diff --git a/hub/.doctrees/docs/unify/unify.doctree b/hub/.doctrees/docs/unify/unify.doctree index 99eb93c3e3..97184256b6 100644 Binary files a/hub/.doctrees/docs/unify/unify.doctree and b/hub/.doctrees/docs/unify/unify.doctree differ diff --git a/hub/.doctrees/docs/unify/unify/unify.tests.doctree b/hub/.doctrees/docs/unify/unify/unify.tests.doctree deleted file mode 100644 index a85bd87b62..0000000000 Binary files a/hub/.doctrees/docs/unify/unify/unify.tests.doctree and /dev/null differ diff --git a/hub/.doctrees/docs/unify/unify/unify.utils.doctree b/hub/.doctrees/docs/unify/unify/unify.utils.doctree index f0a1641b13..7e6765862f 100644 Binary files a/hub/.doctrees/docs/unify/unify/unify.utils.doctree and b/hub/.doctrees/docs/unify/unify/unify.utils.doctree differ diff --git a/hub/.doctrees/environment.pickle b/hub/.doctrees/environment.pickle index c0946d09f3..f91ca987b3 100644 Binary files a/hub/.doctrees/environment.pickle and b/hub/.doctrees/environment.pickle differ diff --git a/hub/.doctrees/home/home.doctree b/hub/.doctrees/home/home.doctree index c6e7a61af7..9831307bd7 100644 Binary files a/hub/.doctrees/home/home.doctree and b/hub/.doctrees/home/home.doctree differ diff --git a/hub/.doctrees/index.doctree b/hub/.doctrees/index.doctree index c7a1218fe5..c53c1f420b 100644 Binary files a/hub/.doctrees/index.doctree and b/hub/.doctrees/index.doctree differ diff --git a/hub/_sources/docs/unify/unify.rst.txt b/hub/_sources/docs/unify/unify.rst.txt index 0090e600b4..d15fdb1fc1 100644 --- a/hub/_sources/docs/unify/unify.rst.txt +++ b/hub/_sources/docs/unify/unify.rst.txt @@ -9,6 +9,5 @@ unify.chat unify.clients unify.exceptions - unify.tests unify.utils diff --git a/hub/_sources/docs/unify/unify/unify.tests.rst.txt b/hub/_sources/docs/unify/unify/unify.tests.rst.txt deleted file mode 100644 index 33bf2466c4..0000000000 --- a/hub/_sources/docs/unify/unify/unify.tests.rst.txt +++ /dev/null @@ -1,16 +0,0 @@ -Tests -===== - - - - -.. automodule:: unify.tests - :members: - :special-members: __init__ - :undoc-members: - :show-inheritance: - - - - -.. discussion-links:: unify.tests \ No newline at end of file diff --git a/hub/_sources/home/home.rst.txt b/hub/_sources/home/home.rst.txt index 39f3ae145c..32369b9ca4 100644 --- a/hub/_sources/home/home.rst.txt +++ b/hub/_sources/home/home.rst.txt @@ -1,13 +1,15 @@ Welcome to Unify! ================= -Unify is your centralized platform for LLM endpoints. If you’re using or planning to use an LLM in your application or service, Unify lets you: +We're on a mission to unify and simplify the LLM landscape. Unify lets you: -* **πŸš€ Route to the best endpoints**: Send each prompt to the endpoint(s) that will (a) return the best response, and (b) yield the best performance for a target metric of your choice, including high-throughput, low cost or low latency. +* **πŸ”‘ Use any LLM from any Provider**: With a single interface, you can use all LLMs from all providers by simply changing one string. +No need to manage several API keys or handle different input-output formats. Unify handles all of that for you! -* **βš–οΈ Benchmark endpoint performance**: Objectively compare endpoints speed, latency and costs with our dynamic benchmarks to make informed decisions when selecting a model or provider. +* **πŸ“Š Improve LLM Performance**: Add your own custom tests and evals, and benchmark your own prompts on all models and providers. +Comparing quality, cost and speed, and iterate on your system prompt until all test cases pass, and you can deploy your app! -* **πŸ”‘ Use any endpoint with a single key**: Access the latest LLMs through any endpoint provider with a single API Key to. Each model has a unfied API that enables seamless provider switching without needing to refactor your code. +* **πŸ”€ Route to the Best LLM**: Improve quality, cost and speed by routing to the perfect model and provider for each individual prompt. Getting Started --------------- diff --git a/hub/concepts/benchmarks.html b/hub/concepts/benchmarks.html index b8ddd0b9b0..0c5e73fd79 100644 --- a/hub/concepts/benchmarks.html +++ b/hub/concepts/benchmarks.html @@ -258,7 +258,6 @@
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    @@ -476,7 +475,6 @@

    How does it work?Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    diff --git a/hub/concepts/deploy_router.html b/hub/concepts/deploy_router.html index febf98d823..3d11f30d6f 100644 --- a/hub/concepts/deploy_router.html +++ b/hub/concepts/deploy_router.html @@ -258,7 +258,6 @@
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    @@ -525,7 +524,6 @@

    Round Up
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    diff --git a/hub/concepts/first_request.html b/hub/concepts/first_request.html index ae97cbba3d..dd205a091b 100644 --- a/hub/concepts/first_request.html +++ b/hub/concepts/first_request.html @@ -258,7 +258,6 @@
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    @@ -589,7 +588,6 @@

    Round Up
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    diff --git a/hub/concepts/images.html b/hub/concepts/images.html index b0aef378bd..a3dfe9759b 100644 --- a/hub/concepts/images.html +++ b/hub/concepts/images.html @@ -258,7 +258,6 @@
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    @@ -414,7 +413,6 @@

    On-Prem ImagesChat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    diff --git a/hub/concepts/reference.html b/hub/concepts/reference.html index 82239753fb..32cd751a81 100644 --- a/hub/concepts/reference.html +++ b/hub/concepts/reference.html @@ -258,7 +258,6 @@
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    @@ -565,7 +564,6 @@

    POST /chat/completionsChat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    diff --git a/hub/concepts/router.html b/hub/concepts/router.html index ff44e401ab..69d3c0760b 100644 --- a/hub/concepts/router.html +++ b/hub/concepts/router.html @@ -258,7 +258,6 @@
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    @@ -510,7 +509,6 @@

    Training a router (beta)Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    diff --git a/hub/concepts/unify_api.html b/hub/concepts/unify_api.html index 531b7f52a9..c6b1b5ca59 100644 --- a/hub/concepts/unify_api.html +++ b/hub/concepts/unify_api.html @@ -258,7 +258,6 @@
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    @@ -624,7 +623,6 @@

    LLM FallbacksChat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    diff --git a/hub/console/building_router.html b/hub/console/building_router.html index 51bf9c5e4e..71b9342ec9 100644 --- a/hub/console/building_router.html +++ b/hub/console/building_router.html @@ -258,7 +258,6 @@
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    @@ -516,7 +515,6 @@

    Round Up
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    diff --git a/hub/console/connecting_stack.html b/hub/console/connecting_stack.html index 0b55ddbae4..c5d54df49d 100644 --- a/hub/console/connecting_stack.html +++ b/hub/console/connecting_stack.html @@ -258,7 +258,6 @@
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    @@ -482,7 +481,6 @@

    Round Up
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    diff --git a/hub/console/running_benchmarks.html b/hub/console/running_benchmarks.html index 034a4f8482..f533e86807 100644 --- a/hub/console/running_benchmarks.html +++ b/hub/console/running_benchmarks.html @@ -258,7 +258,6 @@
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    @@ -530,7 +529,6 @@

    Round Up
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    diff --git a/hub/docs/unify/unify.html b/hub/docs/unify/unify.html index 5a346cec23..d2c9bf1092 100644 --- a/hub/docs/unify/unify.html +++ b/hub/docs/unify/unify.html @@ -258,7 +258,6 @@
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    @@ -337,10 +336,7 @@

    unify.exceptions

    -

    unify.tests

    -

    - -

    unify.utils

    +

    unify.utils

    @@ -447,7 +443,6 @@
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    diff --git a/hub/docs/unify/unify/unify.chat.html b/hub/docs/unify/unify/unify.chat.html index e02e6afeab..c2b56ace66 100644 --- a/hub/docs/unify/unify/unify.chat.html +++ b/hub/docs/unify/unify/unify.chat.html @@ -258,7 +258,6 @@
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    @@ -644,7 +643,6 @@
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    diff --git a/hub/docs/unify/unify/unify.clients.html b/hub/docs/unify/unify/unify.clients.html index 09f85dc469..60d1bf941e 100644 --- a/hub/docs/unify/unify/unify.clients.html +++ b/hub/docs/unify/unify/unify.clients.html @@ -258,7 +258,6 @@
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    @@ -826,7 +825,6 @@
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    diff --git a/hub/docs/unify/unify/unify.exceptions.html b/hub/docs/unify/unify/unify.exceptions.html index 21eca10f01..689e5ada4a 100644 --- a/hub/docs/unify/unify/unify.exceptions.html +++ b/hub/docs/unify/unify/unify.exceptions.html @@ -62,7 +62,7 @@ - + @@ -258,7 +258,6 @@
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    @@ -416,11 +415,11 @@

    next

    -

    Tests

    +

    Utils

     @@ -520,7 +519,6 @@
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    diff --git a/hub/docs/unify/unify/unify.tests.html b/hub/docs/unify/unify/unify.tests.html deleted file mode 100644 index f5c595bb89..0000000000 --- a/hub/docs/unify/unify/unify.tests.html +++ /dev/null @@ -1,677 +0,0 @@ - - - - - - - - - - - Tests — Unify Documentation - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    - - - - - - - - - - -
    -
    -
    -
    - - - Ctrl+K -
    -
    - -
    -
    - - -
    -
    - - - -
    - - - -
    - - -
    - -
    -
    - -
    - - - -
    - -
    - -
    - -
    - -
    - -
    -
    -
    - - -
    -
    - - - - -
    - -
    - - -
    -
    - -
    -
    - -
    - -
    - - - - -
    - -
    - - -
    -
    - - - - - -
    - -
    -

    Tests#

    -
    -
    -class unify.tests.TestAsyncUnify(methodName='runTest')#
    -

    Bases: IsolatedAsyncioTestCase

    -
    -
    -setUp()#
    -

    Hook method for setting up the test fixture before exercising it.

    -
    -
    Return type:
    -

    None

    -
    -
    -
    - -
    -
    -async test_generate_returns_generator_when_stream_true()#
    -
    -
    Return type:
    -

    None

    -
    -
    -
    - -
    -
    -async test_generate_returns_string_when_stream_false()#
    -
    -
    Return type:
    -

    None

    -
    -
    -
    - -
    -
    -async test_incorrect_model_name_raises_internal_server_error()#
    -
    -
    Return type:
    -

    None

    -
    -
    -
    - -
    -
    -async test_invalid_api_key_raises_authentication_error()#
    -
    -
    Return type:
    -

    None

    -
    -
    -
    - -
    -
    -async test_missing_api_key_raises_key_error(mock_get)#
    -
    -
    Return type:
    -

    None

    -
    -
    -
    - -
    - -
    -
    -class unify.tests.TestUnify(methodName='runTest')#
    -

    Bases: TestCase

    -
    -
    -setUp()#
    -

    Hook method for setting up the test fixture before exercising it.

    -
    -
    Return type:
    -

    None

    -
    -
    -
    - -
    -
    -test_generate_returns_generator_when_stream_true()#
    -
    -
    Return type:
    -

    None

    -
    -
    -
    - -
    -
    -test_generate_returns_string_when_stream_false()#
    -
    -
    Return type:
    -

    None

    -
    -
    -
    - -
    -
    -test_incorrect_model_name_raises_internal_server_error()#
    -
    -
    Return type:
    -

    None

    -
    -
    -
    - -
    -
    -test_invalid_api_key_raises_authentication_error()#
    -
    -
    Return type:
    -

    None

    -
    -
    -
    - -
    -
    -test_missing_api_key_raises_key_error(mock_get)#
    -
    -
    Return type:
    -

    None

    -
    -
    -
    - -
    - -
    - - -
    - - - - - - - -
    - - - -
    - - -
    -
    - On this page -
    -
    - -
    - - -
    -
    - -
    - -
    -
    -
    - - - - - - - - - \ No newline at end of file diff --git a/hub/docs/unify/unify/unify.utils.html b/hub/docs/unify/unify/unify.utils.html index e88bee5baa..5f443d3fa8 100644 --- a/hub/docs/unify/unify/unify.utils.html +++ b/hub/docs/unify/unify/unify.utils.html @@ -63,7 +63,7 @@ - + @@ -258,7 +258,6 @@
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    @@ -442,18 +441,18 @@
    -unify.utils.list_endpoints(model)#
    -

    Get a list of endpoints for a specific model.

    +unify.utils.list_endpoints(model=None, provider=None)# +

    Get a list of available endpoints, either in total or for a specific model or provider.

    Return type:

    List[str]

    -
    Args:

    model (str): The name of the model.

    +
    Args:

    model (str): If specified, returns the list of endpoints supporting this model. +provider (str): If specified, returns the list of endpoints supporting this provider.

    -
    Returns:

    List[str]: A list of endpoint names associated with the model if successful, -otherwise an empty list.

    +
    Returns:

    List[str]: A list of endpoint names if successful, otherwise an empty list.

    Raises:

    BadRequestError: If there was an HTTP error. ValueError: If there was an error parsing the JSON response.

    @@ -485,14 +484,16 @@
    -unify.utils.list_models()#
    -

    Get a list of available models.

    +unify.utils.list_models(provider=None)# +

    Get a list of available models, either in total or for a specific provider.

    Return type:

    List[str]

    +
    Args:

    provider (str): If specified, returns the list of models supporting this provider.

    +
    Returns:

    List[str]: A list of available model names if successful, otherwise an empty list.

    Raises:

    BadRequestError: If there was an HTTP error. @@ -503,15 +504,15 @@

    -unify.utils.list_providers(model)#
    -

    Get a list of providers for a specific model.

    +unify.utils.list_providers(model=None)# +

    Get a list of available providers, either in total or for a specific model.

    Return type:

    List[str]

    -
    Args:

    model (str): The name of the model.

    +
    Args:

    model (str): If specified, returns the list of providers supporting this model.

    Returns:

    List[str]: A list of provider names associated with the model if successful, otherwise an empty list.

