هل كان لدى أحد تجربة في جعل هذا يعمل مع ollama محليًا؟
أحاول أيضًا جعل هذا يعمل مع ollama، يبدو أن واجهة برمجة التطبيقات (API) التي يستخدمها المكوّن الإضافي Discourse AI غير متوافقة مع Ollama وأي إعدادات أقوم بتغييرها لا تغير طلب واجهة برمجة التطبيقات (API).
هذا ما يعمل مع ollama:
curl http://192.168.1.2:11434/api/generate -d '{\
\"model\": \"llama3.2\",\
\"prompt\": \"Why is the sky blue?\"\
}'
ويبدو أن ما ورد أعلاه هو النوع الوحيد من الطلبات التي يحاولها المكوّن الإضافي. على سبيل المثال:
curl http://192.168.1.2:11434/ \
-X POST \
-H 'Content-Type: application/json' \
-d '{\"inputs\":\"\u003cs\u003e[INST] What is your favourite condiment? [/INST] Well, Im quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever Im cooking up in the kitchen!\u003c/s\u003e [INST] Do you have mayonnaise recipes? [/INST]\",\"parameters\":{\"max_new_tokens\":500, \"temperature\":0.5,\"top_p\": 0.9}}'
من المفترض أن يدعم روبوت الدردشة بالذكاء الاصطناعي ollama ولكنني غير قادر على الحصول على رد منه أيضًا.
لذا، أي شخص نجح في جعل هذا يعمل مع ollama، يرجى نشر الإعدادات التي استخدمتها!
إعجابَين (2)
يبدو أنني تحدثت مبكرًا جدًا، إذا لم يكن لدي أي إعدادات في إضافة Discourse AI مضبوطة وقمت باتباع تعليمات RAG في هذا المنشور أحصل على ردود في دردشة الذكاء الاصطناعي من Ollama!
إعجاب واحد (1)
يعمل بشكل جيد تمامًا مع ollama، لدينا عدة أشخاص في الفريق يستخدمونه.
إعجاب واحد (1)
رائع. هل يوجد دليل يمكننا اتباعه حول كيفية تطبيق ذلك؟
أنا مهتم أكثر بالتلخيص والوظائف الأخرى بدلاً من روبوت الدردشة.
تقدير الوقت: هذه التهيئة لا تعمل:
(لقد قمت بإخفاء عنوان IP الخاص بمضيفي هنا).
ما يحدث هو أنني أحصل على خطأ داخلي في الخادم عند النقر فوق “تشغيل الاختبار”.
في /logs، أرى:
NameError (متغير محلي غير معرف أو طريقة `tokenizer' لنسخة من `DiscourseAi::Completions::Dialects::ChatGpt)
app/controllers/application_controller.rb:427:in `block in with_resolved_locale'
app/controllers/application_controller.rb:427:in `with_resolved_locale'
lib/middleware/omniauth_bypass_middleware.rb:35:in `call'
lib/content_security_policy/middleware.rb:12:in `call'
lib/middleware/anonymous_cache.rb:409:in `call'
lib/middleware/csp_script_nonce_injector.rb:12:in `call'
config/initializers/008-rack-cors.rb:14:in `call'
config/initializers/100-quiet_logger.rb:20:in `call'
config/initializers/100-silence_logger.rb:29:in `call'
lib/middleware/enforce_hostname.rb:24:in `call'
lib/middleware/processing_request.rb:12:in `call'
lib/middleware/request_tracker.rb:385:in `call'
يحدث هذا بغض النظر عن المُرمّز الذي أختاره. أنا أختبر هذا على 3.5.0beta1-dev (c1ee4e120e).
إعجاب واحد (1)
عيّن عنوان URL إلى http://localhost:11434/v1/chat/completions
إعجاب واحد (1)
لا يزال الاختبار يفشل مع خطأ في الخادم الداخلي، ونفس رسالة السجل أيضًا - خطأ NameError يقول أن ‘tokenizer’ هو متغير محلي غير معرف.
إعجاب واحد (1)
جرب حفظ النموذج كما هو، ثم قم بتحديث الصفحة، ثم عد مرة أخرى عبر زر “تعديل LLM” وقم بتشغيل اختبار جديد.
نفس النتيجة - لقد مررت بها عدة مرات، لكنني جربتها مرة أخرى للتو.
