llms-py 2.0.8__py3-none-any.whl → 2.0.10__py3-none-any.whl

llms.py

@@ -14,6 +14,7 @@ import mimetypes
 import traceback
 import sys
 import site
+from urllib.parse import parse_qs
 
 import aiohttp
 from aiohttp import web
@@ -21,7 +22,7 @@ from aiohttp import web
 from pathlib import Path
 from importlib import resources   # Py≥3.9  (pip install importlib_resources for 3.7/3.8)
 
-VERSION = "2.0.8"
+VERSION = "2.0.10"
 _ROOT = None
 g_config_path = None
 g_ui_path = None
@@ -63,7 +64,8 @@ def chat_summary(chat):
                     elif 'file' in item:
                         if 'file_data' in item['file']:
                             data = item['file']['file_data']
-                            item['file']['file_data'] = f"({len(data)})"
+                            prefix = data.split(',', 1)[0]
+                            item['file']['file_data'] = prefix + f",({len(data) - len(prefix)})"
     return json.dumps(clone, indent=2)
 
 def gemini_chat_summary(gemini_chat):
@@ -89,6 +91,60 @@ def is_url(url):
 def get_filename(file):
     return file.rsplit('/',1)[1] if '/' in file else 'file'
 
+def parse_args_params(args_str):
+    """Parse URL-encoded parameters and return a dictionary."""
+    if not args_str:
+        return {}
+
+    # Parse the URL-encoded string
+    parsed = parse_qs(args_str, keep_blank_values=True)
+
+    # Convert to simple dict with single values (not lists)
+    result = {}
+    for key, values in parsed.items():
+        if len(values) == 1:
+            value = values[0]
+            # Try to convert to appropriate types
+            if value.lower() == 'true':
+                result[key] = True
+            elif value.lower() == 'false':
+                result[key] = False
+            elif value.isdigit():
+                result[key] = int(value)
+            else:
+                try:
+                    # Try to parse as float
+                    result[key] = float(value)
+                except ValueError:
+                    # Keep as string
+                    result[key] = value
+        else:
+            # Multiple values, keep as list
+            result[key] = values
+
+    return result
+
+def apply_args_to_chat(chat, args_params):
+    """Apply parsed arguments to the chat request."""
+    if not args_params:
+        return chat
+
+    # Apply each parameter to the chat request
+    for key, value in args_params.items():
+        if isinstance(value, str):
+            if key == 'stop':
+                if ',' in value:
+                    value = value.split(',')
+            elif key == 'max_completion_tokens' or key == 'max_tokens' or key == 'n' or key == 'seed' or key == 'top_logprobs':
+                value = int(value)
+            elif key == 'temperature' or key == 'top_p' or key == 'frequency_penalty' or key == 'presence_penalty':
+                value = float(value)
+            elif key == 'store' or key == 'logprobs' or key == 'enable_thinking' or key == 'parallel_tool_calls' or key == 'stream':
+                value = bool(value)
+        chat[key] = value
+
+    return chat
+
 def is_base_64(data):
     try:
         base64.b64decode(data)
@@ -190,8 +246,9 @@ async def process_chat(chat):
                                     content = f.read()
                                     file['filename'] = get_filename(url)
                                     file['file_data'] = f"data:{mimetype};base64,{base64.b64encode(content).decode('utf-8')}"
-                            elif is_base_64(url):
-                                file['filename'] = 'file'
+                            elif url.startswith('data:'):
+                                if 'filename' not in file:
+                                    file['filename'] = 'file' 
                                 pass # use base64 data as-is
                             else:
                                 raise Exception(f"Invalid file: {url}")
@@ -232,6 +289,25 @@ class OpenAiProvider:
         if api_key is not None:
             self.headers["Authorization"] = f"Bearer {api_key}"
 