    @@ -580,12 +581,12 @@

    previous

    -

    Tests

    +

    Exceptions

     Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    diff --git a/hub/genindex.html b/hub/genindex.html index 31cb2123d0..4758bb8705 100644 --- a/hub/genindex.html +++ b/hub/genindex.html @@ -257,7 +257,6 @@
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    @@ -317,7 +316,6 @@

    Index

    | P | R | S - | T | U
    @@ -469,8 +467,6 @@

    M

  • unify.clients
  • unify.exceptions -
    • -
  • unify.tests
  • unify.utils
    • @@ -543,59 +539,11 @@

    S

  • (unify.clients.AsyncUnify method)
  • (unify.clients.Unify method) -
    • - -
  • setUp() (unify.tests.TestAsyncUnify method) - -
    • -

    T

    - - - -
    -

    U

    - - -
      @@ -625,13 +573,6 @@

      U

    Console

    @@ -328,11 +327,17 @@

    Welcome to Unify!#

    -

    Unify is your centralized platform for LLM endpoints. If you’re using or planning to use an LLM in your application or service, Unify lets you:

    +

    We’re on a mission to unify and simplify the LLM landscape. Unify lets you:

      -

    • πŸš€ Route to the best endpoints: Send each prompt to the endpoint(s) that will (a) return the best response, and (b) yield the best performance for a target metric of your choice, including high-throughput, low cost or low latency.

      • -

    • βš–οΈ Benchmark endpoint performance: Objectively compare endpoints speed, latency and costs with our dynamic benchmarks to make informed decisions when selecting a model or provider.

      • -

    • πŸ”‘ Use any endpoint with a single key: Access the latest LLMs through any endpoint provider with a single API Key to. Each model has a unfied API that enables seamless provider switching without needing to refactor your code.

      • +

    • πŸ”‘ Use any LLM from any Provider: With a single interface, you can use all LLMs from all providers by simply changing one string.

      • +
    +

    No need to manage several API keys or handle different input-output formats. Unify handles all of that for you!

    +
      +

    • πŸ“Š Improve LLM Performance: Add your own custom tests and evals, and benchmark your own prompts on all models and providers.

      • +
    +

    Comparing quality, cost and speed, and iterate on your system prompt until all test cases pass, and you can deploy your app!

    +
      +

    • πŸ”€ Route to the Best LLM: Improve quality, cost and speed by routing to the perfect model and provider for each individual prompt.

    Getting Started#

    @@ -446,7 +451,6 @@

    Getting StartedChat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    diff --git a/hub/index.html b/hub/index.html index ba9a254696..6f9bf201e8 100644 --- a/hub/index.html +++ b/hub/index.html @@ -259,7 +259,6 @@
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    @@ -303,11 +302,17 @@

    Welcome to Unify!#

    -

    Unify is your centralized platform for LLM endpoints. If you’re using or planning to use an LLM in your application or service, Unify lets you:

    +

    We’re on a mission to unify and simplify the LLM landscape. Unify lets you:

      -

    • πŸš€ Route to the best endpoints: Send each prompt to the endpoint(s) that will (a) return the best response, and (b) yield the best performance for a target metric of your choice, including high-throughput, low cost or low latency.

      • -

    • βš–οΈ Benchmark endpoint performance: Objectively compare endpoints speed, latency and costs with our dynamic benchmarks to make informed decisions when selecting a model or provider.

      • -

    • πŸ”‘ Use any endpoint with a single key: Access the latest LLMs through any endpoint provider with a single API Key to. Each model has a unfied API that enables seamless provider switching without needing to refactor your code.

      • +

    • πŸ”‘ Use any LLM from any Provider: With a single interface, you can use all LLMs from all providers by simply changing one string.

      • +
    +

    No need to manage several API keys or handle different input-output formats. Unify handles all of that for you!

    +
      +

    • πŸ“Š Improve LLM Performance: Add your own custom tests and evals, and benchmark your own prompts on all models and providers.

      • +
    +

    Comparing quality, cost and speed, and iterate on your system prompt until all test cases pass, and you can deploy your app!

    +
      +

    • πŸ”€ Route to the Best LLM: Improve quality, cost and speed by routing to the perfect model and provider for each individual prompt.

    Getting Started#

    @@ -440,7 +445,6 @@

    Getting StartedChat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    diff --git a/hub/objects.inv b/hub/objects.inv index 0c2f413477..a8d1b7f0b3 100644 Binary files a/hub/objects.inv and b/hub/objects.inv differ diff --git a/hub/on_prem/on_prem_access.html b/hub/on_prem/on_prem_access.html index fcf1ded587..a69ed731d9 100644 --- a/hub/on_prem/on_prem_access.html +++ b/hub/on_prem/on_prem_access.html @@ -258,7 +258,6 @@
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    @@ -432,7 +431,6 @@

    On-Prem accessChat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    diff --git a/hub/on_prem/sso.html b/hub/on_prem/sso.html index f777473e27..001c9ada02 100644 --- a/hub/on_prem/sso.html +++ b/hub/on_prem/sso.html @@ -257,7 +257,6 @@
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    @@ -489,7 +488,6 @@

    SSO (Single Sign On)Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    diff --git a/hub/py-modindex.html b/hub/py-modindex.html index 01177d214f..3d88a2bc05 100644 --- a/hub/py-modindex.html +++ b/hub/py-modindex.html @@ -260,7 +260,6 @@
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    @@ -334,11 +333,6 @@

    Python Module Index

    		    unify.exceptions
        - unify.tests -
        @@ -429,7 +423,6 @@

    Python Module Index

  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    diff --git a/hub/search.html b/hub/search.html index 54866807df..181fb9f27a 100644 --- a/hub/search.html +++ b/hub/search.html @@ -259,7 +259,6 @@
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    @@ -413,7 +412,6 @@