لقد قمت بالتثبيت بالطريقة المعتادة - أضفتها إلى ملف app.yml الخاص بي وقمت بتشغيل ./launcher rebuild app
السطر الذي أضفته كان:
hooks:
after_code:
- exec:
cd: $home/plugins
cmd:
- sudo -E -u discourse git clone https://github.com/discourse/discourse-ai.git
(لقد أزلت المكونات الإضافية الأخرى من القائمة ولكن تركت مكونات yml حتى تتمكن من رؤية مكان هذا في ملف yml.)
إعجاب واحد (1)
سأعيد إعداد أولاما المحلية الخاصة بي غدًا وسأبلغ هنا.
إعجاب واحد (1)
لقد فعلت:
ollama serve
ollama run phi4
# اختبار
curl http://localhost:11434/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "phi4",
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How much is 1+1?"
}
]
}' -s | jq .choices[].message.content
"The sum of 1 + 1 is 2. \n\nIn basic arithmetic, when you add one unit to another single unit, the total number becomes two units. This operation is part of fundamental addition principles used in mathematics. Is there anything else I can help with regarding math or any other topic?"
تم اختباره على المساعد
إعجابَين (2)
Thanks for testing this.
I notice that I’ve got an extra option (Disable streaming completions) compared to your config. Is it possible it’s the model selection that’s causing an issue for me? (I’ve got deepseek-r1:32b installed).
curl http://localhost:11434/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-r1:32b",
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How much is 1+1?"
}
]
}' -s | jq .choices[].message.content
"<think>\nAlright, I'm trying to figure out how much 1 plus 1 equals. Okay, so let's break this down step by step even though it seems simple.\n\nFirst, I know that addition is combining two numbers to get a total sum. So, when we say 1 + 1, we're essentially putting together one object and another object to see how many we have in total.\n\nLet me visualize it: imagine I have one apple in my left hand and another apple in my right hand. If I put them together, how many apples do I have? It should be two apples, right?\n\nAnother way to think about it is using a number line. Starting at the number 1, if I move forward by one more step, where do I land? That's right, on the number 2.\n\nI can also use my fingers to count. Hold up one finger on my left hand and another on my right. Now, count them all: one, two. So that gives me a total of two fingers, which means 1 + 1 = 2.\n\nMaybe I should check if there's another perspective or method. For instance, in binary, the number system used by computers, 1 + 1 equals 10 because it carries over after reaching 2 (which is represented as 10). But that's a different context. In standard base-10 arithmetic, which we use daily, 1 + 1 remains 2.\n\nLet me also consider the concept of sets. If I have a set containing one element and another set with one element, combining them would result in a set with two elements. That reinforces that 1 + 1 equals 2.\n\nI might wonder if there's any scenario where 1 + 1 doesn't equal 2. But within the realm of basic arithmetic and mathematics as we learn it, the answer is consistently two.\n\nTo make sure I'm not missing anything, maybe I should look into some mathematical proofs or principles that confirm this. For example, in Peano axioms, which form the foundation of arithmetic, the idea of adding 1 to 1 would follow the axiom that every natural number has a successor, and 2 is defined as the successor of 1.\n\nTherefore, putting all these thoughts together—visualizing objects, using a number line, counting fingers, considering sets, and even touching on mathematical axioms—it all points towards 1 + 1 equaling 2.\n</think>\n\nThe result of adding 1 and 1 together is 2. This can be seen in simple arithmetic and various ways of visualizing the problem.\n\n**Answer:** \n$1 + 1 = \\boxed{2}$"
Similar result, though I get the <think> tags with this particular model - so maybe the model won’t be suitable for this use.
I’ve just rebuilt (ie, ./launcher rebuild app) my installation and made sure everything is current - I show “all up-to-date” in my Update page.
Selecting either deepseek-r1:32b or phi4 (which I installed and tested as well), I still am getting the internal server error response in the browser.
But in my logs, I’m seeing something new.
FinalDestination::SSRFDetector::DisallowedIpError (FinalDestination: all resolved IPs were disallowed) lib/final_destination/ssrf_detector.rb:105:in 'lookup_and_filter_ips' lib/final_destination/http'
lib/final_destination/ssrf_detector.rb:105:in `lookup_and_filter_ips'
lib/final_destination/http.rb:15:in `connect'
net-http (0.6.0) lib/net/http.rb:1642:in `do_start'
net-http (0.6.0) lib/net/http.rb:1631:in `start'
net-http (0.6.0) lib/net/http.rb:1070:in `start'
plugins/discourse-ai/lib/completions/endpoints/base.rb:105:in `perform_completion!'