+        self.frequency_penalty = float(kwargs['frequency_penalty']) if 'frequency_penalty' in kwargs else None
+        self.max_completion_tokens = int(kwargs['max_completion_tokens']) if 'max_completion_tokens' in kwargs else None
+        self.n = int(kwargs['n']) if 'n' in kwargs else None
+        self.parallel_tool_calls = bool(kwargs['parallel_tool_calls']) if 'parallel_tool_calls' in kwargs else None
+        self.presence_penalty = float(kwargs['presence_penalty']) if 'presence_penalty' in kwargs else None
+        self.prompt_cache_key = kwargs['prompt_cache_key'] if 'prompt_cache_key' in kwargs else None
+        self.reasoning_effort = kwargs['reasoning_effort'] if 'reasoning_effort' in kwargs else None
+        self.safety_identifier = kwargs['safety_identifier'] if 'safety_identifier' in kwargs else None        
+        self.seed = int(kwargs['seed']) if 'seed' in kwargs else None
+        self.service_tier = kwargs['service_tier'] if 'service_tier' in kwargs else None
+        self.stop = kwargs['stop'] if 'stop' in kwargs else None
+        self.store = bool(kwargs['store']) if 'store' in kwargs else None
+        self.temperature = float(kwargs['temperature']) if 'temperature' in kwargs else None
+        self.top_logprobs = int(kwargs['top_logprobs']) if 'top_logprobs' in kwargs else None
+        self.top_p = float(kwargs['top_p']) if 'top_p' in kwargs else None
+        self.verbosity = kwargs['verbosity'] if 'verbosity' in kwargs else None
+        self.stream = bool(kwargs['stream']) if 'stream' in kwargs else None
+        self.enable_thinking = bool(kwargs['enable_thinking']) if 'enable_thinking' in kwargs else None
+
     @classmethod
     def test(cls, base_url=None, api_key=None, models={}, **kwargs):
         return base_url is not None and api_key is not None and len(models) > 0
@@ -247,6 +323,41 @@ class OpenAiProvider:
         # with open(os.path.join(os.path.dirname(__file__), 'chat.wip.json'), "w") as f:
         #     f.write(json.dumps(chat, indent=2))
 
+        if self.frequency_penalty is not None:
+            chat['frequency_penalty'] = self.frequency_penalty
+        if self.max_completion_tokens is not None:
+            chat['max_completion_tokens'] = self.max_completion_tokens
+        if self.n is not None:
+            chat['n'] = self.n
+        if self.parallel_tool_calls is not None:
+            chat['parallel_tool_calls'] = self.parallel_tool_calls
+        if self.presence_penalty is not None:
+            chat['presence_penalty'] = self.presence_penalty
+        if self.prompt_cache_key is not None:
+            chat['prompt_cache_key'] = self.prompt_cache_key
+        if self.reasoning_effort is not None:
+            chat['reasoning_effort'] = self.reasoning_effort
+        if self.safety_identifier is not None:
+            chat['safety_identifier'] = self.safety_identifier
+        if self.seed is not None:
+            chat['seed'] = self.seed
+        if self.service_tier is not None:
+            chat['service_tier'] = self.service_tier
+        if self.stop is not None:
+            chat['stop'] = self.stop
+        if self.store is not None:
+            chat['store'] = self.store
+        if self.temperature is not None:
+            chat['temperature'] = self.temperature
+        if self.top_logprobs is not None:
+            chat['top_logprobs'] = self.top_logprobs
+        if self.top_p is not None:
+            chat['top_p'] = self.top_p
+        if self.verbosity is not None:
+            chat['verbosity'] = self.verbosity
+        if self.enable_thinking is not None:
+            chat['enable_thinking'] = self.enable_thinking
+
         chat = await process_chat(chat)
         _log(f"POST {self.chat_url}")
         _log(chat_summary(chat))
@@ -333,7 +444,14 @@ class GoogleProvider(OpenAiProvider):
         async with aiohttp.ClientSession() as session:
             for message in chat['messages']:
                 if message['role'] == 'system':
-                    system_prompt = message
+                    content = message['content']
+                    if isinstance(content, list):
+                        for item in content:
+                            if 'text' in item:
+                                system_prompt = item['text']
+                                break
+                    elif isinstance(content, str):
+                        system_prompt = content
                 elif 'content' in message:
                     if isinstance(message['content'], list):
                         parts = []
@@ -409,7 +527,7 @@ class GoogleProvider(OpenAiProvider):
             # Add system instruction if present
             if system_prompt is not None:
                 gemini_chat['systemInstruction'] = {
-                    "parts": [{"text": system_prompt['content']}]
+                    "parts": [{"text": system_prompt}]
                 }
 
             if 'stop' in chat:
@@ -537,10 +655,14 @@ async def chat_completion(chat):
     # If we get here, all providers failed
     raise first_exception
 