    Search

  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    diff --git a/hub/searchindex.js b/hub/searchindex.js index 241326b653..22a764189d 100644 --- a/hub/searchindex.js +++ b/hub/searchindex.js @@ -1 +1 @@ -Search.setIndex({"docnames": ["concepts/benchmarks", "concepts/deploy_router", "concepts/first_request", "concepts/images", "concepts/reference", "concepts/router", "concepts/unify_api", "console/building_router", "console/connecting_stack", "console/running_benchmarks", "docs/unify/unify", "docs/unify/unify/unify.chat", "docs/unify/unify/unify.clients", "docs/unify/unify/unify.exceptions", "docs/unify/unify/unify.tests", "docs/unify/unify/unify.utils", "home/home", "index", "on_prem/on_prem_access", "on_prem/sso", "tools/openapi", "tools/python_library"], "filenames": ["concepts/benchmarks.rst", "concepts/deploy_router.rst", "concepts/first_request.rst", "concepts/images.rst", "concepts/reference.rst", "concepts/router.rst", "concepts/unify_api.rst", "console/building_router.rst", "console/connecting_stack.rst", "console/running_benchmarks.rst", "docs/unify/unify.rst", "docs/unify/unify/unify.chat.rst", "docs/unify/unify/unify.clients.rst", "docs/unify/unify/unify.exceptions.rst", "docs/unify/unify/unify.tests.rst", "docs/unify/unify/unify.utils.rst", "home/home.rst", "index.rst", "on_prem/on_prem_access.rst", "on_prem/sso.rst", "tools/openapi.rst", "tools/python_library.rst"], "titles": ["Benchmarking", "Deploying a router", "Making your first request", "On-Prem Images", "API Reference", "Routing", "Universal API", "Building a custom router", "Connecting your stack", "Benchmarking endpoints", "<no title>", "Chat", "Clients", "Exceptions", "Tests", "Utils", "Welcome to Unify!", "Home", "On-Prem access", "SSO (Single Sign On)", "OpenAPI Specification", "Python Library"], "terms": {"when": [0, 1, 2, 4, 5, 7, 12, 16, 17], "compar": [0, 9, 16, 17], "llm": [0, 1, 2, 8, 9, 11, 16, 17], "i": [0, 1, 2, 4, 6, 7, 8, 9, 11, 12, 15, 16, 17, 19], "constant": 0, "tradeoff": 0, "make": [0, 1, 4, 7, 12, 16, 17], "between": [0, 2, 5, 6, 7, 12], "qualiti": [0, 5, 7], "cost": [0, 1, 5, 6, 7, 9, 16, 17], "latenc": [0, 1, 5, 7, 9, 16, 17], "stronger": 0, "model": [0, 1, 4, 5, 6, 7, 8, 9, 11, 12, 15, 16, 17, 19], "ar": [0, 1, 2, 5, 6, 7, 8, 9, 16, 17], "gener": [0, 1, 2, 4, 5, 6, 12, 19], "slower": 0, "more": [0, 2, 5, 9, 12], "expens": 0, "sometim": [0, 6], "overkil": 0, "task": [0, 1, 5, 7, 9], "hand": [0, 9], "complic": 0, "matter": 0, "further": [0, 7, 12], "new": [0, 2, 5, 6, 7, 8, 9], "releas": [0, 5], "weekli": 0, "each": [0, 1, 5, 6, 7, 9, 15, 16, 17], "claim": 0, "state": 0, "art": 0, "data": [0, 1, 7], "let": [0, 1, 2, 7, 8, 9, 16, 17], "you": [0, 1, 2, 4, 5, 6, 7, 8, 9, 16, 17, 19], "see": [0, 6, 7, 9, 16, 17], "differ": [0, 4, 5, 7, 9], "perform": [0, 1, 7, 9, 16, 17], "can": [0, 1, 2, 4, 5, 6, 7, 8, 9, 16, 17, 19], "relat": 0, "live": [0, 5, 6], "stat": 0, "pull": [0, 19], "from": [0, 1, 2, 4, 5, 6, 7, 9, 11, 12, 15, 16, 17, 19], "our": [0, 1, 2, 6, 7, 8, 9, 16, 17, 18, 19], "runtim": [0, 5, 6], "come": [0, 4, 5, 6], "out": [0, 2, 5, 6], "simpli": [0, 2, 9], "re": [0, 7, 9, 16, 17, 19], "run": [0, 2, 6, 7, 8, 11, 19], "thei": [0, 5, 6], "first": [0, 1, 4, 5, 6, 7, 9, 16, 17], "creat": [0, 2, 4, 6, 7, 8], "which": [0, 4, 5, 6, 7, 9, 19], "repres": [0, 11], "want": [0, 1, 2, 7, 8, 9], "evalu": [0, 9, 15], "need": [0, 1, 2, 5, 6, 7, 8, 9, 16, 17], "list": [0, 2, 6, 7, 9, 12, 15], "prompt": [0, 1, 5, 6, 8, 9, 12, 15, 16, 17], "option": [0, 1, 5, 7, 8, 11, 12, 15], "includ": [0, 1, 7, 8, 9, 16, 17], "refer": [0, 5, 8], "gold": 0, "standard": [0, 6, 8], "answer": [0, 5, 8], "contain": [0, 2, 5, 6, 8, 9, 12, 15], "tend": [0, 9], "get": [0, 1, 5, 6, 11, 12, 15, 18], "accur": 0, "The": [0, 2, 4, 5, 6, 7, 8, 9, 11, 12, 15, 16, 17, 19], "file": [0, 2, 5, 8, 15, 19], "itself": 0, "should": [0, 2, 6, 8, 9, 19], "jsonl": [0, 5, 8], "format": [0, 4, 5, 6, 11, 12], "one": [0, 1, 2, 4, 5, 6, 8, 9], "entri": [0, 5], "per": [0, 1, 7], "line": [0, 2], "exampl": [0, 1, 2, 4, 5, 6, 7, 8], "below": [0, 1, 2, 7, 8, 9], "thi": [0, 1, 2, 4, 5, 6, 7, 8, 9, 16, 17, 19], "ref_answ": [0, 5], "second": [0, 1, 7], "us": [0, 4, 5, 6, 7, 8, 9, 11, 12, 15, 16, 17, 19], "least": [0, 9], "50": 0, "most": [0, 5, 8], "result": [0, 5, 7, 8, 9], "current": [0, 1, 4, 6, 7, 9, 16, 17], "an": [0, 1, 5, 6, 7, 8, 11, 12, 15, 16, 17], "maximum": 0, "limit": [0, 2, 5, 6], "500": [0, 13], "we": [0, 1, 2, 5, 6, 7, 8, 9, 16, 17], "don": [0, 4, 7], "t": [0, 1, 2, 4, 5, 7, 9], "much": [0, 1, 5], "extra": 0, "detail": [0, 1, 2, 4, 6, 7, 19], "past": 0, "250": 0, "In": [0, 1, 2, 5, 6, 7, 8, 9, 16, 17], "dashboard": [0, 5, 7, 9], "click": [0, 5, 7, 8, 9], "select": [0, 5, 7, 9, 16, 17], "open": [0, 7, 9], "interfac": [0, 1, 2, 5, 6, 8, 9, 16, 17], "upload": [0, 2, 5, 7, 8, 9, 15], "finish": [0, 5], "ll": [0, 1, 2, 5, 7, 8, 9, 16, 17], "receiv": [0, 5, 7], "email": [0, 5, 7], "graph": [0, 5, 7, 9], "displai": [0, 5, 7, 9], "x": [0, 2, 4, 6, 7, 9, 19], "axi": [0, 9], "set": [0, 1, 2, 6, 7, 8, 11, 12, 14], "time": [0, 1, 5, 6, 7, 9], "token": [0, 1, 5, 6, 7, 9, 12], "inter": [0, 1, 5, 7], "either": [0, 6, 7, 16, 17], "linear": 0, "log": 0, "scale": 0, "gpt4o": 0, "judg": 0, "cf": 0, "http": [0, 2, 4, 12, 13, 15, 19], "arxiv": 0, "org": 0, "ab": 0, "2306": 0, "05685": 0, "": [0, 1, 2, 5, 6, 7, 8, 9, 12, 16, 17, 19], "respons": [0, 1, 2, 4, 5, 6, 12, 15, 16, 17, 19], "section": [1, 2, 7, 8, 9, 16, 17], "learn": [1, 2, 4, 5, 7, 8, 9, 16, 17], "how": [1, 2, 5, 6, 7, 8, 9, 16, 17], "unifi": [1, 2, 4, 7, 8, 11, 12, 13, 14, 15, 19], "through": [1, 2, 6, 7, 8, 9, 16, 17], "api": [1, 5, 7, 8, 11, 12, 15, 16, 17, 19], "If": [1, 2, 4, 6, 7, 8, 9, 11, 12, 15, 16, 17], "haven": [1, 2, 9], "done": [1, 2, 7, 9], "so": [1, 2, 6, 7, 8, 9, 16, 17], "recommend": [1, 2, 9, 16, 17], "request": [1, 4, 7, 9, 13, 16, 17, 19], "familiar": [1, 16, 17], "leverag": 1, "inform": [1, 7, 9, 16, 17], "benchmark": [1, 2, 5, 6, 7, 8, 16, 17], "automat": [1, 6, 7], "rout": [1, 2, 7, 8, 16, 17], "best": [1, 5, 7, 16, 17], "provid": [1, 4, 5, 6, 7, 8, 9, 11, 12, 15, 16, 17], "choos": [1, 2, 5, 7], "valu": [1, 9, 11, 12, 15], "chang": [1, 5, 7, 9], "over": [1, 5, 9], "dynam": [1, 16, 17], "ensur": [1, 7, 9], "alwai": [1, 9], "without": [1, 16, 17], "have": [1, 2, 4, 5, 6, 7, 8, 9, 19], "monitor": 1, "yourself": 1, "To": [1, 2, 4, 5, 6, 9, 18], "onli": [1, 2, 6, 7, 9, 16, 17], "provier": 1, "name": [1, 2, 4, 6, 7, 8, 9, 11, 12, 15], "support": [1, 2, 6], "configur": [1, 2, 5, 7, 9], "follow": [1, 4, 5, 6], "config": 1, "lowest": 1, "input": [1, 4], "output": [1, 6, 9, 12], "itl": 1, "ttft": [1, 9], "highest": 1, "tk": 1, "sec": [1, 9], "For": [1, 2, 5, 7, 8, 9], "e": [1, 2, 5, 7, 9], "g": [1, 2, 7, 9], "python": [1, 19], "packag": 1, "endpoint": [1, 4, 7, 11, 12, 15, 16, 17], "import": [1, 2, 6, 19], "o": [1, 2], "assum": [1, 2, 7, 8], "ad": [1, 2, 9], "unify_kei": [1, 2, 11, 12, 15], "your": [1, 4, 5, 6, 12, 16, 17, 19], "environ": [1, 2, 7, 11, 12, 15, 16, 17], "variabl": [1, 2, 11, 12, 15], "otherwis": [1, 2, 12, 15], "would": [1, 2, 6, 7, 8, 9], "specifi": [1, 2, 4, 5, 6, 7, 8, 9, 15], "api_kei": [1, 2, 6, 11, 12, 15, 19], "argument": [1, 2, 4], "mistral": [1, 2, 6, 9], "7b": [1, 2, 6, 9], "instruct": [1, 2, 6, 9], "v0": [1, 2, 4, 6, 9], "3": [1, 2, 4, 6, 7, 9, 19], "explain": [1, 2, 4, 9, 16, 17, 19], "who": [1, 2, 4, 19], "newton": [1, 2, 4, 19], "wa": [1, 2, 4, 12, 15, 19], "hi": [1, 2, 4, 6, 19], "entir": [1, 2, 4, 9, 19], "theori": [1, 2, 4, 19], "gravit": [1, 2, 4, 19], "give": [1, 2, 4, 16, 17, 19], "long": [1, 2, 4, 19], "pleas": [1, 2, 4, 19], "all": [1, 2, 4, 6, 7, 8, 9, 13, 15, 19], "achiev": [1, 2, 4, 19], "addition": 1, "multipl": 1, "other": [1, 2, 6, 7, 9], "featur": [1, 16, 17], "enabl": [1, 7, 16, 17], "ani": [1, 2, 6, 7, 9, 16, 17], "whose": [1, 15], "lower": [1, 12], "than": [1, 5, 9], "specif": [1, 2, 4, 5, 9, 15], "just": [1, 2, 9], "append": [1, 4], "float": [1, 12], "prefer": 1, "mode": 1, "keep": 1, "thing": 1, "simpl": 1, "alias": 1, "oc": 1, "ic": 1, "ot": 1, "illustr": [1, 16, 17], "some": [1, 2, 6, 7, 9, 16, 17], "0": [1, 2, 4, 6, 7, 12], "5input": 1, "case": [1, 2, 7, 9], "ha": [1, 2, 6, 7, 16, 17], "smaller": [1, 5], "5": 1, "credit": [1, 4, 6, 11, 12], "million": 1, "1output": 1, "likewis": [1, 2, 6], "scenario": 1, "direct": 1, "offer": [1, 18], "1": [1, 5, 12], "5ic": 1, "15itl": 1, "now": [1, 2, 7, 8, 9, 19], "someth": [1, 6, 9], "similar": [1, 5], "alia": 1, "also": [1, 2, 7, 8, 9], "consid": 1, "less": 1, "15": 1, "m": 1, "depend": [1, 7], "might": 1, "where": [1, 2, 7, 9, 12], "meet": [1, 6, 7], "criteria": 1, "render": 1, "unfulfil": 1, "404": [1, 13], "error": [1, 4, 12, 13, 15], "correspond": [1, 2, 4, 7, 9], "explan": 1, "detect": 1, "polici": 1, "do": [1, 2, 8], "like": [1, 2, 6, 7, 8, 9, 12, 16, 17, 19], "won": 1, "work": [1, 7, 16, 17], "sinc": 1, "price": 1, "yet": [1, 4, 7], "001ic": 1, "status_cod": [1, 2], "cheapest": 1, "fallback": 1, "payload": [1, 2, 6], "train": [1, 9], "befor": [1, 2, 7, 9, 14], "id": [1, 2, 4, 6, 7], "same": [1, 2, 5, 7], "call": [1, 7, 18], "code": [1, 2, 6, 16, 17], "send": [1, 4, 9, 16, 17], "gpt": [1, 7], "claud": [1, 7, 19], "llama3": [1, 7], "anthropic_8": [1, 7], "28e": [1, 7], "03_4": [1, 7], "66e": [1, 7], "4_1": [1, 7], "00e": [1, 7], "06": [1, 6, 7], "queri": [1, 4, 5, 7, 8, 16, 17], "curl": [1, 2, 4, 6, 19], "among": 1, "page": [1, 2, 4, 6, 7, 9], "That": [1, 7, 8, 9], "know": [1, 2, 8, 9], "care": 1, "about": [1, 4, 5, 9], "start": [1, 2, 11], "applic": [1, 2, 4, 6, 7, 13, 16, 17, 19], "across": [2, 7, 8, 9], "alreadi": [2, 7, 8], "sign": [2, 4, 6, 16, 17], "consol": [2, 6, 7, 8, 9], "greet": 2, "There": [2, 6, 8, 9], "link": 2, "interact": [2, 4, 6, 11, 12, 16, 17], "suspect": 2, "leak": 2, "wai": [2, 6, 7, 8], "safe": 2, "regener": 2, "replac": [2, 6], "old": 2, "workflow": [2, 6], "balanc": [2, 4, 6, 7], "account": [2, 4, 6, 7, 9, 12], "both": [2, 6, 7], "identifi": 2, "given": [2, 4, 15], "go": [2, 4, 5, 6, 7, 9, 16, 17], "copi": [2, 5, 7], "top": [2, 6, 9], "row": 2, "tabl": [2, 9], "v2": 2, "show": [2, 7, 8, 9, 11], "firework": [2, 6], "ai": [2, 4, 6, 8], "custom": [2, 9, 13, 16, 17], "abl": [2, 5], "easiest": 2, "unifyai": [2, 6, 19], "instal": [2, 6], "pip": [2, 6], "script": 2, "insert": 2, "your_api_kei": [2, 4, 6], "env": [2, 19], "project": 2, "pass": 2, "client": [2, 6, 11, 19], "store": 2, "safeti": 2, "remain": [2, 9, 12], "readi": [2, 7, 8, 16, 17], "method": [2, 14], "abov": 2, "return": [2, 6, 11, 12, 14, 15, 16, 17], "string": [2, 5, 6, 12], "access": [2, 6, 7, 9, 11, 12, 16, 17, 19], "coupl": 2, "list_model": [2, 15], "list_provid": [2, 15], "addit": 2, "synchron": 2, "asynchron": [2, 12], "well": [2, 6, 7, 8], "stream": [2, 4, 6, 12], "check": [2, 9], "repo": 2, "text": [2, 4, 6], "chat": [2, 5, 6, 7, 19], "complet": [2, 5, 6, 7, 9, 19], "wouldn": 2, "normal": 2, "allow": [2, 5, 7, 9], "bypass": 2, "model_nam": [2, 11, 12], "provider_nam": [2, 11, 12], "been": [2, 7], "deploi": [2, 6, 7, 9, 16, 17], "languag": [2, 6], "post": [2, 6, 19], "h": [2, 4, 6, 19], "accept": [2, 4, 6, 19], "json": [2, 4, 6, 12, 15, 19], "author": [2, 4, 6], "bearer": [2, 4, 6], "your_unify_kei": [2, 6], "content": [2, 4, 6, 12, 15, 19], "type": [2, 4, 6, 11, 12, 14, 15, 19], "d": [2, 4, 6, 7, 16, 17, 19], "messag": [2, 4, 6, 12, 19], "role": [2, 4, 6, 19], "user": [2, 4, 6, 7, 12, 19], "true": [2, 6, 12], "Or": 2, "url": [2, 6], "header": [2, 6], "print": [2, 