From d92c5ad71cb23a9dfd1b75d33a0007bfe1f8ae59 Mon Sep 17 00:00:00 2001 From: Krrish Dholakia Date: Sat, 22 Mar 2025 20:11:53 -0700 Subject: [PATCH] docs(index.md): completed documentation for new stable release --- .../docs/guides/security_settings.md | 66 +++++++++++++++++++ docs/my-website/docs/providers/ollama.md | 61 +++++++++++++++++ docs/my-website/docs/proxy/config_settings.md | 1 + .../release_notes/v1.63.14/index.md | 42 ++++++------ docs/my-website/sidebars.js | 1 + 5 files changed, 149 insertions(+), 22 deletions(-) create mode 100644 docs/my-website/docs/guides/security_settings.md diff --git a/docs/my-website/docs/guides/security_settings.md b/docs/my-website/docs/guides/security_settings.md new file mode 100644 index 0000000000..4dfeda2d70 --- /dev/null +++ b/docs/my-website/docs/guides/security_settings.md @@ -0,0 +1,66 @@ +import Tabs from '@theme/Tabs'; +import TabItem from '@theme/TabItem'; + +# SSL Security Settings + +If you're in an environment using an older TTS bundle, with an older encryption, follow this guide. + + +LiteLLM uses HTTPX for network requests, unless otherwise specified. + +1. Disable SSL verification + + + + + +```python +import litellm +litellm.ssl_verify = False +``` + + + +```yaml +litellm_settings: + ssl_verify: false +``` + + + + +```bash +export SSL_VERIFY="False" +``` + + + +2. Lower security settings + + + + +```python +import litellm +litellm.ssl_security_level = 1 +litellm.ssl_certificate = "/path/to/certificate.pem" +``` + + + +```yaml +litellm_settings: + ssl_security_level: 1 + ssl_certificate: "/path/to/certificate.pem" +``` + + + +```bash +export SSL_SECURITY_LEVEL="1" +export SSL_CERTIFICATE="/path/to/certificate.pem" +``` + + + + diff --git a/docs/my-website/docs/providers/ollama.md b/docs/my-website/docs/providers/ollama.md index 848be2beb7..21dfde9982 100644 --- a/docs/my-website/docs/providers/ollama.md +++ b/docs/my-website/docs/providers/ollama.md @@ -202,6 +202,67 @@ curl -X POST 'http://0.0.0.0:4000/chat/completions' \ + +## Using Ollama FIM on `/v1/completions` + +LiteLLM supports calling Ollama's `/api/generate` endpoint on `/v1/completions` requests. + + + + +```python +import litellm +litellm._turn_on_debug() # turn on debug to see the request +from litellm import completion + +response = completion( + model="ollama/llama3.1", + prompt="Hello, world!", + api_base="http://localhost:11434" +) +print(response) +``` + + + +1. Setup config.yaml + +```yaml +model_list: + - model_name: "llama3.1" + litellm_params: + model: "ollama/llama3.1" + api_base: "http://localhost:11434" +``` + +2. Start proxy + +```bash +litellm --config /path/to/config.yaml --detailed_debug + +# RUNNING ON http://0.0.0.0:4000 +``` + +3. Test it! + +```python +from openai import OpenAI + +client = OpenAI( + api_key="anything", # 👈 PROXY KEY (can be anything, if master_key not set) + base_url="http://0.0.0.0:4000" # 👈 PROXY BASE URL +) + +response = client.completions.create( + model="ollama/llama3.1", + prompt="Hello, world!", + api_base="http://localhost:11434" +) +print(response) +``` + + + ## Using ollama `api/chat` In order to send ollama requests to `POST /api/chat` on your ollama server, set the model prefix to `ollama_chat` diff --git a/docs/my-website/docs/proxy/config_settings.md b/docs/my-website/docs/proxy/config_settings.md index 71ea045fb1..0e85223d45 100644 --- a/docs/my-website/docs/proxy/config_settings.md +++ b/docs/my-website/docs/proxy/config_settings.md @@ -147,6 +147,7 @@ general_settings: |------|------|-------------| | completion_model | string | The default model to use for completions when `model` is not specified in the request | | disable_spend_logs | boolean | If true, turns off writing each transaction to the database | +| disable_spend_updates | boolean | If true, turns off all spend updates to