-async def cli_chat(chat, image=None, audio=None, file=None, raw=False):
+async def cli_chat(chat, image=None, audio=None, file=None, args=None, raw=False):
     if g_default_model:
         chat['model'] = g_default_model
 
+    # Apply args parameters to chat request
+    if args:
+        chat = apply_args_to_chat(chat, args)
+
     # process_chat downloads the image, just adding the reference here
     if image is not None:
         first_message = None
@@ -925,6 +1047,7 @@ def main():
     parser.add_argument('--image',        default=None, help='Image input to use in chat completion')
     parser.add_argument('--audio',        default=None, help='Audio input to use in chat completion')
     parser.add_argument('--file',         default=None, help='File input to use in chat completion')
+    parser.add_argument('--args',         default=None, help='URL-encoded parameters to add to chat request (e.g. "temperature=0.7&seed=111")', metavar='PARAMS')
     parser.add_argument('--raw',          action='store_true', help='Return raw AI JSON response')
 
     parser.add_argument('--list',         action='store_true', help='Show list of enabled providers and their models (alias ls provider?)')
@@ -1141,7 +1264,7 @@ def main():
         app.router.add_route('*', '/{tail:.*}', index_handler)
         
         if os.path.exists(g_ui_path):
-            async def ui_json_handler(request):
+            async def ui_config_handler(request):
                 with open(g_ui_path, "r") as f:
                     ui = json.load(f)
                     if 'defaults' not in ui:
@@ -1153,7 +1276,7 @@ def main():
                         "disabled": disabled 
                     }
                     return web.json_response(ui)
-            app.router.add_get('/ui.json', ui_json_handler)
+            app.router.add_get('/config', ui_config_handler)
 
         print(f"Starting server on port {port}...")
         web.run_app(app, host='0.0.0.0', port=port)
@@ -1256,13 +1379,21 @@ def main():
             if len(extra_args) > 0:
                 prompt = ' '.join(extra_args)
                 # replace content of last message if exists, else add
-                last_msg = chat['messages'][-1]
-                if last_msg['role'] == 'user':
-                    last_msg['content'] = prompt
+                last_msg = chat['messages'][-1] if 'messages' in chat else None
+                if last_msg and last_msg['role'] == 'user':
+                    if isinstance(last_msg['content'], list):
+                        last_msg['content'][-1]['text'] = prompt
+                    else:
+                        last_msg['content'] = prompt
                 else:
                     chat['messages'].append({'role': 'user', 'content': prompt})
 
-            asyncio.run(cli_chat(chat, image=cli_args.image, audio=cli_args.audio, file=cli_args.file, raw=cli_args.raw))
+            # Parse args parameters if provided
+            args = None
+            if cli_args.args is not None:
+                args = parse_args_params(cli_args.args)
+
+            asyncio.run(cli_chat(chat, image=cli_args.image, audio=cli_args.audio, file=cli_args.file, args=args, raw=cli_args.raw))
             exit(0)
         except Exception as e:
             print(f"{cli_args.logprefix}Error: {e}")

