Skip to content

AI Endpoints doc: guide to oai instead of using specific model endpoints #8706

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

Draft
RemiSahl wants to merge 11 commits into
base: develop
Choose a base branch
from
Draft

AI Endpoints doc: guide to oai instead of using specific model endpoints #8706

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
e572d23
wip: use oai endpoint by default (structured output guide)
Nov 17, 2025
ff644bc
wip: use oai endpoint by default (function calling guide)
Nov 17, 2025
bef9641
wip: use oai endpoint by default (tuto_01_audio_summarizer)
Nov 17, 2025
c9f4fa0
wip: use oai endpoint by default (tuto_02_voice_virtual_assistant)
Nov 17, 2025
3325212
wip: use oai endpoint by default (tuto_03)
Nov 17, 2025
a9e0a6c
wip: use oai endpoint by default (tuto_05)
Nov 17, 2025
b8333bf
wip: use oai endpoint by default (tuto_06)
Nov 17, 2025
70e90ed
wip: use oai endpoint by default (tuto_07)
Nov 17, 2025
2f64490
wip: use oai endpoint by default (tuto_08)
Nov 17, 2025
787cecf
wip: use oai endpoint by default (tuto_09)
Nov 17, 2025
da3723b
wip: use oai endpoint by default (tuto_10,11,12)
Nov 17, 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
17 changes: 10 additions & 7 deletions ...c_cloud/ai_machine_learning/endpoints_guide_05_structured_output/guide.de-de.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -114,7 +114,7 @@ The following code samples provide a simple example on how to specify a JSON sch
>> # Initialise the client
>> api_key = os.environ['AI_ENDPOINT_API_KEY'] # Assuming your API key is available in this environment variable (export AI_ENDPOINT_API_KEY='your_api_key')
>> openai_client = openai.OpenAI(
>> base_url='https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1',
>> base_url='https://oai.endpoints.kepler.ai.cloud.ovh.net/v1',
>> api_key=api_key
>> )
>>
Expand Down Expand Up @@ -151,7 +151,7 @@ The following code samples provide a simple example on how to specify a JSON sch
>> Input query:
>>
>> ```sh
>> curl -X POST "https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1/chat/completions" \
>> curl -X POST "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/chat/completions" \
>> -H 'accept: application/json'\
>> -H 'content-type: application/json' \
>> -d '{
Expand All @@ -160,6 +160,7 @@ The following code samples provide a simple example on how to specify a JSON sch
>> { "content": "You are a helpful assistant that help users rank different things. You always answer in JSON format.", "role": "system" },
>> { "content": "What are the top 3 most popular programming languages ?", "role": "user" }
>> ],
>> "model": "Meta-Llama-3_3-70B-Instruct",
>> "response_format": {
>> "type":"json_schema",
>> "json_schema": {
Expand Down Expand Up @@ -258,14 +259,15 @@ The following code samples provide a simple example on how to specify a JSON sch
>> // Initialise the client
>> const apiKey = process.env.AI_ENDPOINT_API_KEY; // Assuming your API key is available in this environment variable (export AI_ENDPOINT_API_KEY='your_api_key')
>> const options = {
>> url: 'https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1/chat/completions',
>> url: 'https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/chat/completions',
>> headers: {
>> 'Content-Type': 'application/json',
>> 'Authorization': `Bearer ${apiKey}`
>> },
>> json: true,
>> body: {
>> messages: messages,
>> model: 'Meta-Llama-3_3-70B-Instruct',
>> response_format: {
>> type: 'json_schema',
>> json_schema: jsonSchema
Expand Down Expand Up @@ -327,7 +329,7 @@ The following code samples provide a simple example on how to use the legacy JSO
>> # Initialise the client
>> api_key = os.environ['AI_ENDPOINT_API_KEY'] # Assuming your API key is available in this environment variable (export AI_ENDPOINT_API_KEY='your_api_key')
>> openai_client = openai.OpenAI(
>> base_url='https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1',
>> base_url='https://oai.endpoints.kepler.ai.cloud.ovh.net/v1',
>> api_key=api_key
>> )
>>
Expand Down Expand Up @@ -375,7 +377,7 @@ The following code samples provide a simple example on how to use the legacy JSO
>> Input query:
>>
>> ```sh
>> curl -X POST "https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1/chat/completions" \
>> curl -X POST "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/chat/completions" \
>> -H 'accept: application/json' \
>> -H 'content-type: application/json' \
>> -d '{
Expand Down Expand Up @@ -413,14 +415,15 @@ The following code samples provide a simple example on how to use the legacy JSO
>> // Initialise the client
>> const apiKey = process.env.AI_ENDPOINT_API_KEY; // Assuming your API key is available in this environment variable (export AI_ENDPOINT_API_KEY='your_api_key')
>> const options = {
>> url: 'https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1/chat/completions',
>> url: 'https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/chat/completions',
>> headers: {
>> 'Content-Type': 'application/json',
>> 'Authorization': `Bearer ${apiKey}`
>> },
>> json: true,
>> body: {
>> messages: messages,
>> model: 'Meta-Llama-3_3-70B-Instruct',
>> response_format: {
>> type: 'json_object',
>> },
Expand Down Expand Up @@ -487,7 +490,7 @@ class LanguageRankings(BaseModel):
# Initialise the client
api_key = os.environ['AI_ENDPOINT_API_KEY'] # Assuming your API key is available in this environment variable (export AI_ENDPOINT_API_KEY='your_api_key')
openai_client = openai.OpenAI(
base_url='https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1',
base_url='https://oai.endpoints.kepler.ai.cloud.ovh.net/v1',
api_key=api_key
)