6], "200": [2, 4], "chunk": [2, 6, 12], "iter_cont": 2, "chunk_siz": 2, "1024": [2, 12], "decod": 2, "utf": 2, "8": [2, 12], "els": [2, 9], "doc": 2, "avail": [2, 4, 5, 8, 15, 16, 17], "here": [2, 4, 5, 7], "thank": 2, "easili": 2, "integr": [2, 8], "lot": 2, "switch": [2, 16, 17], "base_url": [2, 6, 19], "sai": [2, 6], "test": [2, 7, 9], "word": 2, "showcas": 2, "function": 2, "choic": [2, 4, 6, 16, 17], "delta": [2, 6], "end": [2, 6], "take": [2, 7], "look": [2, 6, 7, 19], "snippet": 2, "offlin": 2, "api_bas": 2, "order": [2, 9], "insert_model": 2, "next": [2, 5, 6, 7, 8, 9], "lorem": [3, 20, 21], "ipsum": [3, 20, 21], "welcom": 4, "resourc": 4, "up": [4, 6, 12, 14], "kei": [4, 6, 8, 11, 12, 15, 16, 17], "retriev": [4, 11, 12], "authent": 4, "ok": 4, "success": [4, 12, 15], "oper": 4, "associ": [4, 15], "corresponding_user_id": 4, "232": [4, 6], "32": [4, 6], "401": [4, 13], "unauthor": [4, 13], "invalid": 4, "403": [4, 13], "forbidden": [4, 13], "Not": [4, 13], "host": [4, 8], "openai": [4, 8, 11, 12], "sure": 4, "its": [4, 6, 7], "after": [4, 5, 7], "llama": [4, 6, 7, 9], "8b": [4, 6], "anyscal": 4, "fals": [4, 11, 12], "schema": 4, "object": [4, 6, 11, 12, 16, 17], "defin": 4, "1704999905": 4, "meta": 4, "hf": 4, "xr868c": 4, "t4z": 4, "tkltfxxzsvq57wmhxb34el5zuuxsatfu": 4, "usag": [4, 6], "completion_token": [4, 6], "512": 4, "prompt_token": [4, 6], "34": 4, "total_token": [4, 6], "546": 4, "finish_reason": [4, 6], "length": [4, 9], "index": [4, 6], "isaac": 4, "1643": 4, "1727": 4, "assist": [4, 6], "422": [4, 13], "unprocess": [4, 13], "entiti": [4, 13], "flexibl": 5, "handl": [5, 6], "advantag": 5, "sever": 5, "reason": [5, 6], "small": 5, "faster": 5, "cheaper": 5, "wherea": 5, "bigger": 5, "capabl": 5, "often": 5, "rang": 5, "difficulti": 5, "everi": [5, 6], "week": 5, "strength": 5, "weak": 5, "continu": 5, "improv": 5, "ride": 5, "wave": 5, "abil": 5, "minimis": 5, "base": [5, 7, 11, 12, 13, 14], "statist": 5, "purpos": 5, "wide": 5, "varieti": [5, 8], "green": 5, "star": [5, 9], "q": 5, "c": 5, "4": [5, 7, 12], "65e": 5, "03": 5, "2": [5, 12], "08e": 5, "05": 5, "07e": 5, "paramet": [5, 6], "stand": 5, "rel": 5, "weigh": 5, "customiz": 5, "meaning": 5, "directli": 5, "restrict": 5, "them": [5, 7, 9], "model1": 5, "model2": 5, "model3": 5, "provider1": 5, "provider2": 5, "rate": 5, "hit": 5, "move": [5, 7], "mean": [5, 19], "higher": [5, 12], "singl": [5, 6, 12, 16, 17], "ve": [5, 8, 9], "found": [5, 13], "those": [5, 8], "product": [5, 6], "visualis": 5, "form": [5, 6], "xxx": 5, "yyi": 5, "accuraci": 5, "final": [5, 7], "system": [5, 12], "onc": [5, 7, 8, 9, 16, 17, 19], "sea": 6, "own": [6, 8], "subtl": 6, "nuanc": 6, "A": [6, 7, 12, 15], "common": [6, 8], "One": 6, "program": 6, "three": 6, "command": 6, "termin": 6, "unify_api_kei": 6, "hello": 6, "field": 6, "find": [6, 9], "made": 6, "togeth": 6, "1718888877": 6, "896bfc1ae84271aa": 6, "lhr": 6, "25": 6, "13": 6, "38": 6, "7": 6, "6e": 6, "stop": [6, 12], "It": 6, "nice": 6, "help": 6, "seed": 6, "11563975138181362140": 6, "via": [6, 8], "number": [6, 12], "total": 6, "u": [6, 9, 18], "temperatur": [6, 12], "max_token": [6, 12], "mai": [6, 7], "compat": 6, "download": [6, 15], "document": 6, "readm": 6, "sampl": [6, 12], "infer": 6, "design": [6, 9], "exist": 6, "straightforward": 6, "try": 6, "rememb": 6, "const": 6, "baseurl": 6, "apikei": 6, "await": 6, "again": [6, 8], "manag": 6, "spend": 6, "behind": [6, 9], "scene": 6, "refil": 6, "get_credit": 6, "your_user_id": 6, "fine": [6, 7], "tune": [6, 7, 9], "add": [6, 7, 8, 9], "relev": 6, "individu": 6, "outag": 6, "disrupt": 6, "combat": 6, "down": 6, "fail": 6, "until": 6, "succe": 6, "reach": 6, "tag": 6, "becom": 6, "model_a": 6, "provider_a": 6, "model_b": 6, "provider_b": 6, "actual": 6, "went": 6, "window": 7, "dataset": [7, 9, 15], "intend": 7, "earlier": [7, 9], "variant": 7, "dropdown": [7, 9], "notic": [7, 16, 17], "becaus": 7, "doe": 7, "button": [7, 8], "submit": [7, 9], "job": [7, 9], "schedul": 7, "behalf": [7, 8], "ahead": 7, "duplic": 7, "previous": 7, "calls1": [7, 9], "call2": 7, "q1": 7, "q2": 7, "repeat": 7, "howev": 7, "70b": 7, "trigger": [7, 9], "manual": 7, "track": [7, 9], "progress": [7, 9], "With": 7, "stage": 7, "accordingli": 7, "visual": [7, 9], "step": [7, 8, 19], "explor": [7, 9], "variou": [7, 9], "possibl": 7, "trade": 7, "off": [7, 8], "speed": [7, 9, 16, 17], "variat": 7, "These": 7, "As": [7, 9], "point": [7, 9, 16, 17], "plot": [7, 9], "view": [7, 9], "constrain": 7, "search": 7, "space": 7, "certain": 7, "deploy": 7, "guarante": 7, "requir": 7, "Of": 7, "cours": 7, "visibl": 7, "remov": [7, 9, 15], "presum": 7, "anthrop": [7, 19], "properli": 7, "save": [7, 15], "moment": 7, "therefor": 7, "appli": 7, "altern": [7, 8], "had": 7, "overwritten": 7, "clauc": 7, "place": 7, "legend": [7, 9], "underneath": 7, "parent": 7, "slightli": 7, "reduc": 7, "amount": 7, "decid": 7, "stick": 7, "decis": [7, 16, 17], "avoid": 7, "immedi": 7, "futur": 7, "appear": [7, 9], "full": 7, "frequenc": 7, "gpt4": 7, "42": 7, "29": 7, "calls2": [7, 9], "18": 7, "11": 7, "metric": [7, 9, 16, 17], "ax": 7, "verifi": 7, "session": 7, "perman": 7, "veri": 7, "happi": [7, 9], "forget": 7, "delet": [7, 15], "anytim": 7, "press": [7, 9], "besid": 7, "clipboard": 7, "along": 7, "default": [7, 9, 11, 12, 15], "shelf": 8, "azur": 8, "ml": 8, "catalog": 8, "vertex": 8, "garden": 8, "aw": 8, "bedrock": 8, "whole": 8, "major": 8, "cloud": 8, "regardless": 8, "expos": [8, 9], "adher": 8, "got": 8, "said": 8, "screen": 8, "local": [8, 15, 19], "build": 8, "label": [8, 9], "preview": 8, "imag": [8, 9], "router": [8, 9, 16, 17], "navig": 9, "ones": 9, "methodologi": 9, "head": 9, "By": 9, "six": 9, "openherm": 9, "shown": 9, "On": 9, "against": 9, "scatter": 9, "replot": 9, "similarili": 9, "score": 9, "updat": 9, "averag": 9, "granular": 9, "outsid": 9, "popular": 9, "period": 9, "suit": 9, "dedic": 9, "region": 9, "sequenc": [9, 12], "latest": [9, 16, 17, 19], "sort": 9, "icon": 9, "column": 9, "reveal": 9, "pattern": 9, "figur": 9, "fit": 9, "resum": 9, "previou": 9, "privat": 9, "server": [9, 13], "vari": 9, "fastest": 9, "under": 9, "ip": 9, "address": 9, "lock": 9, "indic": 9, "necessari": 9, "subsect": 9, "separ": 9, "expand": 9, "pair": 9, "histori": [9, 11, 12], "mixtral": 9, "financ": 9, "alongsid": 9, "foundat": 9, "class": [11, 12, 13, 14], "chatbot": 11, "none": [11, 12, 14, 15], "agent": 11, "__init__": [11, 12], "initi": [11, 12], "arg": [11, 12, 15], "str": [11, 12, 15], "uploaded_bi": [11, 12], "must": [11, 12, 15], "attempt": [11, 12], "rais": [11, 12, 13, 15], "unifyerror": [11, 12, 13], "miss": [11, 12], "clear_chat_histori": 11, "clear": 11, "properti": [11, 12], "dar201": [11, 12], "noqa": [11, 12], "show_credit": 11, "show_provid": 11, "loop": 11, "bool": [11, 12], "whether": 11, "consumpt": 11, "set_client": 11, "dar101": [11, 12], "set_endpoint": [11, 12], "set_model": [11, 12], "set_provid": [11, 12], "asyncunifi": 12, "async": [12, 14], "user_prompt": 12, "system_prompt": 12, "union": 12, "asyncgener": 12, "dict": [12, 15], "dictionari": [12, 15], "convers": 12, "int": 12, "max": 12, "what": [12, 19], "random": 12, "while": 12, "focus": 12, "determinist": 12, "yield": [12, 16, 17], "occur": 12, "dure": 12, "get_credit_bal": 12, "left": 12, "badrequesterror": [12, 13, 15], "valueerror": [12, 15], "pars": [12, 15], "authenticationerror": 13, "400": 13, "bad": 13, "conflicterror": 13, "409": 13, "conflict": 13, "internalservererror": 13, "intern": 13, "notfounderror": 13, "permissiondeniederror": 13, "ratelimiterror": 13, "429": 13, "too": 13, "mani": 13, "unprocessableentityerror": 13, "testasyncunifi": 14, "methodnam": 14, "runtest": 14, "isolatedasynciotestcas": 14, "setup": 14, "hook": 14, "fixtur": 14, "exercis": 14, "test_generate_returns_generator_when_stream_tru": 14, "test_generate_returns_string_when_stream_fals": 14, "test_incorrect_model_name_raises_internal_server_error": 14, "test_invalid_api_key_raises_authentication_error": 14, "test_missing_api_key_raises_key_error": 14, "mock_get": 14, "testunifi": 14, "testcas": 14, "delete_dataset": 15, "platform": [15, 16, 17], "path": 15, "info": 15, "msg": 15, "delete_evalu": 15, "download_dataset": 15, "list_dataset": 15, "fetch": 15, "list_endpoint": 15, "empti": 15, "list_evalu": 15, "upload_dataset_from_dictionari": 15, "upload_dataset_from_fil": 15, "central": [16, 17], "plan": [16, 17], "servic": [16, 17, 19], "b": [16, 17], "target": [16, 17], "high": [16, 17], "throughput": [16, 17], "low": [16, 17], "unfi": [16, 17], "seamless": [16, 17], "refactor": [16, 17], "concept": [16, 17], "quick": [16, 17], "read": [16, 17], "guid": [16, 17], "throughout": [16, 17], "mark": [16, 17], "beta": [16, 17], "constantli": [16, 17], "iter": [16, 17], "roadmap": [16, 17], "leav": [16, 17], "feedback": [16, 17], "suggest": [16, 17], "love": [16, 17], "discuss": [16, 17], "book": 18, "prem": 19, "microservic": 19, "grant": 19, "docker": 19, "Then": 19, "dt": 19, "p": 19, "8000": 19, "env_file_path": 19, "deepinfra_api_kei": 19, "stability_api_kei": 19, "mistral_ai_api_kei": 19, "perplexity_ai_api_kei": 19, "anyscale_api_kei": 19, "octoai_api_kei": 19, "openai_api_kei": 19, "together_ai_api_kei": 19, "replicate_api_kei": 19, "lepton_ai_api_kei": 19, "fireworks_ai_api_kei": 19, "anthropic_api_kei": 19, "vertexai_service_acc_json": 19, "vertexai_gcloud_path": 19, "vertexai_project": 19, "vertexai_loc": 19, "weather": 19, "san": 19, "francisco": 19, "tokyo": 19, "pari": 19, "localhost": 19, "haiku": 19, "random_key_wont_be_us": 19, "life": 19}, "objects": {"unify": [[11, 0, 0, "-", "chat"], [12, 0, 0, "-", "clients"], [13, 0, 0, "-", "exceptions"], [14, 0, 0, "-", "tests"], [15, 0, 0, "-", "utils"]], "unify.chat": [[11, 1, 1, "", "ChatBot"]], "unify.chat.ChatBot": [[11, 2, 1, "", "__init__"], [11, 2, 1, "", "clear_chat_history"], [11, 3, 1, "", "client"], [11, 3, 1, "", "endpoint"], [11, 3, 1, "", "model"], [11, 3, 1, "", "provider"], [11, 2, 1, "", "run"], [11, 2, 1, "", "set_client"], [11, 2, 1, "", "set_endpoint"], [11, 2, 1, "", "set_model"], [11, 2, 1, "", "set_provider"]], "unify.clients": [[12, 1, 1, "", "AsyncUnify"], [12, 1, 1, "", "Unify"]], "unify.clients.AsyncUnify": [[12, 2, 1, "", "__init__"], [12, 3, 1, "", "endpoint"], [12, 2, 1, "", "generate"], [12, 2, 1, "", "get_credit_balance"], [12, 3, 1, "", "model"], [12, 3, 1, "", "provider"], [12, 2, 1, "", "set_endpoint"], [12, 2, 1, "", "set_model"], [12, 2, 1, "", "set_provider"]], "unify.clients.Unify": [[12, 2, 1, "", "__init__"], [12, 3, 1, "", "endpoint"], [12, 2, 1, "", "generate"], [12, 2, 1, "", "get_credit_balance"], [12, 3, 1, "", "model"], [12, 3, 1, "", "provider"], [12, 2, 1, "", "set_endpoint"], [12, 2, 1, "", "set_model"], [12, 2, 1, "", "set_provider"]], "unify.exceptions": [[13, 4, 1, "", "AuthenticationError"], [13, 4, 1, "", "BadRequestError"], [13, 4, 1, "", "ConflictError"], [13, 4, 1, "", "InternalServerError"], [13, 4, 1, "", "NotFoundError"], [13, 4, 1, "", "PermissionDeniedError"], [13, 4, 1, "", "RateLimitError"], [13, 4, 1, "", "UnifyError"], [13, 4, 1, "", "UnprocessableEntityError"]], "unify.tests": [[14, 1, 1, "", "TestAsyncUnify"], [14, 1, 1, "", "TestUnify"]], "unify.tests.TestAsyncUnify": [[14, 2, 1, "", "setUp"], [14, 2, 1, "", "test_generate_returns_generator_when_stream_true"], [14, 2, 1, "", "test_generate_returns_string_when_stream_false"], [14, 2, 