the DB. Including key/user/team spend updates. | | disable_master_key_return | boolean | If true, turns off returning master key on UI. (checked on '/user/info' endpoint) | | disable_retry_on_max_parallel_request_limit_error | boolean | If true, turns off retries when max parallel request limit is reached | | disable_reset_budget | boolean | If true, turns off reset budget scheduled task | diff --git a/docs/my-website/release_notes/v1.63.14/index.md b/docs/my-website/release_notes/v1.63.14/index.md index 564687606c..f30231604a 100644 --- a/docs/my-website/release_notes/v1.63.14/index.md +++ b/docs/my-website/release_notes/v1.63.14/index.md @@ -59,7 +59,7 @@ Here's a Demo Instance to test changes: - Bedrock: Support bedrock application inference profiles [Docs](https://docs.litellm.ai/docs/providers/bedrock#bedrock-application-inference-profile) - Infer aws region from bedrock application profile id - (`arn:aws:bedrock:us-east-1:...`) -- Ollama - support calling via `/v1/completions` - [NEEDS DOCS]https://github.com/BerriAI/litellm/pull/9333 +- Ollama - support calling via `/v1/completions` [Get Started](../../docs/providers/ollama#using-ollama-fim-on-v1completions) - Bedrock - support `us.deepseek.r1-v1:0` model name [Docs](../../docs/providers/bedrock#supported-aws-bedrock-models) https://github.com/BerriAI/litellm/pull/9363 @@ -97,35 +97,33 @@ https://github.com/BerriAI/litellm/pull/9363 - Support post-call guardrails for streaming responses - https://github.com/BerriAI/litellm/commit/4a31b32a88b7729a032e58ab046079d17000087f [NEEDS DOCS] - Arize [Get Started](../../docs/observability/arize_integration) - - fix invalid package import - [PR](https://github.com/BerriAI/litellm/pull/9338) - - migrate to using standardloggingpayload for metadata, ensures spans land successfully - [PR](https://github.com/BerriAI/litellm/pull/9338) - - fix logging to just log the LLM I/O - [PR](https://github.com/BerriAI/litellm/pull/9353) - - Dynamic API Key/Space param support - [Get Started](../../docs/observability/arize_integration#pass-arize-spacekey-per-request) -- StandardLoggingPayload - Log litellm_model_name in payload. Allows knowing what the model sent to API provider was - [Get Started](../../docs/proxy/logging_spec#standardlogginghiddenparams) -- Prompt Management - Allow building custom prompt management integration - https://github.com/BerriAI/litellm/pull/9384 + - fix invalid package import [PR](https://github.com/BerriAI/litellm/pull/9338) + - migrate to using standardloggingpayload for metadata, ensures spans land successfully [PR](https://github.com/BerriAI/litellm/pull/9338) + - fix logging to just log the LLM I/O [PR](https://github.com/BerriAI/litellm/pull/9353) + - Dynamic API Key/Space param support [Get Started](../../docs/observability/arize_integration#pass-arize-spacekey-per-request) +- StandardLoggingPayload - Log litellm_model_name in payload. Allows knowing what the model sent to API provider was [Get Started](../../docs/proxy/logging_spec#standardlogginghiddenparams) +- Prompt Management - Allow building custom prompt management integration [Get Started](../../docs/proxy/custom_prompt_management.md) ## Performance / Reliability improvements -- Redis Caching - add 5s default timeout, prevents hanging redis connection from impacting llm calls - https://github.com/BerriAI/litellm/commit/db92956ae33ed4c4e3233d7e1b0c7229817159bf -- Allow disabling all spend updates / writes to DB - patch to allow disabling all spend updates to DB with a flag - https://github.com/BerriAI/litellm/pull/9331 -- Azure OpenAI - correctly re-use azure openai client - https://github.com/BerriAI/litellm/commit/f2026ef907c06d94440930917add71314b901413 -- Azure OpenAI - uses litellm.ssl_verify on Azure/OpenAI clients -- Usage-based routing - Wildcard model support