Expand Down
17 changes: 10 additions & 7 deletions ...cloud/ai_machine_learning/endpoints_guide_05_structured_output/guide.en-asia.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -114,7 +114,7 @@ The following code samples provide a simple example on how to specify a JSON sch
>> # Initialise the client
>> api_key = os.environ['AI_ENDPOINT_API_KEY'] # Assuming your API key is available in this environment variable (export AI_ENDPOINT_API_KEY='your_api_key')
>> openai_client = openai.OpenAI(
>> base_url='https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1',
>> base_url='https://oai.endpoints.kepler.ai.cloud.ovh.net/v1',
>> api_key=api_key
>> )
>>
Expand Down Expand Up @@ -151,7 +151,7 @@ The following code samples provide a simple example on how to specify a JSON sch
>> Input query:
>>
>> ```sh
>> curl -X POST "https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1/chat/completions" \
>> curl -X POST "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/chat/completions" \
>> -H 'accept: application/json'\
>> -H 'content-type: application/json' \
>> -d '{
Expand All @@ -160,6 +160,7 @@ The following code samples provide a simple example on how to specify a JSON sch
>> { "content": "You are a helpful assistant that help users rank different things. You always answer in JSON format.", "role": "system" },
>> { "content": "What are the top 3 most popular programming languages ?", "role": "user" }
>> ],
>> "model": "Meta-Llama-3_3-70B-Instruct",
>> "response_format": {
>> "type":"json_schema",
>> "json_schema": {
Expand Down Expand Up @@ -258,14 +259,15 @@ The following code samples provide a simple example on how to specify a JSON sch
>> // Initialise the client
>> const apiKey = process.env.AI_ENDPOINT_API_KEY; // Assuming your API key is available in this environment variable (export AI_ENDPOINT_API_KEY='your_api_key')
>> const options = {
>> url: 'https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1/chat/completions',
>> url: 'https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/chat/completions',
>> headers: {
>> 'Content-Type': 'application/json',
>> 'Authorization': `Bearer ${apiKey}`
>> },
>> json: true,
>> body: {
>> messages: messages,
>> model: 'Meta-Llama-3_3-70B-Instruct',
>> response_format: {
>> type: 'json_schema',
>> json_schema: jsonSchema
Expand Down Expand Up @@ -327,7 +329,7 @@ The following code samples provide a simple example on how to use the legacy JSO
>> # Initialise the client
>> api_key = os.environ['AI_ENDPOINT_API_KEY'] # Assuming your API key is available in this environment variable (export AI_ENDPOINT_API_KEY='your_api_key')
>> openai_client = openai.OpenAI(
>> base_url='https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1',
>> base_url='https://oai.endpoints.kepler.ai.cloud.ovh.net/v1',
>> api_key=api_key
>> )
>>
Expand Down Expand Up @@ -375,7 +377,7 @@ The following code samples provide a simple example on how to use the legacy JSO
>> Input query:
>>
>> ```sh
>> curl -X POST "https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1/chat/completions" \
>> curl -X POST "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/chat/completions" \
>> -H 'accept: application/json' \
>> -H 'content-type: application/json' \
>> -d '{
Expand Down Expand Up @@ -413,14 +415,15 @@ The following code samples provide a simple example on how to use the legacy JSO
>> // Initialise the client
>> const apiKey = process.env.AI_ENDPOINT_API_KEY; // Assuming your API key is available in this environment variable (export AI_ENDPOINT_API_KEY='your_api_key')
>> const options = {
>> url: 'https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1/chat/completions',
>> url: 'https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/chat/completions',
>> headers: {
>> 'Content-Type': 'application/json',
>> 'Authorization': `Bearer ${apiKey}`
>> },
>> json: true,
>> body: {
>> messages: messages,
>> model: 'Meta-Llama-3_3-70B-Instruct',
>> response_format: {
>> type: 'json_object',
>> },
Expand Down Expand Up @@ -487,7 +490,7 @@ class LanguageRankings(BaseModel):
# Initialise the client
api_key = os.environ['AI_ENDPOINT_API_KEY'] # Assuming your API key is available in this environment variable (export AI_ENDPOINT_API_KEY='your_api_key')
openai_client = openai.OpenAI(
base_url='https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1',
base_url='https://oai.endpoints.kepler.ai.cloud.ovh.net/v1',
api_key=api_key
)

