15 Releases published by 1 person

• v1.46.1.dev2

  published Sep 17, 2024

• v1.46.2

  published Sep 18, 2024

• v1.46.4

  published Sep 18, 2024

• v1.46.5

  published Sep 18, 2024

• v1.46.6

  published Sep 19, 2024

• v1.46.7

  published Sep 20, 2024

• v1.46.8

  published Sep 20, 2024

• v1.47.0

  published Sep 21, 2024

• v1.47.1

  published Sep 22, 2024

• v1.47.2

  published Sep 23, 2024

• v1.47.2.dev1

  published Sep 23, 2024

• v1.47.2.dev4

  published Sep 23, 2024

• v1.47.2.dev5

  published Sep 24, 2024

• v1.48.0

  published Sep 24, 2024

• v1.48.0.dev1

  published Sep 24, 2024

59 Pull requests merged by 9 people

• [Admin UI - Proxy] Add Deepseek as a provider

  #5857 merged Sep 24, 2024

• Update the dockerignore file

  #5863 merged Sep 24, 2024

• LiteLLM Minor Fixes & Improvements (09/23/2024)

  #5842 merged Sep 24, 2024

• [Docker-Security Fix] - handle debian issue on docker builds

  #5752 merged Sep 24, 2024

• [Feat] Admin UI - Add Service Accounts

  #5855 merged Sep 24, 2024

• [Feat UI sso] store 'provider' in user metadata

  #5856 merged Sep 24, 2024

• [Feat-Proxy] add service accounts backend

  #5852 merged Sep 23, 2024

• [Feat] SSO - add provider in the OpenID field for custom sso

  #5849 merged Sep 23, 2024

• [UI Fix] List all teams on UI when user is Admin

  #5851 merged Sep 23, 2024

• [Testing-Proxy] Add E2E Admin UI testing

  #5845 merged Sep 23, 2024

• feat(vertex): Use correct provider for response_schema support check

  #5815 merged Sep 22, 2024

• Cost tracking improvements

  #5828 merged Sep 22, 2024

• LiteLLM Minor Fixes & Improvements (09/21/2024)

  #5819 merged Sep 22, 2024

• [Fix] virtual key auth checks on vertex ai pass through endpoints

  #5827 merged Sep 22, 2024

• [fix-sso] Allow internal user viewer to view usage routes

  #5825 merged Sep 21, 2024

• Fix premium user check on key creation

  #5826 merged Sep 21, 2024

• [SSO-UI] Set new sso users as internal_view role users

  #5824 merged Sep 21, 2024

• [Feat] Allow setting custom arize endpoint

  #5709 merged Sep 21, 2024

• [Feat] Prometheus - show status code and class type on prometheus

  #5806 merged Sep 21, 2024

• [Feat] Add testing for prometheus failure metrics

  #5823 merged Sep 21, 2024

• [Feat] Allow setting supports_vision for Custom OpenAI endpoints + Added testing

  #5821 merged Sep 21, 2024

• Litellm disable keys

  #5814 merged Sep 21, 2024

• Fixed DeepSeek input and output tokens

  #5718 merged Sep 21, 2024

• Correct casing

  #5817 merged Sep 21, 2024

• [Feat] Add fireworks AI embedding

  #5812 merged Sep 21, 2024

• LiteLLM Minor Fixes & Improvements (09/20/2024)

  #5807 merged Sep 21, 2024

• refactor: cleanup root of repo

  #5813 merged Sep 21, 2024

• [Feat-Proxy] Allow using custom sso handler

  #5809 merged Sep 21, 2024

• [Fix] log update_db statement in .debug() mode

  #5810 merged Sep 21, 2024

• [Fix] Tag Based Routing not work with wildcard routing

  #5805 merged Sep 20, 2024

• LiteLLM Minor Fixes & Improvements (09/19/2024)

  #5793 merged Sep 20, 2024

• ui fix correct team not loading

  #5804 merged Sep 20, 2024

• [Feat] Add Error Handling for /key/list endpoint

  #5787 merged Sep 20, 2024

• [ Proxy - User Management]: If user assigned to a team don't show Default Team

  #5791 merged Sep 20, 2024

• [Feat] Add proxy level prometheus metrics

  #5789 merged Sep 20, 2024

• [Chore-Docs] fix curl on /get team info swagger

  #5792 merged Sep 19, 2024

• test: replace gpt-3.5-turbo-0613 (deprecated model)

  #5794 merged Sep 19, 2024

• [Feat] Add Azure gpt-35-turbo-0301 pricing

  #5790 merged Sep 19, 2024

• LiteLLM Minor Fixes & Improvements (09/18/2024)

  #5772 merged Sep 19, 2024

• [Feat] add Groq gemma2 9b pricing

  #5788 merged Sep 19, 2024

• [Fix-Bedrock] use Bedrock converse for "meta.llama3-8b-instruct-v1:0", "meta.llama3-70b-instruct-v1:0"