llms_py-2.0.10.data/data/index.html

@@ -0,0 +1,80 @@
+<html>
+<head>
+    <title>llms.py</title>
+    <link rel="stylesheet" href="/ui/typography.css">
+    <link rel="stylesheet" href="/ui/app.css">
+    <link rel="icon" type="image/svg" href="/ui/fav.svg">
+    <style>
+        [type='button'],button[type='submit']{cursor:pointer}
+        [type='checkbox'].switch:checked:hover, 
+        [type='checkbox'].switch:checked:focus,
+        [type='checkbox'].switch:checked,
+        [type='checkbox'].switch:focus,
+        [type='checkbox'].switch
+        {
+            border: none; 
+            background: none;
+            outline: none;
+            box-shadow: none;
+            cursor: pointer;
+        }
+    </style>
+</head>
+<script type="importmap">
+    {
+        "imports": {
+            "vue": "/ui/lib/vue.min.mjs",
+            "vue-router": "/ui/lib/vue-router.min.mjs",
+            "@servicestack/client": "/ui/lib/servicestack-client.mjs",
+            "@servicestack/vue": "/ui/lib/servicestack-vue.mjs",
+            "idb": "/ui/lib/idb.min.mjs",
+            "marked": "/ui/lib/marked.min.mjs",
+            "highlight.js": "/ui/lib/highlight.min.mjs"
+        }
+    }
+</script>
+<body>
+<div id="app"></div>
+</body>
+<script type="module">
+import { createApp, defineAsyncComponent } from 'vue'
+import { createWebHistory, createRouter } from "vue-router"
+import ServiceStackVue from "@servicestack/vue"
+import App from '/ui/App.mjs'
+import ai from '/ui/ai.mjs'
+import SettingsDialog from '/ui/SettingsDialog.mjs'
+
+const { config, models } = await ai.init()
+const MainComponent = defineAsyncComponent(() => import(ai.base + '/ui/Main.mjs'))
+const RecentsComponent = defineAsyncComponent(() => import(ai.base + '/ui/Recents.mjs'))
+
+const Components = {
+    SettingsDialog,
+}
+
+const routes = [
+    { path: '/', component: MainComponent },
+    { path: '/c/:id', component: MainComponent },
+    { path: '/recents', component: RecentsComponent  },
+    { path: '/:fallback(.*)*', component: MainComponent }
+]
+routes.forEach(r => r.path = ai.base + r.path)
+const router = createRouter({
+    history: createWebHistory(),
+    routes,
+})
+const app = createApp(App, { config, models })
+app.use(router)
+app.use(ServiceStackVue)
+app.provide('ai', ai)
+app.provide('config', config)
+app.provide('models', models)
+Object.keys(Components).forEach(name => {
+    app.component(name, Components[name])
+})
+
+window.ai = app.config.globalProperties.$ai = ai
+
+app.mount('#app')
+</script>
+</html>

{llms_py-2.0.8.data → llms_py-2.0.10.data}/data/llms.json

@@ -9,7 +9,12 @@
             "messages": [
                 {
                     "role": "user",
-                    "content": ""
+                    "content": [
+                        {
+                            "type": "text",
+                            "text": ""
+                        }
+                    ]
                 }
             ]
         },
@@ -90,10 +95,8 @@
                 "deepseek-r1:671b": "deepseek/deepseek-r1-0528:free",
                 "gemini-2.0-flash": "google/gemini-2.0-flash-exp:free",
                 "glm-4.5-air": "z-ai/glm-4.5-air:free",
-                "grok-4-fast": "x-ai/grok-4-fast:free",
                 "mai-ds-r1": "microsoft/mai-ds-r1:free",
                 "llama3.3:70b": "meta-llama/llama-3.3-70b-instruct:free",
-                "kimi-k2": "moonshotai/kimi-k2:free",
                 "nemotron-nano:9b": "nvidia/nemotron-nano-9b-v2:free",
                 "deepseek-r1-distill-llama:70b": "deepseek/deepseek-r1-distill-llama-70b:free",
                 "gpt-oss:20b": "openai/gpt-oss-20b:free",
@@ -102,7 +105,6 @@
                 "devstral-small": "mistralai/devstral-small-2505:free",
                 "venice-uncensored:24b": "cognitivecomputations/dolphin-mistral-24b-venice-edition:free",
                 "llama3.3:8b": "meta-llama/llama-3.3-8b-instruct:free",
-                "llama3.1:405b": "meta-llama/llama-3.1-405b-instruct:free",
                 "kimi-dev:72b": "moonshotai/kimi-dev-72b:free",
                 "gemma3:27b": "google/gemma-3-27b-it:free",
                 "qwen3-coder": "qwen/qwen3-coder:free",
@@ -171,7 +173,7 @@
             }
         },
         "ollama": {
-            "enabled": false,
+            "enabled": true,
             "type": "OllamaProvider",
             "base_url": "http://localhost:11434",
             "models": {},
@@ -389,7 +391,8 @@
                 "qwen2.5-vl:7b": "qwen2.5-vl-7b-instruct",
                 "qwen2.5-vl:3b": "qwen2.5-vl-3b-instruct",
                 "qwen2.5-omni:7b": "qwen2.5-omni-7b"
-            }
+            },
+            "enable_thinking": false
         },
         "z.ai": {
             "enabled": false,
@@ -404,7 +407,8 @@
                 "glm-4.5-airx": "glm-4.5-airx",
                 "glm-4.5-flash": "glm-4.5-flash",
                 "glm-4:32b": "glm-4-32b-0414-128k"
-            }
+            },
+            "temperature": 0.7
         },
         "mistral": {
             "enabled": false,
@@ -417,20 +421,22 @@
                 "devstral-medium": "devstral-medium-2507",
                 "codestral:22b": "codestral-latest",
                 "mistral-ocr": "mistral-ocr-latest",
-                "voxtral-mini": "voxtral-mini-latest",
                 "mistral-small3.2:24b": "mistral-small-latest",
                 "magistral-small": "magistral-small-latest",
                 "devstral-small": "devstral-small-2507",
                 "voxtral-small": "voxtral-small-latest",
+                "voxtral-mini": "voxtral-mini-latest",
+                "codestral-embed": "codestral-embed-2505",
+                "mistral-embed": "mistral-embed",
                 "mistral-large:123b": "mistral-large-latest",
                 "pixtral-large:124b": "pixtral-large-latest",
                 "pixtral:12b": "pixtral-12b",
-                "mistral-nemo:12b": "mistral-nemo",
+                "mistral-nemo:12b": "open-mistral-nemo",
                 "mistral-saba": "mistral-saba-latest",
                 "mistral:7b": "open-mistral-7b",
                 "mixtral:8x7b": "open-mixtral-8x7b",
                 "mixtral:8x22b": "open-mixtral-8x22b",
-                "ministral:8b": "ministral-3b-latest",
+                "ministral:8b": "ministral-8b-latest",
                 "ministral:3b": "ministral-3b-latest"
             }
         }