Expand Down
17 changes: 10 additions & 7 deletions ...c_cloud/ai_machine_learning/endpoints_guide_05_structured_output/guide.en-au.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -114,7 +114,7 @@ The following code samples provide a simple example on how to specify a JSON sch
>> # Initialise the client
>> api_key = os.environ['AI_ENDPOINT_API_KEY'] # Assuming your API key is available in this environment variable (export AI_ENDPOINT_API_KEY='your_api_key')
>> openai_client = openai.OpenAI(
>> base_url='https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1',
>> base_url='https://oai.endpoints.kepler.ai.cloud.ovh.net/v1',
>> api_key=api_key
>> )
>>
Expand Down Expand Up @@ -151,7 +151,7 @@ The following code samples provide a simple example on how to specify a JSON sch
>> Input query:
>>
>> ```sh
>> curl -X POST "https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1/chat/completions" \
>> curl -X POST "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/chat/completions" \
>> -H 'accept: application/json'\
>> -H 'content-type: application/json' \
>> -d '{
Expand All @@ -160,6 +160,7 @@ The following code samples provide a simple example on how to specify a JSON sch
>> { "content": "You are a helpful assistant that help users rank different things. You always answer in JSON format.", "role": "system" },
>> { "content": "What are the top 3 most popular programming languages ?", "role": "user" }
>> ],
>> "model": "Meta-Llama-3_3-70B-Instruct",
>> "response_format": {
>> "type":"json_schema",
>> "json_schema": {
Expand Down Expand Up @@ -258,14 +259,15 @@ The following code samples provide a simple example on how to specify a JSON sch
>> // Initialise the client
>> const apiKey = process.env.AI_ENDPOINT_API_KEY; // Assuming your API key is available in this environment variable (export AI_ENDPOINT_API_KEY='your_api_key')
>> const options = {
>> url: 'https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1/chat/completions',
>> url: 'https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/chat/completions',
>> headers: {
>> 'Content-Type': 'application/json',
>> 'Authorization': `Bearer ${apiKey}`
>> },
>> json: true,
>> body: {
>> messages: messages,
>> model: 'Meta-Llama-3_3-70B-Instruct',
>> response_format: {
>> type: 'json_schema',
>> json_schema: jsonSchema
Expand Down Expand Up @@ -327,7 +329,7 @@ The following code samples provide a simple example on how to use the legacy JSO
>> # Initialise the client
>> api_key = os.environ['AI_ENDPOINT_API_KEY'] # Assuming your API key is available in this environment variable (export AI_ENDPOINT_API_KEY='your_api_key')
>> openai_client = openai.OpenAI(
>> base_url='https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1',
>> base_url='https://oai.endpoints.kepler.ai.cloud.ovh.net/v1',
>> api_key=api_key
>> )
>>
Expand Down Expand Up @@ -375,7 +377,7 @@ The following code samples provide a simple example on how to use the legacy JSO
>> Input query:
>>
>> ```sh
>> curl -X POST "https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1/chat/completions" \
>> curl -X POST "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/chat/completions" \
>> -H 'accept: application/json' \
>> -H 'content-type: application/json' \
>> -d '{
Expand Down Expand Up @@ -413,14 +415,15 @@ The following code samples provide a simple example on how to use the legacy JSO
>> // Initialise the client
>> const apiKey = process.env.AI_ENDPOINT_API_KEY; // Assuming your API key is available in this environment variable (export AI_ENDPOINT_API_KEY='your_api_key')
>> const options = {
>> url: 'https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1/chat/completions',
>> url: 'https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/chat/completions',
>> headers: {
>> 'Content-Type': 'application/json',
>> 'Authorization': `Bearer ${apiKey}`
>> },
>> json: true,
>> body: {
>> messages: messages,
>> model: 'Meta-Llama-3_3-70B-Instruct',
>> response_format: {
>> type: 'json_object',
>> },
Expand Down Expand Up @@ -487,7 +490,7 @@ class LanguageRankings(BaseModel):
# Initialise the client
api_key = os.environ['AI_ENDPOINT_API_KEY'] # Assuming your API key is available in this environment variable (export AI_ENDPOINT_API_KEY='your_api_key')
openai_client = openai.OpenAI(
base_url='https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1',
base_url='https://oai.endpoints.kepler.ai.cloud.ovh.net/v1',
api_key=api_key
)