1, "", "test_incorrect_model_name_raises_internal_server_error"], [14, 2, 1, "", "test_invalid_api_key_raises_authentication_error"], [14, 2, 1, "", "test_missing_api_key_raises_key_error"]], "unify.tests.TestUnify": [[14, 2, 1, "", "setUp"], [14, 2, 1, "", "test_generate_returns_generator_when_stream_true"], [14, 2, 1, "", "test_generate_returns_string_when_stream_false"], [14, 2, 1, "", "test_incorrect_model_name_raises_internal_server_error"], [14, 2, 1, "", "test_invalid_api_key_raises_authentication_error"], [14, 2, 1, "", "test_missing_api_key_raises_key_error"]], "unify.utils": [[15, 5, 1, "", "delete_dataset"], [15, 5, 1, "", "delete_evaluation"], [15, 5, 1, "", "download_dataset"], [15, 5, 1, "", "evaluate"], [15, 5, 1, "", "list_datasets"], [15, 5, 1, "", "list_endpoints"], [15, 5, 1, "", "list_evaluations"], [15, 5, 1, "", "list_models"], [15, 5, 1, "", "list_providers"], [15, 5, 1, "", "upload_dataset_from_dictionary"], [15, 5, 1, "", "upload_dataset_from_file"]]}, "objtypes": {"0": "py:module", "1": "py:class", "2": "py:method", "3": "py:property", "4": "py:exception", "5": "py:function"}, "objnames": {"0": ["py", "module", "Python module"], "1": ["py", "class", "Python class"], "2": ["py", "method", "Python method"], "3": ["py", "property", "Python property"], "4": ["py", "exception", "Python exception"], "5": ["py", "function", "Python function"]}, "titleterms": {"benchmark": [0, 9], "prepar": [0, 5], "your": [0, 2, 7, 8, 9], "dataset": [0, 5, 8], "how": 0, "doe": 0, "work": 0, "deploi": 1, "router": [1, 5, 7], "us": [1, 2], "base": 1, "optim": 1, "metric": 1, "defin": 1, "threshold": 1, "custom": [1, 5, 6, 7, 8], "round": [1, 2, 7, 8, 9], "up": [1, 2, 7, 8, 9], "make": 2, "first": 2, "request": [2, 6], "get": [2, 4, 16, 17], "kei": 2, "find": 2, "model": 2, "provid": 2, "queri": [2, 6], "an": 2, "endpoint": [2, 5, 6, 8, 9], "python": [2, 6, 21], "packag": [2, 6], "openai": [2, 6], "api": [2, 4, 6], "format": 2, "compat": 2, "tool": 2, "sdk": 2, "open": 2, "interpret": 2, "On": [3, 18, 19], "prem": [3, 18], "imag": 3, "refer": 4, "get_credit": 4, "post": 4, "chat": [4, 11], "complet": 4, "rout": 5, "what": 5, "i": 5, "llm": [5, 6], "foundat": 5, "filter": 5, "maximis": 5, "throughput": 5, "fine": 5, "tune": 5, "train": [5, 7], "beta": [5, 7, 8, 9], "univers": 6, "authent": 6, "http": 6, "unifi": [6, 16, 17], "nodej": 6, "bill": 6, "advanc": 6, "featur": 6, "fallback": 6, "build": 7, "connect": 8, "stack": 8, "prerequisit": 8, "ad": 8, "qualiti": 9, "runtim": 9, "run": 9, "own": 9, "client": 12, "except": 13, "test": 14, "util": 15, "welcom": [16, 17], "start": [16, 17], "access": 18, "sso": 19, "singl": 19, "sign": 19, "openapi": 20, "specif": 20, "librari": 21}, "envversion": {"sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "nbsphinx": 4, "sphinx": 60}, "alltitles": {"Benchmarking endpoints": [[9, "benchmarking-endpoints"]], "Quality benchmarks": [[9, "quality-benchmarks"], [9, "id4"]], "Runtime benchmarks": [[9, "runtime-benchmarks"], [9, "id2"]], "Running your own benchmarks (Beta)": [[9, "running-your-own-benchmarks-beta"]], "Round Up": [[9, "round-up"], [8, "round-up"], [7, "round-up"], [1, "round-up"], [2, "round-up"]], "Connecting your stack": [[8, "connecting-your-stack"]], "Custom endpoints (Beta)": [[8, "custom-endpoints-beta"]], "Prerequisite": [[8, "prerequisite"]], "Adding the endpoints": [[8, "adding-the-endpoints"]], "Custom datasets": [[8, "custom-datasets"]], "Universal API": [[6, "universal-api"]], "Authentication": [[6, "authentication"]], "Querying the API": [[6, "querying-the-api"]], "HTTP Request": [[6, "http-request"]], "Unify Python Package": [[6, "unify-python-package"]], "OpenAI Python Package": [[6, "openai-python-package"]], "OpenAI NodeJS Package": [[6, "openai-nodejs-package"]], "Billing": [[6, "billing"]], "Advanced features": [[6, "advanced-features"]], "Custom endpoints": [[6, "custom-endpoints"]], "LLM Fallbacks": [[6, "llm-fallbacks"]], "Building a custom router": [[7, "building-a-custom-router"]], "Training a custom router (Beta)": [[7, "training-a-custom-router-beta"]], "Customizing your router (Beta)": [[7, "customizing-your-router-beta"]], "Routing": [[5, "routing"]], "What is LLM routing?": [[5, "what-is-llm-routing"]], "Foundation router": [[5, "foundation-router"]], "Filtering endpoints": [[5, "filtering-endpoints"]], "Maximising throughput": [[5, "maximising-throughput"]], "Fine-tuned custom router": [[5, "fine-tuned-custom-router"]], "Preparing a dataset": [[5, "preparing-a-dataset"]], "Training a router (beta)": [[5, "training-a-router-beta"]], "Deploying a router": [[1, "deploying-a-router"]], "Using the base router": [[1, "using-the-base-router"]], "Optimizing a metric": [[1, "optimizing-a-metric"]], "Defining thresholds": [[1, "defining-thresholds"]], "Using a custom router": [[1, "using-a-custom-router"]], "API Reference": [[4, "api-reference"]], "GET /get_credits": [[4, "get-get-credits"]], "POST /chat/completions": [[4, "post-chat-completions"]], "Making your first request": [[2, "making-your-first-request"]], "Getting a key": [[2, "getting-a-key"]], "Finding a model and provider": [[2, "finding-a-model-and-provider"]], "Querying an endpoint": [[2, "querying-an-endpoint"]], "Using the Python Package": [[2, "using-the-python-package"]], "Using the OpenAI API Format": [[2, "using-the-openai-api-format"]], "Compatible Tools": [[2, "compatible-tools"]], "OpenAI SDK": [[2, "openai-sdk"]], "Open Interpreter": [[2, "open-interpreter"]], "Benchmarking": [[0, "benchmarking"]], "Preparing your dataset": [[0, "preparing-your-dataset"]], "Benchmarking your dataset": [[0, "benchmarking-your-dataset"]], "How does it work?": [[0, "how-does-it-work"]], "On-Prem Images": [[3, "on-prem-images"]], "Python Library": [[21, "python-library"]], "OpenAPI Specification": [[20, "openapi-specification"]], "Utils": [[15, "module-unify.utils"]], "Welcome to Unify!": [[17, "welcome-to-unify"], [16, "welcome-to-unify"]], "Getting Started": [[17, "getting-started"], [16, "getting-started"]], "SSO (Single Sign On)": [[19, "sso-single-sign-on"]], "On-Prem access": [[18, "on-prem-access"]], "Exceptions": [[13, "module-unify.exceptions"]], "Tests": [[14, "module-unify.tests"]], "Clients": [[12, "module-unify.clients"]], "Chat": [[11, "module-unify.chat"]]}, "indexentries": {"chatbot (class in unify.chat)": [[11, "unify.chat.ChatBot"]], "__init__() (unify.chat.chatbot method)": [[11, "unify.chat.ChatBot.__init__"]], "clear_chat_history() (unify.chat.chatbot method)": [[11, "unify.chat.ChatBot.clear_chat_history"]], "client (unify.chat.chatbot property)": [[11, "unify.chat.ChatBot.client"]], "endpoint (unify.chat.chatbot property)": [[11, "unify.chat.ChatBot.endpoint"]], "model (unify.chat.chatbot property)": [[11, "unify.chat.ChatBot.model"]], "module": [[11, "module-unify.chat"], [12, "module-unify.clients"], [13, "module-unify.exceptions"], [14, "module-unify.tests"], [15, "module-unify.utils"]], "provider (unify.chat.chatbot property)": [[11, "unify.chat.ChatBot.provider"]], "run() (unify.chat.chatbot method)": [[11, "unify.chat.ChatBot.run"]], "set_client() (unify.chat.chatbot method)": [[11, "unify.chat.ChatBot.set_client"]], "set_endpoint() (unify.chat.chatbot method)": [[11, "unify.chat.ChatBot.set_endpoint"]], "set_model() (unify.chat.chatbot method)": [[11, "unify.chat.ChatBot.set_model"]], "set_provider() (unify.chat.chatbot method)": [[11, "unify.chat.ChatBot.set_provider"]], "unify.chat": [[11, "module-unify.chat"]], "asyncunify (class in unify.clients)": [[12, "unify.clients.AsyncUnify"]], "unify (class in unify.clients)": [[12, "unify.clients.Unify"]], "__init__() (unify.clients.asyncunify method)": [[12, "unify.clients.AsyncUnify.__init__"]], "__init__() (unify.clients.unify method)": [[12, "unify.clients.Unify.__init__"]], "endpoint (unify.clients.asyncunify property)": [[12, "unify.clients.AsyncUnify.endpoint"]], "endpoint (unify.clients.unify property)": [[12, "unify.clients.Unify.endpoint"]], "generate() (unify.clients.asyncunify method)": [[12, "unify.clients.AsyncUnify.generate"]], "generate() (unify.clients.unify method)": [[12, "unify.clients.Unify.generate"]], "get_credit_balance() (unify.clients.asyncunify method)": [[12, "unify.clients.AsyncUnify.get_credit_balance"]], "get_credit_balance() (unify.clients.unify method)": [[12, "unify.clients.Unify.get_credit_balance"]], "model (unify.clients.asyncunify property)": [[12, "unify.clients.AsyncUnify.model"]], "model (unify.clients.unify property)": [[12, "unify.clients.Unify.model"]], "provider (unify.clients.asyncunify property)": [[12, "unify.clients.AsyncUnify.provider"]], "provider (unify.clients.unify property)": [[12, "unify.clients.Unify.provider"]], "set_endpoint() (unify.clients.asyncunify method)": [[12, "unify.clients.AsyncUnify.set_endpoint"]], "set_endpoint() (unify.clients.unify method)": [[12, "unify.clients.Unify.set_endpoint"]], "set_model() (unify.clients.asyncunify method)": [[12, "unify.clients.AsyncUnify.set_model"]], "set_model() (unify.clients.unify method)": [[12, "unify.clients.Unify.set_model"]], "set_provider() (unify.clients.asyncunify method)": [[12, "unify.clients.AsyncUnify.set_provider"]], "set_provider() (unify.clients.unify method)": [[12, "unify.clients.Unify.set_provider"]], "unify.clients": [[12, "module-unify.clients"]], "authenticationerror": [[13, "unify.exceptions.AuthenticationError"]], "badrequesterror": [[13, "unify.exceptions.BadRequestError"]], "conflicterror": [[13, "unify.exceptions.ConflictError"]], "internalservererror": [[13, "unify.exceptions.InternalServerError"]], "notfounderror": [[13, "unify.exceptions.NotFoundError"]], "permissiondeniederror": [[13, "unify.exceptions.PermissionDeniedError"]], "ratelimiterror": [[13, "unify.exceptions.RateLimitError"]], "unifyerror": [[13, "unify.exceptions.UnifyError"]], "unprocessableentityerror": [[13, "unify.exceptions.UnprocessableEntityError"]], "unify.exceptions": [[13, "module-unify.exceptions"]], "testasyncunify (class in unify.tests)": [[14, "unify.tests.TestAsyncUnify"]], "testunify (class in unify.tests)": [[14, "unify.tests.TestUnify"]], "setup() (unify.tests.testasyncunify method)": [[14, "unify.tests.TestAsyncUnify.setUp"]], "setup() (unify.tests.testunify method)": [[14, "unify.tests.TestUnify.setUp"]], "test_generate_returns_generator_when_stream_true() (unify.tests.testasyncunify method)": [[14, "unify.tests.TestAsyncUnify.test_generate_returns_generator_when_stream_true"]], "test_generate_returns_generator_when_stream_true() (unify.tests.testunify method)": [[14, "unify.tests.TestUnify.test_generate_returns_generator_when_stream_true"]], "test_generate_returns_string_when_stream_false() (unify.tests.testasyncunify method)": [[14, "unify.tests.TestAsyncUnify.test_generate_returns_string_when_stream_false"]], "test_generate_returns_string_when_stream_false() (unify.tests.testunify method)": [[14, "unify.tests.TestUnify.test_generate_returns_string_when_stream_false"]], "test_incorrect_model_name_raises_internal_server_error() (unify.tests.testasyncunify method)": [[14, "unify.tests.TestAsyncUnify.test_incorrect_model_name_raises_internal_server_error"]], "test_incorrect_model_name_raises_internal_server_error() (unify.tests.testunify method)": [[14, "unify.tests.TestUnify.test_incorrect_model_name_raises_internal_server_error"]], "test_invalid_api_key_raises_authentication_error() (unify.tests.testasyncunify