llms_py-2.0.10.data/data/ui/Avatar.mjs

@@ -0,0 +1,28 @@
+import { computed, inject } from "vue"
+
+export default {
+    template:`
+        <div v-if="$ai.auth?.profileUrl" :title="authTitle">
+            <img :src="$ai.auth.profileUrl" class="size-8 rounded-full" />
+        </div>
+    `,
+    setup() {
+        const ai = inject('ai')
+        const authTitle = computed(() => {
+            if (!ai.auth) return ''
+            const { userId, userName, displayName, bearerToken, roles } = ai.auth
+            const name = userName || displayName
+            const prefix = roles && roles.includes('Admin') ? 'Admin' : 'Name'
+            const sb = [
+                name ? `${prefix}: ${name}` : '',
+                `API Key: ${bearerToken}`,
+                `${userId}`,
+            ]
+            return sb.filter(x => x).join('\n')
+        })
+        
+        return {
+            authTitle,
+        }
+    }
+}

llms_py-2.0.10.data/data/ui/Brand.mjs

@@ -0,0 +1,23 @@
+export default {
+    template:`
+    <div class="flex-shrink-0 px-4 py-4 border-b border-gray-200 bg-white min-h-16 select-none">
+        <div class="flex items-center justify-between">
+            <button type="button"
+                @click="$emit('home')"
+                class="text-lg font-semibold text-gray-900 hover:text-blue-600 focus:outline-none transition-colors"
+                title="Go back to initial state"
+            >
+                History
+            </button>
+            <button type="button"
+                @click="$emit('new')"
+                class="text-gray-900 hover:text-blue-600 focus:outline-none transition-colors"
+                title="New Chat"
+            >
+                <svg class="size-6" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><g fill="none" stroke="currentColor" stroke-linecap="round" stroke-linejoin="round" stroke-width="2"><path d="M12 3H5a2 2 0 0 0-2 2v14a2 2 0 0 0 2 2h14a2 2 0 0 0 2-2v-7"/><path d="M18.375 2.625a1 1 0 0 1 3 3l-9.013 9.014a2 2 0 0 1-.853.505l-2.873.84a.5.5 0 0 1-.62-.62l.84-2.873a2 2 0 0 1 .506-.852z"/></g></svg>
+            </button>
+        </div>
+    </div>
+    `,
+    emits:['home','new'],
+}