  #5729 merged Sep 19, 2024

• feat(prometheus_api.py): support querying prometheus metrics for all-up + key-level spend on UI

  #5782 merged Sep 19, 2024

• Databricks Integration: Integrate Databricks SDK as optional mechanism for fetching API base and token, if unspecified

  #5746 merged Sep 19, 2024

• [Feat- prometheus] track input and output tokens

  #5780 merged Sep 19, 2024

• [Fix-Proxy] Enforce Virtual Key Auth on /vertex-ai/, /bedrock, passthrough endpoints

  #5779 merged Sep 18, 2024

• [Chore-Proxy] enforce jwt auth as enterprise feature

  #5770 merged Sep 18, 2024

• [Chore LiteLLM Proxy] enforce prometheus metrics as enterprise feature

  #5769 merged Sep 18, 2024

• [Feat-Proxy] Add Azure Assistants API - Create Assistant, Delete Assistant Support

  #5777 merged Sep 18, 2024

• [Prometheus] track requested model

  #5774 merged Sep 18, 2024

• [Feat - GCS Bucket Logger] Use StandardLoggingPayload

  #5771 merged Sep 18, 2024

• Additional Fixes (09/17/2024)

  #5759 merged Sep 18, 2024

• LiteLLM Minor Fixes & Improvements (09/17/2024)

  #5742 merged Sep 18, 2024

• [Feat] Log Request metadata on gcs bucket logging

  #5743 merged Sep 18, 2024

• [Fix] Router/ Proxy - Tag Based routing, raise correct error when no deployments found and tag filtering is on

  #5745 merged Sep 18, 2024

• [Feat-Proxy-DataDog] Log Redis, Postgres Failure events on DataDog

  #5750 merged Sep 18, 2024

• [Fix] o1-mini causes pydantic warnings on reasoning_tokens

  #5754 merged Sep 18, 2024

• Bump next from 14.1.1 to 14.2.10 in /ui/litellm-dashboard

  #5753 merged Sep 18, 2024

• Litellm fix router testing

  #5748 merged Sep 18, 2024

• Fix hardcoding of schema in view check

  #5749 merged Sep 17, 2024

16 Pull requests opened by 8 people

• Log assistants API calls to cloudwatch

  #5761 opened Sep 18, 2024

• Merge: #5815- feat(vertex): Use correct provider for response_schema support check

  #5829 opened Sep 22, 2024

• [Prometheus Testing] Add tests for litellm_input_tokens_total, litellm_output_tokens_total, litellm_total_tokens_total

  #5841 opened Sep 23, 2024

• Add REST API examples to Vision documentation

  #5844 opened Sep 23, 2024

• fix deserialization error when using gpt-4o-mini

  #5848 opened Sep 23, 2024

• LiteLLM Minor Fixes & Improvements (09/23/2024) (#5842)

  #5858 opened Sep 24, 2024

• Upgrade dependencies in dockerfile

  #5862 opened Sep 24, 2024

• Update some of the python dependencies

  #5864 opened Sep 24, 2024

• Update some of the python dependencies connected to llms

  #5865 opened Sep 24, 2024

• Upgrade prism lib

  #5866 opened Sep 24, 2024

• Upgrade python packages

  #5867 opened Sep 24, 2024

• Upgrade poetry lock file

  #5868 opened Sep 24, 2024

• Install curl to be used for AWS ECS health check

  #5869 opened Sep 24, 2024

• Update litellm helm envconfigmap

  #5872 opened Sep 24, 2024

• Add new Gemini models

  #5874 opened Sep 24, 2024

• [Fix] OTEL - Don't log messages when callback settings disable message logging

  #5875 opened Sep 24, 2024

41 Issues closed by 8 people

• [Bug]: prisma.errors.DataError: The column `requester_ip_address` does not exist in the current database.

  #4876 closed Sep 24, 2024

• [Feature]: Cloudflare AI Gateway support for Google Vertex AI

  #3732 closed Sep 24, 2024

• [Bug]: Ollama provider missing api_key

  #5832 closed Sep 22, 2024

• [Feature]: `supports_prompt_caching` property for LMs

  #5776 closed Sep 22, 2024

• [Feature]: Add enable and disable features for the model and Virtual Keys

  #5328 closed Sep 22, 2024

• [Bug]: Latest release broke virtual key creation

  #5820 closed Sep 21, 2024

• [Bug]: Vertex gemini-pro-vision error using LiteLLM SDK

  #5768 closed Sep 21, 2024

• [Feature]: Add Auto-discovery of "*" models when calling /models and /v1/model/info

  #5818 closed Sep 21, 2024

• [Feature]: Add Fireworks AI Embedding

  #5797 closed Sep 21, 2024

• [Bug]: `stream_options` with fake streaming

  #5803 closed Sep 21, 2024

• Support CONFIG_FILE_PATH for proxy (Easier Azure container deployment)