method)": [[14, "unify.tests.TestAsyncUnify.test_invalid_api_key_raises_authentication_error"]], "test_invalid_api_key_raises_authentication_error() (unify.tests.testunify method)": [[14, "unify.tests.TestUnify.test_invalid_api_key_raises_authentication_error"]], "test_missing_api_key_raises_key_error() (unify.tests.testasyncunify method)": [[14, "unify.tests.TestAsyncUnify.test_missing_api_key_raises_key_error"]], "test_missing_api_key_raises_key_error() (unify.tests.testunify method)": [[14, "unify.tests.TestUnify.test_missing_api_key_raises_key_error"]], "unify.tests": [[14, "module-unify.tests"]], "delete_dataset() (in module unify.utils)": [[15, "unify.utils.delete_dataset"]], "delete_evaluation() (in module unify.utils)": [[15, "unify.utils.delete_evaluation"]], "download_dataset() (in module unify.utils)": [[15, "unify.utils.download_dataset"]], "evaluate() (in module unify.utils)": [[15, "unify.utils.evaluate"]], "list_datasets() (in module unify.utils)": [[15, "unify.utils.list_datasets"]], "list_endpoints() (in module unify.utils)": [[15, "unify.utils.list_endpoints"]], "list_evaluations() (in module unify.utils)": [[15, "unify.utils.list_evaluations"]], "list_models() (in module unify.utils)": [[15, "unify.utils.list_models"]], "list_providers() (in module unify.utils)": [[15, "unify.utils.list_providers"]], "unify.utils": [[15, "module-unify.utils"]], "upload_dataset_from_dictionary() (in module unify.utils)": [[15, "unify.utils.upload_dataset_from_dictionary"]], "upload_dataset_from_file() (in module unify.utils)": [[15, "unify.utils.upload_dataset_from_file"]]}}) \ No newline at end of file +Search.setIndex({"docnames": ["concepts/benchmarks", "concepts/deploy_router", "concepts/first_request", "concepts/images", "concepts/reference", "concepts/router", "concepts/unify_api", "console/building_router", "console/connecting_stack", "console/running_benchmarks", "docs/unify/unify", "docs/unify/unify/unify.chat", "docs/unify/unify/unify.clients", "docs/unify/unify/unify.exceptions", "docs/unify/unify/unify.utils", "home/home", "index", "on_prem/on_prem_access", "on_prem/sso", "tools/openapi", "tools/python_library"], "filenames": ["concepts/benchmarks.rst", "concepts/deploy_router.rst", "concepts/first_request.rst", "concepts/images.rst", "concepts/reference.rst", "concepts/router.rst", "concepts/unify_api.rst", "console/building_router.rst", "console/connecting_stack.rst", "console/running_benchmarks.rst", "docs/unify/unify.rst", "docs/unify/unify/unify.chat.rst", "docs/unify/unify/unify.clients.rst", "docs/unify/unify/unify.exceptions.rst", "docs/unify/unify/unify.utils.rst", "home/home.rst", "index.rst", "on_prem/on_prem_access.rst", "on_prem/sso.rst", "tools/openapi.rst", "tools/python_library.rst"], "titles": ["Benchmarking", "Deploying a router", "Making your first request", "On-Prem Images", "API Reference", "Routing", "Universal API", "Building a custom router", "Connecting your stack", "Benchmarking endpoints", "<no title>", "Chat", "Clients", "Exceptions", "Utils", "Welcome to Unify!", "Home", "On-Prem access", "SSO (Single Sign On)", "OpenAPI Specification", "Python Library"], "terms": {"when": [0, 1, 2, 4, 5, 7, 12], "compar": [0, 9, 15, 16], "llm": [0, 1, 2, 8, 9, 11, 15, 16], "i": [0, 1, 2, 4, 6, 7, 8, 9, 11, 12, 14, 15, 16, 18], "constant": 0, "tradeoff": 0, "make": [0, 1, 4, 7, 12, 15, 16], "between": [0, 2, 5, 6, 7, 12], "qualiti": [0, 5, 7, 15, 16], "cost": [0, 1, 5, 6, 7, 9, 15, 16], "latenc": [0, 1, 5, 7, 9], "stronger": 0, "model": [0, 1, 4, 5, 6, 7, 8, 9, 11, 12, 14, 15, 16, 18], "ar": [0, 1, 2, 5, 6, 7, 8, 9, 15, 16], "gener": [0, 1, 2, 4, 5, 6, 12, 18], "slower": 0, "more": [0, 2, 5, 9, 12], "expens": 0, "sometim": [0, 6], "overkil": 0, "task": [0, 1, 5, 7, 9], "hand": [0, 9], "complic": 0, "matter": 0, "further": [0, 7, 12], "new": [0, 2, 5, 6, 7, 8, 9], "releas": [0, 5], "weekli": 0, "each": [0, 1, 5, 6, 7, 9, 14, 15, 16], "claim": 0, "state": 0, "art": 0, "data": [0, 1, 7], "let": [0, 1, 2, 7, 8, 9, 15, 16], "you": [0, 1, 2, 4, 5, 6, 7, 8, 9, 15, 16, 18], "see": [0, 6, 7, 9, 15, 16], "differ": [0, 4, 5, 7, 9, 15, 16], "perform": [0, 1, 7, 9, 15, 16], "can": [0, 1, 2, 4, 5, 6, 7, 8, 9, 15, 16, 18], "relat": 0, "live": [0, 5, 6], "stat": 0, "pull": [0, 18], "from": [0, 1, 2, 4, 5, 6, 7, 9, 11, 12, 14, 15, 16, 18], "our": [0, 1, 2, 6, 7, 8, 9, 15, 16, 17, 18], "runtim": [0, 5, 6], "come": [0, 4, 5, 6], "out": [0, 2, 5, 6], "simpli": [0, 2, 9, 15, 16], "re": [0, 7, 9, 15, 16, 18], "run": [0, 2, 6, 7, 8, 11, 18], "thei": [0, 5, 6], "first": [0, 1, 4, 5, 6, 7, 9, 15, 16], "creat": [0, 2, 4, 6, 7, 8], "which": [0, 4, 5, 6, 7, 9, 18], "repres": [0, 11], "want": [0, 1, 2, 7, 8, 9], "evalu": [0, 9, 14], "need": [0, 1, 2, 5, 6, 7, 8, 9, 15, 16], "list": [0, 2, 6, 7, 9, 12, 14], "prompt": [0, 1, 5, 6, 8, 9, 12, 14, 15, 16], "option": [0, 1, 5, 7, 8, 11, 12, 14], "includ": [0, 1, 7, 8, 9], "refer": [0, 5, 8], "gold": 0, "standard": [0, 6, 8], "answer": [0, 5, 8], "contain": [0, 2, 5, 6, 8, 9, 12, 14], "tend": [0, 9], "get": [0, 1, 5, 6, 11, 12, 14, 17], "accur": 0, "The": [0, 2, 4, 5, 6, 7, 8, 9, 11, 12, 15, 16, 18], "file": [0, 2, 5, 8, 14, 18], "itself": 0, "should": [0, 2, 6, 8, 9, 18], "jsonl": [0, 5, 8], "format": [0, 4, 5, 6, 11, 12, 15, 16], "one": [0, 1, 2, 4, 5, 6, 8, 9, 15, 16], "entri": [0, 5], "per": [0, 1, 7], "line": [0, 2], "exampl": [0, 1, 2, 4, 5, 6, 7, 8], "below": [0, 1, 2, 7, 8, 9], "thi": [0, 1, 2, 4, 5, 6, 7, 8, 9, 14, 15, 16, 18], "ref_answ": [0, 5], "second": [0, 1, 7], "us": [0, 4, 5, 6, 7, 8, 9, 11, 12, 14, 15, 16, 18], "least": [0, 9], "50": 0, "most": [0, 5, 8], "result": [0, 5, 7, 8, 9], "current": [0, 1, 4, 6, 7, 9, 15, 16], "an": [0, 1, 5, 6, 7, 8, 11, 12, 14], "maximum": 0, "limit": [0, 2, 5, 6], "500": [0, 13], "we": [0, 1, 2, 5, 6, 7, 8, 9, 15, 16], "don": [0, 4, 7], "t": [0, 1, 2, 4, 5, 7, 9], "much": [0, 1, 5], "extra": 0, "detail": [0, 1, 2, 4, 6, 7, 18], "past": 0, "250": 0, "In": [0, 1, 2, 5, 6, 7, 8, 9, 15, 16], "dashboard": [0, 5, 7, 9], "click": [0, 5, 7, 8, 9], "select": [0, 5, 7, 9], "open": [0, 7, 9], "interfac": [0, 1, 2, 5, 6, 8, 9, 15, 16], "upload": [0, 2, 5, 7, 8, 9, 14], "finish": [0, 5], "ll": [0, 1, 2, 5, 7, 8, 9, 15, 16], "receiv": [0, 5, 7], "email": [0, 5, 7], "graph": [0, 5, 7, 9], "displai": [0, 5, 7, 9], "x": [0, 2, 4, 6, 7, 9, 18], "axi": [0, 9], "set": [0, 1, 2, 6, 7, 8, 11, 12], "time": [0, 1, 5, 6, 7, 9], "token": [0, 1, 5, 6, 7, 9, 12], "inter": [0, 1, 5, 7], "either": [0, 6, 7, 14, 15, 16], "linear": 0, "log": 0, "scale": 0, "gpt4o": 0, "judg": 0, "cf": 0, "http": [0, 2, 4, 12, 13, 14, 18], "arxiv": 0, "org": 0, "ab": 0, "2306": 0, "05685": 0, "": [0, 1, 2, 5, 6, 7, 8, 9, 12, 18], "respons": [0, 1, 2, 4, 5, 6, 12, 14, 18], "section": [1, 2, 7, 8, 9, 15, 16], "learn": [1, 2, 4, 5, 7, 8, 9, 15, 16], "how": [1, 2, 5, 6, 7, 8, 9, 15, 16], "unifi": [1, 2, 4, 7, 8, 11, 12, 13, 14, 18], "through": [1, 2, 6, 7, 8, 9], "api": [1, 5, 7, 8, 11, 12, 14, 15, 16, 18], "If": [1, 2, 4, 6, 7, 8, 9, 11, 12, 14], "haven": [1, 2, 9], "done": [1, 2, 7, 9], "so": [1, 2, 6, 7, 8, 9, 15, 16], "recommend": [1, 2, 9, 15, 16], "request": [1, 4, 7, 9, 13, 15, 16, 18], "familiar": [1, 15, 16], "leverag": 1, "inform": [1, 7, 9], "benchmark": [1, 2, 5, 6, 7, 8, 15, 16], "automat": [1, 6, 7], "rout": [1, 2, 7, 8, 15, 16], "best": [1, 5, 7, 15, 16], "provid": [1, 4, 5, 6, 7, 8, 9, 11, 12, 14, 15, 16], "choos": [1, 2, 5, 7], "valu": [1, 9, 11, 12, 14], "chang": [1, 5, 7, 9, 15, 16], "over": [1, 5, 9], "dynam": 1, "ensur": [1, 7, 9], "alwai": [1, 9], "without": 1, "have": [1, 2, 4, 5, 6, 7, 8, 9, 18], "monitor": 1, "yourself": 1, "To": [1, 2, 4, 5, 6, 9, 17], "onli": [1, 2, 6, 7, 9, 15, 16], "provier": 1, "name": [1, 2, 4, 6, 7, 8, 9, 11, 12, 14], "support": [1, 2, 6, 14], "configur": [1, 2, 5, 7, 9], "follow": [1, 4, 5, 6], "config": 1, "lowest": 1, "input": [1, 4, 15, 16], "output": [1, 6, 9, 12, 15, 16], "itl": 1, "ttft": [1, 9], "highest": 1, "tk": 1, "sec": [1, 9], "For": [1, 2, 5, 7, 8, 9], "e": [1, 2, 5, 7, 9], "g": [1, 2, 7, 9], "python": [1, 18], "packag": 1, "endpoint": [1, 4, 7, 11, 12, 14, 15, 16], "import": [1, 2, 6, 18], "o": [1, 2], "assum": [1, 2, 7, 8], "ad": [1, 2, 9], "unify_kei": [1, 2, 11, 12, 14], "your": [1, 4, 5, 6, 12, 15, 16, 18], "environ": [1, 2, 7, 11, 12, 14, 15, 16], "variabl": [1, 2, 11, 12, 14], "otherwis": [1, 2, 12, 14], "would": [1, 2, 6, 7, 8, 9], "specifi": [1, 2, 4, 5, 6, 7, 8, 9, 14], "api_kei": [1, 2, 6, 11, 12, 14, 18], "argument": [1, 2, 4], "mistral": [1, 2, 6, 9], "7b": [1, 2, 6, 9], "instruct": [1, 2, 6, 9], "v0": [1, 2, 4, 6, 9], "3": [1, 2, 4, 6, 7, 9, 18], "explain": [1, 2, 4, 9, 15, 16, 18], "who": [1, 2, 4, 18], "newton": [1, 2, 4, 18], "wa": [1, 2, 4, 12, 14, 18], "hi": [1, 2, 4, 6, 18], "entir": [1, 2, 4, 9, 18], "theori": [1, 2, 4, 18], "gravit": [1, 2, 4, 18], "give": [1, 2, 4, 15, 16, 18], "long": [1, 2, 4, 18], "pleas": [1, 2, 4, 18], "all": [1, 2, 4, 6, 7, 8, 9, 13, 14, 15, 16, 18], "achiev": [1, 2, 4, 18], "addition": 1, "multipl": 1, "other": [1, 2, 6, 7, 9], "featur": [1, 15, 16], "enabl": [1, 7], "ani": [1, 2, 6, 7, 9, 15, 16], "whose": [1, 14], "lower": [1, 12], "than": [1, 5, 9], "specif": [1, 2, 4, 5, 9, 14], "just": [1, 2, 9], "append": [1, 4], "float": [1, 12], "prefer": 1, "mode": 1, "keep": 1, "thing": 1, "simpl": 1, "alias": 1, "oc": 1, "ic": 1, "ot": 1, "illustr": [1, 15, 16], "some": [1, 2, 6, 7, 9, 15, 16], "0": [1, 2, 4, 6, 7, 12], "5input": 1, "case": [1, 2, 7, 9, 15, 16], "ha": [1, 2, 6, 7], "smaller": [1, 5], "5": 1, "credit": [1, 4, 6, 11, 12], "million": 1, "1output": 1, "likewis": [1, 2, 6], "scenario": 1, "direct": 1, "offer": [1, 17], "1": [1, 5, 12], "5ic": 1, "15itl": 1, "now": [1, 2, 7, 8, 9, 18], "someth": [1, 6, 9], "similar": [1, 5], "alia": 1, "also": [1, 2, 7, 8, 9], "consid": 1, "less": 1, "15": 1, "m": 1, "depend": [1, 7], "might": 1, "where": [1, 2, 7, 9, 12], "meet": [1, 6, 7], "criteria": 1, "render": 1, "unfulfil": 1, "404": [1, 13], "error": [1, 4, 12, 13, 14], "correspond": [1, 2, 4, 7, 9], "explan": 1, "detect": 1, "polici": 1, "do": [1, 2, 8], "like": [1, 2, 6, 7, 8, 9, 12, 15, 16, 18], "won": 1, "work": [1, 7, 15, 16], "sinc": 1, "price": 1, "yet": [1, 4, 7], "001ic": 1, "status_cod": [1, 2], "cheapest": 1, "fallback": 1, "payload": [1, 2, 6], "train": [1, 9], "befor": [1, 2, 7, 9], "id": [1, 2, 4, 6, 7], "same": [1, 2, 5, 7], "call": [1, 7, 17], "code": [1, 2, 6, 15, 16], "send": [1, 4, 9], "gpt": [1, 7], "claud": [1, 7, 18], "llama3": [1, 7], "anthropic_8": [1, 7], "28e": [1, 7], "03_4": [1, 7], "66e": [1, 7], "4_1": [1, 7], "00e": [1, 7], "06": [1, 6, 7], "queri": [1, 4, 5, 7, 8, 15, 16], "curl": [1, 2, 4, 6, 18], "among": 1, "page": [1, 2, 4, 6, 7, 9], "That": [1, 7, 8, 9], "know": [1, 2, 8, 9], "care": 1, "about": [1, 4, 5, 9], "start": [1, 2, 11], "applic": [1, 2, 4, 6, 7, 13, 18], "across": [2, 7, 8, 9], "alreadi": [2, 7, 8], "sign": [2, 4, 6, 15, 16], "consol": [2, 6, 7, 8, 9], "greet": 2, "There": [2, 6, 8, 9], "link": 2, "interact": [2, 4, 6, 11, 12, 15, 16], "suspect": 2, "leak": 2, "wai": [2, 6, 7, 8], "safe": 2, "regener": 2, "replac": [2, 6], "old": 2, "workflow": [2, 6], "balanc": [2, 4, 6, 7], "account": [2, 4, 6, 7, 9, 12], "both": [2, 6, 7], "identifi": 2, "given": [2, 4, 14], "go": [2, 4, 5, 6, 7, 9, 15, 16], "copi": [2, 5, 7], "top": [2, 6, 9], "row": 2, "tabl": [2, 9], "v2": 2, "show": [2, 7, 8, 9, 11], "firework": [2, 6], "ai": [2, 4, 6, 8], "custom": [2, 9, 13, 15, 16], "abl": [2, 5], "easiest": 2, "unifyai": [2, 6, 18], "instal": [2, 6], "pip": [2, 6], "script": 2, "insert": 2, "your_api_kei": [2, 4, 6], "env": [2, 18], "project": 2, "pass": [2, 15, 16], "client": [2, 6, 11, 18], "store": 2, "safeti": 2, "remain": [2, 9, 12], "readi": [2, 7, 8, 15, 16], "method": 2, "abov": 2, "return": [2, 6, 11, 12, 14], "string": [2, 5, 6, 12, 15, 16], "access": [2, 6, 7, 9, 11, 12, 18], "coupl": 2, "list_model": [2, 14], "list_provid": [2, 14], "addit": 2, "synchron": 2, "asynchron": [2, 12], "well": [2, 6, 7, 8], "stream": [2, 4, 6, 12], "check": [2, 9], "repo": 2, "text": [2, 4, 6], "chat": [2, 5, 6, 7, 18], "complet": [2, 5, 6, 7, 9, 18], "wouldn": 2, "normal": 2, "allow": [2, 5, 7, 9], "bypass": 2, "model_nam": [2, 11, 12], "provider_nam": [2, 11, 12], "been": [2, 7], "deploi": [2, 6, 7, 9, 15, 16], "languag": [2, 6], "post": [2, 6, 18], "h": [2, 4, 6, 18], "accept": [2, 4, 6, 18], "json": [2, 4, 6, 12, 14, 18], "author": [2, 4, 6], "bearer": [2, 4, 6], "your_unify_kei": [2, 6], "content": [2, 4, 6, 12, 14, 18], "type": [2, 4, 6, 11, 12, 14, 18], "d": [2, 4, 6, 7, 15, 16, 18], "messag": [2, 4, 6, 12, 18], "role": [2, 4, 6, 18], "user": [2, 4, 6, 7, 12, 18], "true": [2, 6, 12], "Or": 2, "url": [2, 6], "header": [2, 6], "print": [2, 6], "200": [2, 4], "chunk": [2, 6, 12], "iter_cont": 2, "chunk_siz": 2, "1024": [2, 12], "decod": 2, "utf": 2, "8": [2, 12], "els": [2, 9], "doc": 2, "avail": [2, 4, 5, 8, 14, 15, 16], "here": [2, 4, 5, 7], "thank": 2, "easili": 2, "integr": [2, 8], "lot": 2, "switch": 2, "base_url": [2, 6, 18], "sai": [2, 6], "test": [2, 7, 9, 15, 16], "word": 2, "showcas": 2, "function": 2, "choic": [2, 4, 6], "delta": [2, 6], "end": [2, 6], "take": [2, 7], "look": [2, 6, 7, 18], "snippet": 2, "offlin": 2, "api_bas": 2, "order": [2, 9], "insert_model": 2, "next": [2, 5, 6, 7, 8, 9], "lorem": [3, 19, 20], "ipsum": [3, 19, 20], "welcom": 4, "resourc": 4, "up": [4, 6, 12], "kei": [4, 6, 8, 11, 12, 14, 15, 16], "retriev": [4, 11, 12], "authent": 4, "ok": 4, "success": [4, 12, 14], "oper": 4, "associ": [4, 14], "corresponding_user_id": 4, "232": [4, 6], "32": [4, 6], "401": [4, 13], "unauthor": [4, 13], "invalid": 4, "403": [4, 13], "forbidden": [4, 13], "Not": [4, 13], "host": [4, 8], "openai": [4, 8, 11, 12], "sure": 4, "its": [4, 6, 7], "after": [4, 5, 7], "llama": [4, 6, 7, 9], "8b": [4, 6], "anyscal": 4, "fals": [4, 11, 12], "schema": 4, "object": [4, 6, 11, 12], "defin": 4, "1704999905": 4, "meta": 4, "hf": 4, "xr868c": 4, "t4z": 4, "tkltfxxzsvq57wmhxb34el5zuuxsatfu": 4, "usag": [4, 6], "completion_token": [4, 6], "512": 4, "prompt_token": [4, 6], "34": 4, "total_token": [4, 6], "546": 4, "finish_reason": [4, 6], "length": [4, 9], "index": [4, 6], "isaac": 4, "1643": 4, "1727": 4, "assist": [4, 6], "422": [4, 13], "unprocess": [4, 13], "entiti": [4, 13], "flexibl": 5, "handl": [5, 6, 15, 16], "advantag": 5, "sever": [5, 15, 16], "reason": [5, 6], "small": 5, "faster": 5, "cheaper": 5, "wherea": 5, "bigger": 5, "capabl": 5, "often": 5, "rang": 5, "difficulti": 5, "everi": [5, 6], "week": 5, "strength": 5, "weak": 5, "continu": 5, "improv": [5, 15, 16], "ride": 5, "wave": 5, "abil": 5, "minimis": 5, "base": [5, 7, 11, 12, 13], "statist": 5, "purpos": 5, "wide": 5, "varieti": [5, 8], "green": 5, "star": [5, 9], "q": 5, "c": 5, "4": [5, 7, 12], "65e": 5, "03": 5, "2": [5, 12], "08e": 5, "05": 5, "07e": 5, "paramet": [5, 6], "stand": 5, "rel": 5, "weigh": 5, "customiz": 5, "meaning": 5, "directli": 5, "restrict": 5, "them": [5, 7, 9], "model1": 5, "model2": 5, "model3": 5, "provider1": 5, "provider2": 5, "rate": 5, "hit": 5, "move": [5, 7], "mean": [5, 18], "higher": [5, 12], "singl": [5, 6, 12, 15, 16], "ve": [5, 8, 9], "found": [5, 13], "those": [5, 8], "product": [5, 6], "visualis": 5, "form": [5, 6], "xxx": 5, "yyi": 5, "accuraci": 5, "final": [5, 7], "system": [5, 12, 15, 16], "onc": [5, 7, 8, 9, 15, 16, 18], "sea": 6, "own": [6, 8, 15, 16], "subtl": 6, "nuanc": 6, "A": [6, 7, 12, 14], "common": [6, 8], "One": 6, "program": 6, "three": 6, "command": 6, "termin": 6, "unify_api_kei": 6, "hello": 6, "field": 6, "find": [6, 9], "made": 6, "togeth": 6, "1718888877": 6, "896bfc1ae84271aa": 6, "lhr": 6, "25": 6, "13": 6, "38": 6, "7": 6, "6e": 6, "stop": [6, 12], "It": 6, "nice": 6, "help": 6, "seed": 6, "11563975138181362140": 6, "via": [6, 8], "number": [6, 12], "total": [6, 14], "u": [6, 9, 17], "temperatur": [6, 12], "max_token": [6, 12], "mai": [6, 7], "compat": 6, "download": [6, 14], "document": 6, "readm": 6, "sampl": [6, 12], "infer": 6, "design": [6, 9], "exist": 6, "straightforward": 6, "try": 6, "rememb": 6, "const": 6, "baseurl": 6, "apikei": 6, "await": 6, "again": [6, 8], "manag": [6, 15, 16], "spend": 6, "behind": [6, 9], "scene": 6, "refil": 6, "get_credit": 6, "your_user_id": 6, "fine": [6, 7], "tune": [6, 7, 9], "add": [6, 7, 8, 9, 15, 16], "relev": 6, "individu": [6, 15, 16], "outag": 6, "disrupt": 6, "combat": 6, "down": 6, "fail": 6, "until": [6, 15, 16], "succe": 6, "reach": 6, "tag": 6, "becom": 6, "model_a": 6, "provider_a": 6, "model_b": 6, "provider_b": 6, "actual": 6, "went": 6, "window": 7, "dataset": [7, 9, 14], "intend": 7, "earlier": [7, 9], "variant": 7, "dropdown": [7, 9], "notic": [7, 15, 16], "becaus": 7, "doe": 7, "button": [7, 8], "submit": [7, 9], "job": [7, 9], "schedul": 7, "behalf": [7, 8], "ahead": 7, "duplic": 7, "previous": 7, "calls1": [7, 9], "call2": 7, "q1": 7, "q2": 7, "repeat": 7, "howev": 7, "70b": 7, "trigger": [7, 9], "manual": 7, "track": [7, 9], "progress": [7, 9], "With": [7, 15, 16], "stage": 7, "accordingli": 7, "visual": [7, 9], "step": [7, 8, 18], "explor": [7, 9], "variou": [7, 9], "possibl": 7, "trade": 7, "off": [7, 8], "speed": [7, 9, 15, 16], "variat": 7, "These": 7, "As": [7, 9], "point": [7, 9, 15, 16], "plot": [7, 9], "view": [7, 9], "constrain": 7, "search": 7, "space": 7, "certain": 7, "deploy": 7, "guarante": 7, "requir": 7, "Of": 7, "cours": 7, "visibl": 7, "remov": [7, 9, 14], "presum": 7, "anthrop": [7, 18], "properli": 7, "save": [7, 14], "moment": 7, "therefor": 7, "appli": 7, "altern": [7, 8], "had": 7, "overwritten": 7, "clauc": 7, "place": 7, "legend": [7, 9], "underneath": 7, "parent": 7, "slightli": 7, "reduc": 7, "amount": 7, "decid": 7, "stick": 7, "decis": 7, "avoid": 7, "immedi": 7, "futur": 7, "appear": [7, 9], "full": 7, "frequenc": 7, "gpt4": 7, "42": 7, "29": 7, "calls2": [7, 9], "18": 7, "11": 7, "metric": [7, 9], "ax": 7, "verifi": 7, "session": 7, "perman": 7, "veri": 7, "happi": [7, 9], "forget": 7, "delet": [7, 14], "anytim": 7, "press": [7, 9], "besid": 7, "clipboard": 7, "along": 7, "default": [7, 9, 11, 12, 14], "shelf": 8, "azur": 8, "ml": 8, "catalog": 8, "vertex": 8, "garden": 8, "aw": 8, "bedrock": 8, "whole": 8, "major": 8, "cloud": 8, "regardless": 8, "expos": [8, 9], "adher": 8, "got": 8, "said": 8, "screen": 8, "local": [8, 14, 18], "build": 8, "label": [8, 9], "preview": 8, "imag": [8, 9], "router": [8, 9, 15, 16], "navig": 9, "ones": 9, "methodologi": 9, "head": 9, "By": 9, "six": 9, "openherm": 9, "shown": 9, "On": 9, "against": 9, "scatter": 9, "replot": 9, "similarili": 9, "score": 9, "updat": 9, "averag": 9, "granular": 9, "outsid": 9, "popular": 9, "period": 9, "suit": 9, "dedic": 9, "region": 9, "sequenc": [9, 12], "latest": [9, 18], "sort": 9, "icon": 9, "column": 9, "reveal": 9, "pattern": 9, "figur": 9, "fit": 9, "resum": 9, "previou": 9, "privat": 9, "server": [9, 13], "vari": 9, "fastest": 9, "under": 9, "ip": 9, "address": 9, "lock": 9, "indic": 9, "necessari": 9, "subsect": 9, "separ": 9, "expand": 9, "pair": 9, "histori": [9, 11, 12], "mixtral": 9, "financ": 9, "alongsid": 9, "foundat": 9, "class": [11, 12, 13], "chatbot": 11, "none": [11, 12, 14], "agent": 11, "__init__": [11, 12], "initi": [11, 12], "arg": [11, 12, 14], "str": [11, 12, 14], "uploaded_bi": [11, 12], "must": [11, 12, 14], "attempt": [11, 12], "rais": [11, 12, 13, 14], "unifyerror": [11, 12, 13], "miss": [11, 12], "clear_chat_histori": 11, "clear": 11, "properti": [11, 12], "dar201": [11, 12], "noqa": [11, 12], "show_credit": 11, "show_provid": 11, "loop": 11, "bool": [11, 12], "whether": 11, "consumpt": 11, "set_client": 11, "dar101": [11, 12], "set_endpoint": [11, 12], "set_model": [11, 12], "set_provid": [11, 12], "asyncunifi": 12, "async": 12, "user_prompt": 12, "system_prompt": 12, "union": 12, "asyncgener": 12, "dict": [12, 14], "dictionari": [12, 14], "convers": 12, "int": 12, "max": 12, "what": [12, 18], "random": 12, "while": 12, "focus": 12, "determinist": 12, "yield": 12, "occur": 12, "dure": 12, "get_credit_bal": 12, "left": 12, "badrequesterror": [12, 13, 14], "valueerror": [12, 14], "pars": [12, 14], "authenticationerror": 13, "400": 13, "bad": 13, "conflicterror": 13, "409": 13, "conflict": 13, "internalservererror": 13, "intern": 13, "notfounderror": 13, "permissiondeniederror": 13, "ratelimiterror": 13, "429": 13, "too": 13, "mani": 13, "unprocessableentityerror": 13, "delete_dataset": 14, "platform": 14, "path": 14, "info": 14, "msg": 14, "delete_evalu": 14, "download_dataset": 14, "list_dataset": 14, "fetch": 14, "list_endpoint": 14, "empti": 14, "list_evalu": 14, "upload_dataset_from_dictionari": 14, "upload_dataset_from_fil": 14, "mission": [15, 16], "simplifi": [15, 16], "landscap": [15, 16], "No": [15, 16], "eval": [15, 16], "iter": [15, 16], "app": [15, 16], "perfect": [15, 16], "concept": [15, 16], "quick": [15, 16], "read": [15, 16], "guid": [15, 16], "throughout": [15, 16], "mark": [15, 16], "beta": [15, 16], "plan": [15, 16], "constantli": [15, 16], "roadmap": [15, 16], "leav": [15, 16], "feedback": [15, 16], "suggest": [15, 16], "love": [15, 16], "discuss": [15, 16], "book": 17, "prem": 18, "microservic": 18, "grant": 18, "docker": 18, "Then": 18, "dt": 18, "p": 18, "8000": 18, "env_file_path": 18, "deepinfra_api_kei": 18, "stability_api_kei": 18, "mistral_ai_api_kei": 18, "perplexity_ai_api_kei": 18, "anyscale_api_kei": 18, "octoai_api_kei": 18, "openai_api_kei": 18, "together_ai_api_kei": 18, "replicate_api_kei": 18, "lepton_ai_api_kei": 18, "fireworks_ai_api_kei": 18, "anthropic_api_kei": 18, "vertexai_service_acc_json": 18, "vertexai_gcloud_path": 18, "vertexai_project": 18, "vertexai_loc": 18, "servic": 18, "weather": 18, "san": 18, "francisco": 18, "tokyo": 18, "pari": 18, "localhost": 18, "haiku": 18, "random_key_wont_be_us": 18, "life": 18}, "objects": {"unify": [[11, 0, 0, "-", "chat"], [12, 0, 0, "-", "clients"], [13, 0, 0, "-", "exceptions"], [14, 0, 0, "-", "utils"]], "unify.chat": [[11, 1, 1, "", "ChatBot"]], "unify.chat.ChatBot": [[11, 2, 1, "", "__init__"], [11, 2, 1, "", "clear_chat_history"], [11, 3, 1, "", "client"], [11, 3, 1, "", "endpoint"], [11, 3, 1, "", "model"], [11, 3, 1, "", "provider"], [11, 2, 1, "", "run"], [11, 2, 1, "", "set_client"], [11, 2, 1, "", "set_endpoint"], [11, 2, 1, "", "set_model"], [11, 2, 1, "", "set_provider"]], "unify.clients": [[12, 1, 1, "", "AsyncUnify"], [12, 1, 1, "", "Unify"]], "unify.clients.AsyncUnify": [[12, 2, 1, "", "__init__"], [12, 3, 1, "", "endpoint"], [12, 2, 1, "", "generate"], [12, 2, 1, "", "get_credit_balance"], [12, 3, 1, "", "model"], [12, 3, 1, "", "provider"], [12, 2, 1, "", "set_endpoint"], [12, 2, 1, "", "set_model"], [12, 2, 1, "", "set_provider"]], "unify.clients.Unify": [[12, 2, 1, "", "__init__"], [12, 3, 1, "", "endpoint"], [12, 2, 1, "", "generate"], [12, 2, 1, "", "get_credit_balance"], [12, 3, 1, "", "model"], [12, 3, 1, "", "provider"], [12, 2, 1, "", "set_endpoint"], [12, 2, 1, "", "set_model"], [12, 