Expand Down
17 changes: 10 additions & 7 deletions ...c_cloud/ai_machine_learning/endpoints_guide_05_structured_output/guide.en-ca.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -114,7 +114,7 @@ The following code samples provide a simple example on how to specify a JSON sch
>> # Initialise the client
>> api_key = os.environ['AI_ENDPOINT_API_KEY'] # Assuming your API key is available in this environment variable (export AI_ENDPOINT_API_KEY='your_api_key')
>> openai_client = openai.OpenAI(
>> base_url='https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1',
>> base_url='https://oai.endpoints.kepler.ai.cloud.ovh.net/v1',
>> api_key=api_key
>> )
>>
Expand Down Expand Up @@ -151,7 +151,7 @@ The following code samples provide a simple example on how to specify a JSON sch
>> Input query:
>>
>> ```sh
>> curl -X POST "https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1/chat/completions" \
>> curl -X POST "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/chat/completions" \
>> -H 'accept: application/json'\
>> -H 'content-type: application/json' \
>> -d '{
Expand All @@ -160,6 +160,7 @@ The following code samples provide a simple example on how to specify a JSON sch
>> { "content": "You are a helpful assistant that help users rank different things. You always answer in JSON format.", "role": "system" },
>> { "content": "What are the top 3 most popular programming languages ?", "role": "user" }
>> ],
>> "model": "Meta-Llama-3_3-70B-Instruct",
>> "response_format": {
>> "type":"json_schema",
>> "json_schema": {
Expand Down Expand Up @@ -258,14 +259,15 @@ The following code samples provide a simple example on how to specify a JSON sch
>> // Initialise the client
>> const apiKey = process.env.AI_ENDPOINT_API_KEY; // Assuming your API key is available in this environment variable (export AI_ENDPOINT_API_KEY='your_api_key')
>> const options = {
>> url: 'https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1/chat/completions',
>> url: 'https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/chat/completions',
>> headers: {
>> 'Content-Type': 'application/json',
>> 'Authorization': `Bearer ${apiKey}`
>> },
>> json: true,
>> body: {
>> messages: messages,
>> model: 'Meta-Llama-3_3-70B-Instruct',
>> response_format: {
>> type: 'json_schema',
>> json_schema: jsonSchema
Expand Down Expand Up @@ -327,7 +329,7 @@ The following code samples provide a simple example on how to use the legacy JSO
>> # Initialise the client
>> api_key = os.environ['AI_ENDPOINT_API_KEY'] # Assuming your API key is available in this environment variable (export AI_ENDPOINT_API_KEY='your_api_key')
>> openai_client = openai.OpenAI(
>> base_url='https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1',
>> base_url='https://oai.endpoints.kepler.ai.cloud.ovh.net/v1',
>> api_key=api_key
>> )
>>
Expand Down Expand Up @@ -375,7 +377,7 @@ The following code samples provide a simple example on how to use the legacy JSO
>> Input query:
>>
>> ```sh
>> curl -X POST "https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1/chat/completions" \
>> curl -X POST "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/chat/completions" \
>> -H 'accept: application/json' \
>> -H 'content-type: application/json' \
>> -d '{
Expand Down Expand Up @@ -413,14 +415,15 @@ The following code samples provide a simple example on how to use the legacy JSO
>> // Initialise the client
>> const apiKey = process.env.AI_ENDPOINT_API_KEY; // Assuming your API key is available in this environment variable (export AI_ENDPOINT_API_KEY='your_api_key')
>> const options = {
>> url: 'https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1/chat/completions',
>> url: 'https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/chat/completions',
>> headers: {
>> 'Content-Type': 'application/json',
>> 'Authorization': `Bearer ${apiKey}`
>> },
>> json: true,
>> body: {
>> messages: messages,
>> model: 'Meta-Llama-3_3-70B-Instruct',
>> response_format: {
>> type: 'json_object',
>> },
Expand Down Expand Up @@ -487,7 +490,7 @@ class LanguageRankings(BaseModel):
# Initialise the client
api_key = os.environ['AI_ENDPOINT_API_KEY'] # Assuming your API key is available in this environment variable (export AI_ENDPOINT_API_KEY='your_api_key')
openai_client = openai.OpenAI(
base_url='https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1',
base_url='https://oai.endpoints.kepler.ai.cloud.ovh.net/v1',
api_key=api_key
)

Expand Down
Loading