plugins/discourse-ai/lib/completions/endpoints/open_ai.rb:44:in `perform_completion!'
plugins/discourse-ai/lib/completions/llm.rb:281:in `generate'
plugins/discourse-ai/lib/configuration/llm_validator.rb:36:in `run_test'
plugins/discourse-ai/app/controllers/discourse_ai/admin/ai_llms_controller.rb:128:in `test'
actionpack (7.2.2.1) lib/action_controller/metal/basic_implicit_render.rb:8:in `send_action'
actionpack (7.2.2.1) lib/abstract_controller/base.rb:226:in `process_action'
actionpack (7.2.2.1) lib/action_controller/metal/rendering.rb:193:in `process_action'
actionpack (7.2.2.1) lib/abstract_controller/callbacks.rb:261:in `block in process_action'
activesupport (7.2.2.1) lib/active_support/callbacks.rb:121:in `block in run_callbacks'
app/controllers/application_controller.rb:427:in `block in with_resolved_locale'
i18n (1.14.7) lib/i18n.rb:353:in `with_locale'
app/controllers/application_controller.rb:427:in `with_resolved_locale'
activesupport (7.2.2.1) lib/active_support/callbacks.rb:130:in `block in run_callbacks'
activesupport (7.2.2.1) lib/active_support/callbacks.rb:141:in `run_callbacks'
actionpack (7.2.2.1) lib/abstract_controller/callbacks.rb:260:in `process_action'
actionpack (7.2.2.1) lib/action_controller/metal/rescue.rb:27:in `process_action'
actionpack (7.2.2.1) lib/action_controller/metal/instrumentation.rb:77:in `block in process_action'
activesupport (7.2.2.1) lib/active_support/notifications.rb:210:in `block in instrument'
activesupport (7.2.2.1) lib/active_support/notifications/instrumenter.rb:58:in `instrument'
activesupport (7.2.2.1) lib/active_support/notifications.rb:210:in `instrument'
actionpack (7.2.2.1) lib/action_controller/metal/instrumentation.rb:76:in `process_action'
actionpack (7.2.2.1) lib/action_controller/metal/params_wrapper.rb:259:in `process_action'
activerecord (7.2.2.1) lib/active_record/railties/controller_runtime.rb:39:in `process_action'
actionpack (7.2.2.1) lib/abstract_controller/base.rb:163:in `process'
actionview (7.2.2.1) lib/action_view/rendering.rb:40:in `process'
rack-mini-profiler (3.3.1) lib/mini_profiler/profiling_methods.rb:115:in `block in profile_method'
actionpack (7.2.2.1) lib/action_controller/metal.rb:252:in `dispatch'
actionpack (7.2.2.1) lib/action_controller/metal.rb:335:in `dispatch'
actionpack (7.2.2.1) lib/action_dispatch/routing/route_set.rb:67:in `dispatch'
actionpack (7.2.2.1) lib/action_dispatch/routing/route_set.rb:50:in `serve'
actionpack (7.2.2.1) lib/action_dispatch/routing/mapper.rb:32:in `block in <class:Constraints>'
actionpack (7.2.2.1) lib/action_dispatch/routing/mapper.rb:62:in `serve'
actionpack (7.2.2.1) lib/action_dispatch/journey/router.rb:53:in `block in serve'
actionpack (7.2.2.1) lib/action_dispatch/journey/router.rb:133:in `block in find_routes'
actionpack (7.2.2.1) lib/action_dispatch/journey/router.rb:126:in `each'
actionpack (7.2.2.1) lib/action_dispatch/journey/router.rb:126:in `find_routes'
actionpack (7.2.2.1) lib/action_dispatch/journey/router.rb:34:in `serve'
actionpack (7.2.2.1) lib/action_dispatch/routing/route_set.rb:896:in `call'
lib/middleware/omniauth_bypass_middleware.rb:35:in `call'
rack (2.2.11) lib/rack/tempfile_reaper.rb:15:in `call'
rack (2.2.11) lib/rack/conditional_get.rb:27:in `call'
rack (2.2.11) lib/rack/head.rb:12:in `call'
actionpack (7.2.2.1) lib/action_dispatch/http/permissions_policy.rb:38:in `call'
lib/content_security_policy/middleware.rb:12:in `call'
lib/middleware/anonymous_cache.rb:409:in `call'
lib/middleware/csp_script_nonce_injector.rb:12:in `call'