https://github.com/BerriAI/litellm/pull/9355 -- Usage-based routing - Support batch writing increments to redis - reduces latency to same as ‘simple-shuffle’ - https://github.com/BerriAI/litellm/pull/9357 -- Router - show reason for model cooldown on ‘no healthy deployments available error’ - https://github.com/BerriAI/litellm/pull/9438 -- Caching - add max value limit to an item in in-memory cache (1MB) - prevents OOM errors on large image url’s being sent through proxy - https://github.com/BerriAI/litellm/pull/9448 +- Redis Caching - add 5s default timeout, prevents hanging redis connection from impacting llm calls [PR](https://github.com/BerriAI/litellm/commit/db92956ae33ed4c4e3233d7e1b0c7229817159bf) +- Allow disabling all spend updates / writes to DB - patch to allow disabling all spend updates to DB with a flag [PR](https://github.com/BerriAI/litellm/pull/9331) +- Azure OpenAI - correctly re-use azure openai client, fixes perf issue from previous Stable release [PR](https://github.com/BerriAI/litellm/commit/f2026ef907c06d94440930917add71314b901413) +- Azure OpenAI - uses litellm.ssl_verify on Azure/OpenAI clients [PR](https://github.com/BerriAI/litellm/commit/f2026ef907c06d94440930917add71314b901413) +- Usage-based routing - Wildcard model support [Get Started](../../docs/proxy/usage_based_routing#wildcard-model-support) +- Usage-based routing - Support batch writing increments to redis - reduces latency to same as ‘simple-shuffle’ [PR](https://github.com/BerriAI/litellm/pull/9357) +- Router - show reason for model cooldown on ‘no healthy deployments available error’ [PR](https://github.com/BerriAI/litellm/pull/9438) +- Caching - add max value limit to an item in in-memory cache (1MB) - prevents OOM errors on large image url’s being sent through proxy [PR](https://github.com/BerriAI/litellm/pull/9448) ## General Improvements -- Multiple OIDC Provider support - https://github.com/BerriAI/litellm/commit/324864b7750747ae40345def796c1578263f5896 - Passthrough Endpoints - support returning api-base on pass-through endpoints Response Headers [Docs](../../docs/proxy/response_headers#litellm-specific-headers) -- SSL - support reading ssl security level from env var - Allows user to specify lower security settings - https://github.com/BerriAI/litellm/pull/9330 -- Credentials - only poll Credentials table when `STORE_MODEL_IN_DB` is True - https://github.com/BerriAI/litellm/pull/9376 -- Image URL Handling - new architecture doc on image url handling - https://docs.litellm.ai/docs/proxy/image_handling -- OpenAI - bump to pip install "openai==1.68.2" - https://github.com/BerriAI/litellm/commit/e85e3bc52a9de86ad85c3dbb12d87664ee567a5a -- Gunicorn - security fix - bump gunicorn==23.0.0 # server dep - +- SSL - support reading ssl security level from env var - Allows user to specify lower security settings [Get Started](../../docs/guides/security_settings) +- Credentials - only poll Credentials table when `STORE_MODEL_IN_DB` is True [PR](https://github.com/BerriAI/litellm/pull/9376) +- Image URL Handling - new architecture doc on image url handling [Docs](../../docs/proxy/image_handling) +- OpenAI - bump to pip install "openai==1.68.2" [PR](https://github.com/BerriAI/litellm/commit/e85e3bc52a9de86ad85c3dbb12d87664ee567a5a) +- Gunicorn - security fix - bump gunicorn==23.0.0 [PR](https://github.com/BerriAI/litellm/commit/7e9fc92f5c7fea1e7294171cd3859d55384166eb) ## Complete Git Diff diff --git a/docs/my-website/sidebars.js b/docs/my-website/sidebars.js index 96267d09da..071410bc8a 100644 --- a/docs/my-website/sidebars.js +++ b/docs/my-website/sidebars.js @@ -243,6 +243,7 @@ const sidebars = { "exception_mapping", "completion/provider_specific_params", "guides/finetuned_models", + "guides/security_settings", "completion/audio", "completion/document_understanding", "completion/vision",