="3600">1 hour</option>
<option value="-1">Forever</option>
</select>
<p className="text-xs leading-[18px] font-base text-white text-opacity-60 mt-2">
Choose how long Ollama should keep your model in memory before
unloading.
<a
className="underline text-blue-300"
href="https://github.com/ollama/ollama/blob/main/docs/faq.md#how-do-i-keep-a-model-loaded-in-memory-or-make-it-unload-immediately"
target="_blank"
rel="noreferrer"
>
{" "}
Learn more &rarr;
</a>
</p>
<br />
<p>
<strong>Maximum:</strong> Uses the full context window (up to
Max Tokens). Will result in increased resource usage but allows
for larger context conversations. <br />
</div>
</div>
<div className="w-full flex items-start gap-4">
<div className="flex flex-col w-100">
<label className="text-white text-sm font-semibold">
Auth Token
</label>
<p className="text-xs leading-[18px] font-base text-white text-opacity-60 mt-2">
Enter a <code>Bearer</code> Auth Token for interacting with your
Ollama server.
<br />
This is not recommended for most users.
Used <b>only</b> if running Ollama behind an authentication
server.
</p>
</Tooltip>
<input
type="password"
name="OllamaLLMAuthToken"
className="border-none bg-theme-settings-input-bg mt-2 text-white placeholder:text-theme-settings-input-placeholder text-sm rounded-lg outline-none block w-full p-2.5"
placeholder="Ollama Auth Token"
value={authTokenValue.value}
onChange={authToken.onChange}
onBlur={authToken.onBlur}
required={false}
autoComplete="off"
spellCheck={false}
/>
</div>
</div>
</div>
</div>
</div>
);
}

function OllamaLLMModelSelection({ settings, basePath = null }) {
function OllamaLLMModelSelection({
settings,
basePath = null,
authToken = null,
}) {
const [customModels, setCustomModels] = useState([]);
const [loading, setLoading] = useState(true);

Expand All @@ -207,7 +241,11 @@ function OllamaLLMModelSelection({ settings, basePath = null }) {
}
setLoading(true);
try {
const { models } = await System.customModels("ollama", null, basePath);
const { models } = await System.customModels(
"ollama",
authToken,
basePath
);
setCustomModels(models || []);
} catch (error) {
console.error("Failed to fetch custom models:", error);
Expand All @@ -216,7 +254,7 @@ function OllamaLLMModelSelection({ settings, basePath = null }) {
setLoading(false);
}
findCustomModels();
}, [basePath]);
}, [basePath, authToken]);

if (loading || customModels.length == 0) {
return (
Expand Down
27 changes: 25 additions & 2 deletions frontend/src/hooks/useProviderEndpointAutoDiscovery.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,11 +5,15 @@ import showToast from "@/utils/toast";
export default function useProviderEndpointAutoDiscovery({
provider = null,
initialBasePath = "",
initialAuthToken = null,
ENDPOINTS = [],
}) {
const [loading, setLoading] = useState(false);
const [basePath, setBasePath] = useState(initialBasePath);
const [basePathValue, setBasePathValue] = useState(initialBasePath);

const [authToken, setAuthToken] = useState(initialAuthToken);
const [authTokenValue, setAuthTokenValue] = useState(initialAuthToken);
const [autoDetectAttempted, setAutoDetectAttempted] = useState(false);
const [showAdvancedControls, setShowAdvancedControls] = useState(true);

Expand All @@ -20,7 +24,7 @@ export default function useProviderEndpointAutoDiscovery({
ENDPOINTS.forEach((endpoint) => {
possibleEndpoints.push(
new Promise((resolve, reject) => {
System.customModels(provider, null, endpoint, 2_000)
System.customModels(provider, authTokenValue, endpoint, 2_000)
.then((results) => {
if (!results?.models || results.models.length === 0)
throw new Error("No models");
Expand Down Expand Up @@ -74,9 +78,18 @@ export default function useProviderEndpointAutoDiscovery({
setBasePath(basePathValue);
}

function handleAuthTokenChange(e) {
const value = e.target.value;
setAuthTokenValue(value);
}

function handleAuthTokenBlur() {
setAuthToken(authTokenValue);
}

useEffect(() => {
if (!initialBasePath && !autoDetectAttempted) autoDetect(true);
}, [initialBasePath, autoDetectAttempted]);
}, [initialBasePath, initialAuthToken, autoDetectAttempted]);

return {
autoDetecting: loading,
Expand All @@ -93,6 +106,16 @@ export default function useProviderEndpointAutoDiscovery({
value: basePathValue,
set: setBasePathValue,
},
authToken: {
value: authToken,
set: setAuthTokenValue,
onChange: handleAuthTokenChange,
onBlur: handleAuthTokenBlur,
},
authTokenValue: {
value: authTokenValue,
set: setAuthTokenValue,
},
handleAutoDetectClick,
runAutoDetect: autoDetect,
};
Expand Down
1 change: 1 addition & 0 deletions server/.env.example
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,7 @@ SIG_SALT='salt' # Please generate random string at least 32 chars long.
# OLLAMA_BASE_PATH='http://host.docker.internal:11434'
# OLLAMA_MODEL_PREF='llama2'
# OLLAMA_MODEL_TOKEN_LIMIT=4096
# OLLAMA_AUTH_TOKEN='your-ollama-auth-token-here (optional, only for ollama running behind auth - Bearer token)'

# LLM_PROVIDER='togetherai'
# TOGETHER_AI_API_KEY='my-together-ai-key'
Expand Down
1 change: 1 addition & 0 deletions server/models/systemSettings.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -471,6 +471,7 @@ const SystemSettings = {
OllamaLLMTokenLimit: process.env.OLLAMA_MODEL_TOKEN_LIMIT,
OllamaLLMKeepAliveSeconds: process.env.OLLAMA_KEEP_ALIVE_TIMEOUT ?? 300,
OllamaLLMPerformanceMode: process.env.OLLAMA_PERFORMANCE_MODE ?? "base",
OllamaLLMAuthToken: process.env.OLLAMA_AUTH_TOKEN ?? null,

// Novita LLM Keys
NovitaLLMApiKey: !!process.env.NOVITA_LLM_API_KEY,
Expand Down
Loading