config/initializers/008-rack-cors.rb:14:in `call'
rack (2.2.11) lib/rack/session/abstract/id.rb:266:in `context'
rack (2.2.11) lib/rack/session/abstract/id.rb:260:in `call'
actionpack (7.2.2.1) lib/action_dispatch/middleware/cookies.rb:704:in `call'
actionpack (7.2.2.1) lib/action_dispatch/middleware/callbacks.rb:31:in `block in call'
activesupport (7.2.2.1) lib/active_support/callbacks.rb:101:in `run_callbacks'
actionpack (7.2.2.1) lib/action_dispatch/middleware/callbacks.rb:30:in `call'
actionpack (7.2.2.1) lib/action_dispatch/middleware/debug_exceptions.rb:31:in `call'
actionpack (7.2.2.1) lib/action_dispatch/middleware/show_exceptions.rb:32:in `call'
logster (2.20.1) lib/logster/middleware/reporter.rb:40:in `call'
railties (7.2.2.1) lib/rails/rack/logger.rb:41:in `call_app'
railties (7.2.2.1) lib/rails/rack/logger.rb:29:in `call'
config/initializers/100-quiet_logger.rb:20:in `call'
config/initializers/100-silence_logger.rb:29:in `call'
actionpack (7.2.2.1) lib/action_dispatch/middleware/request_id.rb:33:in `call'
lib/middleware/enforce_hostname.rb:24:in `call'
rack (2.2.11) lib/rack/method_override.rb:24:in `call'
actionpack (7.2.2.1) lib/action_dispatch/middleware/executor.rb:16:in `call'
rack (2.2.11) lib/rack/sendfile.rb:110:in `call'
rack-mini-profiler (3.3.1) lib/mini_profiler.rb:334:in `call'
lib/middleware/processing_request.rb:12:in `call'
message_bus (4.3.9) lib/message_bus/rack/middleware.rb:60:in `call'
lib/middleware/request_tracker.rb:385:in `call'
actionpack (7.2.2.1) lib/action_dispatch/middleware/remote_ip.rb:96:in `call'
railties (7.2.2.1) lib/rails/engine.rb:535:in `call'
railties (7.2.2.1) lib/rails/railtie.rb:226:in `public_send'
railties (7.2.2.1) lib/rails/railtie.rb:226:in `method_missing'
rack (2.2.11) lib/rack/urlmap.rb:74:in `block in call'
rack (2.2.11) lib/rack/urlmap.rb:58:in `each'
rack (2.2.11) lib/rack/urlmap.rb:58:in `call'
unicorn (6.1.0) lib/unicorn/http_server.rb:634:in `process_client'
unicorn (6.1.0) lib/unicorn/http_server.rb:739:in `worker_loop'
unicorn (6.1.0) lib/unicorn/http_server.rb:547:in `spawn_missing_workers'
unicorn (6.1.0) lib/unicorn/http_server.rb:143:in `start'
unicorn (6.1.0) bin/unicorn:128:in `<top (required)>'
vendor/bundle/ruby/3.3.0/bin/unicorn:25:in `load'
vendor/bundle/ruby/3.3.0/bin/unicorn:25:in `<main>'
This Discourse install is realtively fresh, and I’ve not configured any IP address blocking. I’m also the only user on it. I am running ollama in a Docker container, but that shouldn’t be an issue; I use open-webui (also from another docker container) with the instance and that works fine. I am using the local IP address rather than “localhost”, but “localhost” doesn’t behave any differently.
Appreciate the time you’re putting into help figure out what’s going on here.
ETA: I installed jq in the Discourse docker container, and ran the curl command (substituting my local IP address for localhost), and it did run from there - so there’s connectivity between the containers, and the URL is correct).
هذه هي حماية SSRF الافتراضية الخاصة بنا التي يتم تفعيلها. يمكنك إضافة استثناءات إليها عبر متغير البيئة DISCOURSE_ALLOWED_INTERNAL_HOSTS.
يتم تشغيلها عندما يحاول Discourse الوصول إلى عنوان IP يعتبر داخليًا.
4 إعجابات
رائع، لقد تم الأمر - لقد قمت بذلك عبر الإعدادات بدلاً من متغير البيئة، لكن الاختبار نجح الآن. شكراً مرة أخرى على كل المساعدة!
5 إعجابات
تم تقسيم 3 مشاركات إلى موضوع جديد: كيفية استخدام Ollama مع التضمينات
This topic was automatically closed 30 days after the last reply. New replies are no longer allowed.