  #5744 closed Sep 21, 2024

• [Bug]: incorrect kwarg in Routing Strategies docs

  #5808 closed Sep 21, 2024

• [Bug]: Break for google gemini

  #5798 closed Sep 21, 2024

• [Bug]:

  #5811 closed Sep 21, 2024

• [Bug]: Tag Based Routing not work with wildcard routing

  #5801 closed Sep 20, 2024

• Unknown error was encountered while running the model

  #5800 closed Sep 20, 2024

• [Bug]: Visiting "Usage" in the UI causes a server error

  #5756 closed Sep 20, 2024

• This Litellm not working for me i made too difficult to use llms like gemini-1.5-pro please just remove this from every where

  #5802 closed Sep 20, 2024

• [Proxy-UI]:For Each API Key show how many errors/success API calls

  #2455 closed Sep 20, 2024

• [Proxy-UI]:For Each API Key show cache hits

  #2454 closed Sep 20, 2024

• [11/03/2024 - 18/03/2024] New Models/Endpoints/Providers/Improvements

  #2449 closed Sep 20, 2024

• [Feature]: ability to see how much capacity is remaining before hitting quota

  #3323 closed Sep 20, 2024

• [Bug]: Prometheus monitors the number of requests collected in Azure OpenAI

  #4617 closed Sep 20, 2024

• [Feature]: Proxy - User Management: If user assigned to a team don't show Default Team

  #5696 closed Sep 20, 2024

• [Bug]: Broken `More details` links on main documentation page

  #5760 closed Sep 19, 2024

• [Bug]: model list api_key leak

  #5762 closed Sep 19, 2024

• LiteLLM does redis sentinel support?

  #4381 closed Sep 19, 2024

• [Bug]: azure_ad_token not passed in header when stream=True

  #5767 closed Sep 19, 2024

• [Feature]: Convert OpenAI list-content into open-source compatible string type

  #5755 closed Sep 19, 2024

• [Bug]: Can't use image urls that redirects (with Anthropic models)

  #5763 closed Sep 19, 2024

• [Bug]: Docker Compose docs unclear in terms of config.yaml if NOT using DB

  #5739 closed Sep 19, 2024

• [Bug]: Fireworks models are missing from `model_prices_and_context_window.json`

  #4570 closed Sep 19, 2024

• [Bug]: Gemma 2 on Groq missing in pricing

  #5785 closed Sep 19, 2024

• [Bug]: LlamaIndex call OpenAI Like Api got err : NotFoundError 404

  #5784 closed Sep 19, 2024

• [Bug]: deepcopy Causes Error with pydantic_core._pydantic_core.SerializationIterator Object

  #5684 closed Sep 19, 2024

• [Bug]: Docs don't appear to include the /fallback/login endpoint

  #5778 closed Sep 18, 2024

• [Bug]: The 429 error code hides the real cause.

  #5764 closed Sep 18, 2024

• LiteLLM Proxy Startup Error: TypeError in check_view_exists()

  #5702 closed Sep 18, 2024

• [Bug]: Azure_AI not supported for rerank models

  #5667 closed Sep 18, 2024

• [Feature]: Langchain / Smith Logging Integration doesn't appear to expose errors/metadata

  #5738 closed Sep 18, 2024

• [Bug]: o1-mini causes pydantic warnings on `reasoning_tokens`

  #5669 closed Sep 18, 2024

29 Issues opened by 22 people

• [Bug]: LiteLLM ProxyConfig behaves abnormally when using vllm OpenAI-Compatible Endpoints

  #5876 opened Sep 24, 2024

• Error while using ollama llama3.1

  #5871 opened Sep 24, 2024

• [Feature]: Azure ai studio support embedding models

  #5861 opened Sep 24, 2024

• [Feature]: Health Endpoint to Power Latency-Based Routing

  #5860 opened Sep 24, 2024

• [Feature]: Time To First Token Timeout

  #5859 opened Sep 24, 2024

• [Bug]: `openai==1.47` breaks CI

  #5854 opened Sep 23, 2024

• [Bug]: Proxy: Constant "Provider NOT provided" errors in log on invalid model name, no way to stop them

  #5853 opened Sep 23, 2024

• [Bug]: inconsistent `max_tokens` for Bedrock Anthropic Claude 3.5 Sonnet

  #5850 opened Sep 23, 2024

• [Bug]: CompletionTokensDetails is not JSON serializable

  #5847 opened Sep 23, 2024

• [Feature]: Allow creating service account keys

  #5846 opened Sep 23, 2024

• [Feature]: Allow `configurable_clientside_parameters` for switching b/w finetuning models easily

  #5843 opened Sep 23, 2024

• [Bug]: AttributeError: 'LangFuseLogger' object has no attribute 'upstream_langfuse_debug'

  #5840 opened Sep 23, 2024

• [Bug]: Groq - