diff --git a/_downloads/ca9d3b7116524473d8adbde7cf15d167/arch_config_full_reference.yaml b/_downloads/ca9d3b7116524473d8adbde7cf15d167/arch_config_full_reference.yaml index 2206aa2e..1f97369a 100755 --- a/_downloads/ca9d3b7116524473d8adbde7cf15d167/arch_config_full_reference.yaml +++ b/_downloads/ca9d3b7116524473d8adbde7cf15d167/arch_config_full_reference.yaml @@ -32,7 +32,7 @@ endpoints: llm_providers: - name: OpenAI provider: openai - access_key: OPENAI_API_KEY + access_key: $OPENAI_API_KEY model: gpt-4o default: true stream: true @@ -47,7 +47,7 @@ llm_providers: - name: Mistral8x7b provider: mistral - access_key: MISTRAL_API_KEY + access_key: $MISTRAL_API_KEY model: mistral-8x7b - name: MistralLocal7b diff --git a/build_with_arch/agent.html b/build_with_arch/agent.html index 9e656c66..11cda46a 100755 --- a/build_with_arch/agent.html +++ b/build_with_arch/agent.html @@ -183,7 +183,7 @@ is how you would go about enabling this scenario with Arch:

8llm_providers: 9 - name: OpenAI 10 provider: openai -11 access_key: OPENAI_API_KEY +11 access_key: $OPENAI_API_KEY 12 model: gpt-3.5-turbo 13 default: true 14 @@ -316,7 +316,7 @@ the user’s intent.

 8llm_providers: 9 - name: OpenAI 10 provider: openai -11 access_key: OPENAI_API_KEY +11 access_key: $OPENAI_API_KEY 12 model: gpt-3.5-turbo 13 default: true 14 @@ -408,7 +408,7 @@ the user’s intent.

diff --git a/build_with_arch/rag.html b/build_with_arch/rag.html index 6ca1c498..5eab2c28 100755 --- a/build_with_arch/rag.html +++ b/build_with_arch/rag.html @@ -454,7 +454,7 @@ token cost and dramatically improve the speed of their responses back to users.< diff --git a/concepts/llm_provider.html b/concepts/llm_provider.html index 82b098eb..16ee9db3 100755 --- a/concepts/llm_provider.html +++ b/concepts/llm_provider.html @@ -174,7 +174,7 @@ across applications.

10llm_providers: 11 - name: OpenAI 12 provider: openai -13 access_key: OPENAI_API_KEY +13 access_key: $OPENAI_API_KEY 14 model: gpt-4o 15 default: true 16 stream: true @@ -245,7 +245,7 @@ make outbound LLM calls.

-

© 2024, Katanemo Labs, Inc Last updated: Oct 30, 2024. 

+

© 2024, Katanemo Labs, Inc Last updated: Oct 31, 2024. 

diff --git a/concepts/prompt_target.html b/concepts/prompt_target.html index 427bc564..b8b2420d 100755 --- a/concepts/prompt_target.html +++ b/concepts/prompt_target.html @@ -344,7 +344,7 @@ This modular approach not only simplifies your application’s architecture but
-

© 2024, Katanemo Labs, Inc Last updated: Oct 30, 2024. 

+

© 2024, Katanemo Labs, Inc Last updated: Oct 31, 2024. 

diff --git a/concepts/tech_overview/error_target.html b/concepts/tech_overview/error_target.html index 79972e72..095f265d 100755 --- a/concepts/tech_overview/error_target.html +++ b/concepts/tech_overview/error_target.html @@ -229,7 +229,7 @@ The errors are communicated to the application via headers like
-

© 2024, Katanemo Labs, Inc Last updated: Oct 30, 2024. 

+

© 2024, Katanemo Labs, Inc Last updated: Oct 31, 2024. 

diff --git a/concepts/tech_overview/listener.html b/concepts/tech_overview/listener.html index b4794771..fd9e71c1 100755 --- a/concepts/tech_overview/listener.html +++ b/concepts/tech_overview/listener.html @@ -191,7 +191,7 @@ address like arch.l 10llm_providers: 11 - name: OpenAI 12 provider: openai -13 access_key: OPENAI_API_KEY +13 access_key: $OPENAI_API_KEY 14 model: gpt-4o 15 default: true 16 stream: true @@ -233,7 +233,7 @@ address like arch.l
-

© 2024, Katanemo Labs, Inc Last updated: Oct 30, 2024. 

+

© 2024, Katanemo Labs, Inc Last updated: Oct 31, 2024. 

diff --git a/concepts/tech_overview/model_serving.html b/concepts/tech_overview/model_serving.html index 38d27251..2f7a703c 100755 --- a/concepts/tech_overview/model_serving.html +++ b/concepts/tech_overview/model_serving.html @@ -220,7 +220,7 @@ how to generate API keys for model serving

-

© 2024, Katanemo Labs, Inc Last updated: Oct 30, 2024. 

+

© 2024, Katanemo Labs, Inc Last updated: Oct 31, 2024. 

diff --git a/concepts/tech_overview/prompt.html b/concepts/tech_overview/prompt.html index 836471e3..9a2c4f64 100755 --- a/concepts/tech_overview/prompt.html +++ b/concepts/tech_overview/prompt.html @@ -195,7 +195,7 @@ ensuring that unauthorized or harmful behaviors are intercepted early in the pro 10llm_providers: 11 - name: OpenAI 12 provider: openai -13 access_key: OPENAI_API_KEY +13 access_key: $OPENAI_API_KEY 14 model: gpt-4o 15 default: true 16 stream: true @@ -239,7 +239,7 @@ when a user’s intent has changed so that you can build faster, more accurate R 10llm_providers: 11 - name: OpenAI 12 provider: openai -13 access_key: OPENAI_API_KEY +13 access_key: $OPENAI_API_KEY 14 model: gpt-4o 15 default: true 16 stream: true @@ -399,7 +399,7 @@ This setup allows you to take advantage of Arch’s advanced traffic management
-

© 2024, Katanemo Labs, Inc Last updated: Oct 30, 2024. 

+

© 2024, Katanemo Labs, Inc Last updated: Oct 31, 2024. 

diff --git a/concepts/tech_overview/request_lifecycle.html b/concepts/tech_overview/request_lifecycle.html index 2af653c3..6eca65a9 100755 --- a/concepts/tech_overview/request_lifecycle.html +++ b/concepts/tech_overview/request_lifecycle.html @@ -226,7 +226,7 @@ enables scaling to very high core count CPUs.

llm_providers: - name: OpenAI provider: openai - access_key: OPENAI_API_KEY + access_key: $OPENAI_API_KEY model: gpt-4o default: true stream: true @@ -399,7 +399,7 @@ processing request headers and then finalized by the HCM during post-request pro
-

© 2024, Katanemo Labs, Inc Last updated: Oct 30, 2024. 

+

© 2024, Katanemo Labs, Inc Last updated: Oct 31, 2024. 

diff --git a/concepts/tech_overview/tech_overview.html b/concepts/tech_overview/tech_overview.html index b72f2373..e0d47c57 100755 --- a/concepts/tech_overview/tech_overview.html +++ b/concepts/tech_overview/tech_overview.html @@ -216,7 +216,7 @@
-

© 2024, Katanemo Labs, Inc Last updated: Oct 30, 2024. 

+

© 2024, Katanemo Labs, Inc Last updated: Oct 31, 2024. 

diff --git a/concepts/tech_overview/terminology.html b/concepts/tech_overview/terminology.html index 4f0b196c..06e220c9 100755 --- a/concepts/tech_overview/terminology.html +++ b/concepts/tech_overview/terminology.html @@ -210,7 +210,7 @@ incoming prompts. The model server is designed to call the (fast) purpose-built
-

© 2024, Katanemo Labs, Inc Last updated: Oct 30, 2024. 

+

© 2024, Katanemo Labs, Inc Last updated: Oct 31, 2024. 

diff --git a/concepts/tech_overview/threading_model.html b/concepts/tech_overview/threading_model.html index de40bca8..c30b82e8 100755 --- a/concepts/tech_overview/threading_model.html +++ b/concepts/tech_overview/threading_model.html @@ -191,7 +191,7 @@ hardware threads on the machine.

-

© 2024, Katanemo Labs, Inc Last updated: Oct 30, 2024. 

+

© 2024, Katanemo Labs, Inc Last updated: Oct 31, 2024. 

diff --git a/get_started/intro_to_arch.html b/get_started/intro_to_arch.html index b79d14cf..3065d9d9 100755 --- a/get_started/intro_to_arch.html +++ b/get_started/intro_to_arch.html @@ -224,7 +224,7 @@ For more details, read
-

© 2024, Katanemo Labs, Inc Last updated: Oct 30, 2024. 

+

© 2024, Katanemo Labs, Inc Last updated: Oct 31, 2024. 

diff --git a/get_started/overview.html b/get_started/overview.html index 67db51cb..92759506 100755 --- a/get_started/overview.html +++ b/get_started/overview.html @@ -320,7 +320,7 @@ simplify the interaction with upstream LLMs, and improve observability all while
-

© 2024, Katanemo Labs, Inc Last updated: Oct 30, 2024. 

+

© 2024, Katanemo Labs, Inc Last updated: Oct 31, 2024. 

diff --git a/get_started/quickstart.html b/get_started/quickstart.html index 3589e950..75e8f4bc 100755 --- a/get_started/quickstart.html +++ b/get_started/quickstart.html @@ -208,7 +208,7 @@ Below is an example configuration to get you started, including:

llm_providers: - name: OpenAI provider: openai - access_key: OPENAI_API_KEY + access_key: $OPENAI_API_KEY model: gpt-4o default: true stream: true @@ -294,7 +294,7 @@ Below is an example configuration to get you started, including:

-

© 2024, Katanemo Labs, Inc Last updated: Oct 30, 2024. 

+

© 2024, Katanemo Labs, Inc Last updated: Oct 31, 2024. 

diff --git a/guides/function_calling.html b/guides/function_calling.html index 89964538..c86a7afb 100755 --- a/guides/function_calling.html +++ b/guides/function_calling.html @@ -427,7 +427,7 @@ By completing these setup steps, you enable Arch to manage the process from vali
-

© 2024, Katanemo Labs, Inc Last updated: Oct 30, 2024. 

+

© 2024, Katanemo Labs, Inc Last updated: Oct 31, 2024. 

diff --git a/guides/observability/access_logging.html b/guides/observability/access_logging.html index 0ad81bb1..2486b09c 100755 --- a/guides/observability/access_logging.html +++ b/guides/observability/access_logging.html @@ -239,7 +239,7 @@ Access logs can be exported to centralized logging systems (e.g., ELK stack or F
-

© 2024, Katanemo Labs, Inc Last updated: Oct 30, 2024. 

+

© 2024, Katanemo Labs, Inc Last updated: Oct 31, 2024. 

diff --git a/guides/observability/monitoring.html b/guides/observability/monitoring.html index 6380e3f4..11805e9e 100755 --- a/guides/observability/monitoring.html +++ b/guides/observability/monitoring.html @@ -182,7 +182,7 @@ token (TOT) metrics, and the total latency as perceived by users.

-

© 2024, Katanemo Labs, Inc Last updated: Oct 30, 2024. 

+

© 2024, Katanemo Labs, Inc Last updated: Oct 31, 2024. 

diff --git a/guides/observability/observability.html b/guides/observability/observability.html index 4b14e0b0..9ac5e177 100755 --- a/guides/observability/observability.html +++ b/guides/observability/observability.html @@ -199,7 +199,7 @@
-

© 2024, Katanemo Labs, Inc Last updated: Oct 30, 2024. 

+

© 2024, Katanemo Labs, Inc Last updated: Oct 31, 2024. 

diff --git a/guides/observability/tracing.html b/guides/observability/tracing.html index 300303a1..5684085e 100755 --- a/guides/observability/tracing.html +++ b/guides/observability/tracing.html @@ -528,7 +528,7 @@ tools like AWS X-Ray and Datadog, enhancing observability and facilitating faste
-

© 2024, Katanemo Labs, Inc Last updated: Oct 30, 2024. 

+

© 2024, Katanemo Labs, Inc Last updated: Oct 31, 2024. 

diff --git a/guides/prompt_guard.html b/guides/prompt_guard.html index f03d8dfa..9ebd37be 100755 --- a/guides/prompt_guard.html +++ b/guides/prompt_guard.html @@ -306,7 +306,7 @@ By implementing Prompt Guard, developers can provide a robust layer of input val
-

© 2024, Katanemo Labs, Inc Last updated: Oct 30, 2024. 

+

© 2024, Katanemo Labs, Inc Last updated: Oct 31, 2024. 

diff --git a/index.html b/index.html index 38c3adb4..077a0c92 100755 --- a/index.html +++ b/index.html @@ -241,7 +241,7 @@ Resources
-

© 2024, Katanemo Labs, Inc Last updated: Oct 30, 2024. 

+

© 2024, Katanemo Labs, Inc Last updated: Oct 31, 2024. 

diff --git a/resources/configuration_reference.html b/resources/configuration_reference.html index d5d3ca7d..1017d916 100755 --- a/resources/configuration_reference.html +++ b/resources/configuration_reference.html @@ -193,7 +193,7 @@ that they can spend more of their time in building features unique to their AI e 32llm_providers: 33 - name: OpenAI 34 provider: openai - 35 access_key: OPENAI_API_KEY + 35 access_key: $OPENAI_API_KEY 36 model: gpt-4o 37 default: true 38 stream: true @@ -208,7 +208,7 @@ that they can spend more of their time in building features unique to their AI e 47 48 - name: Mistral8x7b 49 provider: mistral - 50 access_key: MISTRAL_API_KEY + 50 access_key: $MISTRAL_API_KEY 51 model: mistral-8x7b 52 53 - name: MistralLocal7b @@ -286,7 +286,7 @@ that they can spend more of their time in building features unique to their AI e
-

© 2024, Katanemo Labs, Inc Last updated: Oct 30, 2024. 

+

© 2024, Katanemo Labs, Inc Last updated: Oct 31, 2024. 

diff --git a/search.html b/search.html index e70bf614..ddf3d6b9 100755 --- a/search.html +++ b/search.html @@ -211,7 +211,7 @@