2, 1, "", "set_provider"]], "unify.exceptions": [[13, 4, 1, "", "AuthenticationError"], [13, 4, 1, "", "BadRequestError"], [13, 4, 1, "", "ConflictError"], [13, 4, 1, "", "InternalServerError"], [13, 4, 1, "", "NotFoundError"], [13, 4, 1, "", "PermissionDeniedError"], [13, 4, 1, "", "RateLimitError"], [13, 4, 1, "", "UnifyError"], [13, 4, 1, "", "UnprocessableEntityError"]], "unify.utils": [[14, 5, 1, "", "delete_dataset"], [14, 5, 1, "", "delete_evaluation"], [14, 5, 1, "", "download_dataset"], [14, 5, 1, "", "evaluate"], [14, 5, 1, "", "list_datasets"], [14, 5, 1, "", "list_endpoints"], [14, 5, 1, "", "list_evaluations"], [14, 5, 1, "", "list_models"], [14, 5, 1, "", "list_providers"], [14, 5, 1, "", "upload_dataset_from_dictionary"], [14, 5, 1, "", "upload_dataset_from_file"]]}, "objtypes": {"0": "py:module", "1": "py:class", "2": "py:method", "3": "py:property", "4": "py:exception", "5": "py:function"}, "objnames": {"0": ["py", "module", "Python module"], "1": ["py", "class", "Python class"], "2": ["py", "method", "Python method"], "3": ["py", "property", "Python property"], "4": ["py", "exception", "Python exception"], "5": ["py", "function", "Python function"]}, "titleterms": {"benchmark": [0, 9], "prepar": [0, 5], "your": [0, 2, 7, 8, 9], "dataset": [0, 5, 8], "how": 0, "doe": 0, "work": 0, "deploi": 1, "router": [1, 5, 7], "us": [1, 2], "base": 1, "optim": 1, "metric": 1, "defin": 1, "threshold": 1, "custom": [1, 5, 6, 7, 8], "round": [1, 2, 7, 8, 9], "up": [1, 2, 7, 8, 9], "make": 2, "first": 2, "request": [2, 6], "get": [2, 4, 15, 16], "kei": 2, "find": 2, "model": 2, "provid": 2, "queri": [2, 6], "an": 2, "endpoint": [2, 5, 6, 8, 9], "python": [2, 6, 20], "packag": [2, 6], "openai": [2, 6], "api": [2, 4, 6], "format": 2, "compat": 2, "tool": 2, "sdk": 2, "open": 2, "interpret": 2, "On": [3, 17, 18], "prem": [3, 17], "imag": 3, "refer": 4, "get_credit": 4, "post": 4, "chat": [4, 11], "complet": 4, "rout": 5, "what": 5, "i": 5, "llm": [5, 6], "foundat": 5, "filter": 5, "maximis": 5, "throughput": 5, "fine": 5, "tune": 5, "train": [5, 7], "beta": [5, 7, 8, 9], "univers": 6, "authent": 6, "http": 6, "unifi": [6, 15, 16], "nodej": 6, "bill": 6, "advanc": 6, "featur": 6, "fallback": 6, "build": 7, "connect": 8, "stack": 8, "prerequisit": 8, "ad": 8, "qualiti": 9, "runtim": 9, "run": 9, "own": 9, "client": 12, "except": 13, "util": 14, "welcom": [15, 16], "start": [15, 16], "access": 17, "sso": 18, "singl": 18, "sign": 18, "openapi": 19, "specif": 19, "librari": 20}, "envversion": {"sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "nbsphinx": 4, "sphinx": 60}, "alltitles": {"On-Prem access": [[17, "on-prem-access"]], "OpenAPI Specification": [[19, "openapi-specification"]], "SSO (Single Sign On)": [[18, "sso-single-sign-on"]], "Welcome to Unify!": [[15, "welcome-to-unify"], [16, "welcome-to-unify"]], "Getting Started": [[15, "getting-started"], [16, "getting-started"]], "API Reference": [[4, "api-reference"]], "GET /get_credits": [[4, "get-get-credits"]], "POST /chat/completions": [[4, "post-chat-completions"]], "Deploying a router": [[1, "deploying-a-router"]], "Using the base router": [[1, "using-the-base-router"]], "Optimizing a metric": [[1, "optimizing-a-metric"]], "Defining thresholds": [[1, "defining-thresholds"]], "Using a custom router": [[1, "using-a-custom-router"]], "Round Up": [[1, "round-up"], [2, "round-up"], [9, "round-up"], [8, "round-up"], [7, "round-up"]], "Making your first request": [[2, "making-your-first-request"]], "Getting a key": [[2, "getting-a-key"]], "Finding a model and provider": [[2, "finding-a-model-and-provider"]], "Querying an endpoint": [[2, "querying-an-endpoint"]], "Using the Python Package": [[2, "using-the-python-package"]], "Using the OpenAI API Format": [[2, "using-the-openai-api-format"]], "Compatible Tools": [[2, "compatible-tools"]], "OpenAI SDK": [[2, "openai-sdk"]], "Open Interpreter": [[2, "open-interpreter"]], "On-Prem Images": [[3, "on-prem-images"]], "Benchmarking": [[0, "benchmarking"]], "Preparing your dataset": [[0, "preparing-your-dataset"]], "Benchmarking your dataset": [[0, "benchmarking-your-dataset"]], "How does it work?": [[0, "how-does-it-work"]], "Benchmarking endpoints": [[9, "benchmarking-endpoints"]], "Quality benchmarks": [[9, "quality-benchmarks"], [9, "id4"]], "Runtime benchmarks": [[9, "runtime-benchmarks"], [9, "id2"]], "Running your own benchmarks (Beta)": [[9, "running-your-own-benchmarks-beta"]], "Connecting your stack": [[8, "connecting-your-stack"]], "Custom endpoints (Beta)": [[8, "custom-endpoints-beta"]], "Prerequisite": [[8, "prerequisite"]], "Adding the endpoints": [[8, "adding-the-endpoints"]], "Custom datasets": [[8, "custom-datasets"]], "Building a custom router": [[7, "building-a-custom-router"]], "Training a custom router (Beta)": [[7, "training-a-custom-router-beta"]], "Customizing your router (Beta)": [[7, "customizing-your-router-beta"]], "Universal API": [[6, "universal-api"]], "Authentication": [[6, "authentication"]], "Querying the API": [[6, "querying-the-api"]], "HTTP Request": [[6, "http-request"]], "Unify Python Package": [[6, "unify-python-package"]], "OpenAI Python Package": [[6, "openai-python-package"]], "OpenAI NodeJS Package": [[6, "openai-nodejs-package"]], "Billing": [[6, "billing"]], "Advanced features": [[6, "advanced-features"]], "Custom endpoints": [[6, "custom-endpoints"]], "LLM Fallbacks": [[6, "llm-fallbacks"]], "Routing": [[5, "routing"]], "What is LLM routing?": [[5, "what-is-llm-routing"]], "Foundation router": [[5, "foundation-router"]], "Filtering endpoints": [[5, "filtering-endpoints"]], "Maximising throughput": [[5, "maximising-throughput"]], "Fine-tuned custom router": [[5, "fine-tuned-custom-router"]], "Preparing a dataset": [[5, "preparing-a-dataset"]], "Training a router (beta)": [[5, "training-a-router-beta"]], "Python Library": [[20, "python-library"]], "Exceptions": [[13, "module-unify.exceptions"]], "Utils": [[14, "module-unify.utils"]], "Chat": [[11, "module-unify.chat"]], "Clients": [[12, "module-unify.clients"]]}, "indexentries": {"chatbot (class in unify.chat)": [[11, "unify.chat.ChatBot"]], "__init__() (unify.chat.chatbot method)": [[11, "unify.chat.ChatBot.__init__"]], "clear_chat_history() (unify.chat.chatbot method)": [[11, "unify.chat.ChatBot.clear_chat_history"]], "client (unify.chat.chatbot property)": [[11, "unify.chat.ChatBot.client"]], "endpoint (unify.chat.chatbot property)": [[11, "unify.chat.ChatBot.endpoint"]], "model (unify.chat.chatbot property)": [[11, "unify.chat.ChatBot.model"]], "module": [[11, "module-unify.chat"], [12, "module-unify.clients"], [13, "module-unify.exceptions"], [14, "module-unify.utils"]], "provider (unify.chat.chatbot property)": [[11, "unify.chat.ChatBot.provider"]], "run() (unify.chat.chatbot method)": [[11, "unify.chat.ChatBot.run"]], "set_client() (unify.chat.chatbot method)": [[11, "unify.chat.ChatBot.set_client"]], "set_endpoint() (unify.chat.chatbot method)": [[11, "unify.chat.ChatBot.set_endpoint"]], "set_model() (unify.chat.chatbot method)": [[11, "unify.chat.ChatBot.set_model"]], "set_provider() (unify.chat.chatbot method)": [[11, "unify.chat.ChatBot.set_provider"]], "unify.chat": [[11, "module-unify.chat"]], "asyncunify (class in unify.clients)": [[12, "unify.clients.AsyncUnify"]], "unify (class in unify.clients)": [[12, "unify.clients.Unify"]], "__init__() (unify.clients.asyncunify method)": [[12, "unify.clients.AsyncUnify.__init__"]], "__init__() (unify.clients.unify method)": [[12, "unify.clients.Unify.__init__"]], "endpoint (unify.clients.asyncunify property)": [[12, "unify.clients.AsyncUnify.endpoint"]], "endpoint (unify.clients.unify property)": [[12, "unify.clients.Unify.endpoint"]], "generate() (unify.clients.asyncunify method)": [[12, "unify.clients.AsyncUnify.generate"]], "generate() (unify.clients.unify method)": [[12, "unify.clients.Unify.generate"]], "get_credit_balance() (unify.clients.asyncunify method)": [[12, "unify.clients.AsyncUnify.get_credit_balance"]], "get_credit_balance() (unify.clients.unify method)": [[12, "unify.clients.Unify.get_credit_balance"]], "model (unify.clients.asyncunify property)": [[12, "unify.clients.AsyncUnify.model"]], "model (unify.clients.unify property)": [[12, "unify.clients.Unify.model"]], "provider (unify.clients.asyncunify property)": [[12, "unify.clients.AsyncUnify.provider"]], "provider (unify.clients.unify property)": [[12, "unify.clients.Unify.provider"]], "set_endpoint() (unify.clients.asyncunify method)": [[12, "unify.clients.AsyncUnify.set_endpoint"]], "set_endpoint() (unify.clients.unify method)": [[12, "unify.clients.Unify.set_endpoint"]], "set_model() (unify.clients.asyncunify method)": [[12, "unify.clients.AsyncUnify.set_model"]], "set_model() (unify.clients.unify method)": [[12, "unify.clients.Unify.set_model"]], "set_provider() (unify.clients.asyncunify method)": [[12, "unify.clients.AsyncUnify.set_provider"]], "set_provider() (unify.clients.unify method)": [[12, "unify.clients.Unify.set_provider"]], "unify.clients": [[12, "module-unify.clients"]], "authenticationerror": [[13, "unify.exceptions.AuthenticationError"]], "badrequesterror": [[13, "unify.exceptions.BadRequestError"]], "conflicterror": [[13, "unify.exceptions.ConflictError"]], "internalservererror": [[13, "unify.exceptions.InternalServerError"]], "notfounderror": [[13, "unify.exceptions.NotFoundError"]], "permissiondeniederror": [[13, "unify.exceptions.PermissionDeniedError"]], "ratelimiterror": [[13, "unify.exceptions.RateLimitError"]], "unifyerror": [[13, "unify.exceptions.UnifyError"]], "unprocessableentityerror": [[13, "unify.exceptions.UnprocessableEntityError"]], "unify.exceptions": [[13, "module-unify.exceptions"]], "delete_dataset() (in module unify.utils)": [[14, "unify.utils.delete_dataset"]], "delete_evaluation() (in module unify.utils)": [[14, "unify.utils.delete_evaluation"]], "download_dataset() (in module unify.utils)": [[14, "unify.utils.download_dataset"]], "evaluate() (in module unify.utils)": [[14, "unify.utils.evaluate"]], "list_datasets() (in module unify.utils)": [[14, "unify.utils.list_datasets"]], "list_endpoints() (in module unify.utils)": [[14, "unify.utils.list_endpoints"]], "list_evaluations() (in module unify.utils)": [[14, "unify.utils.list_evaluations"]], "list_models() (in module unify.utils)": [[14, "unify.utils.list_models"]], "list_providers() (in module unify.utils)": [[14, "unify.utils.list_providers"]], "unify.utils": [[14, "module-unify.utils"]], "upload_dataset_from_dictionary() (in module unify.utils)": [[14, "unify.utils.upload_dataset_from_dictionary"]], "upload_dataset_from_file() (in module unify.utils)": [[14, "unify.utils.upload_dataset_from_file"]]}}) \ No newline at end of file diff --git a/hub/tools/openapi.html b/hub/tools/openapi.html index bb5b0b3870..4a91249e6d 100644 --- a/hub/tools/openapi.html +++ b/hub/tools/openapi.html @@ -258,7 +258,6 @@
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    @@ -414,7 +413,6 @@

    OpenAPI SpecificationChat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    diff --git a/hub/tools/python_library.html b/hub/tools/python_library.html index 04ae536071..a8bcb23cfb 100644 --- a/hub/tools/python_library.html +++ b/hub/tools/python_library.html @@ -258,7 +258,6 @@
  • Chat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console

    @@ -414,7 +413,6 @@

    Python LibraryChat
  • Clients
  • Exceptions
    • -
  • Tests
  • Utils

    • Console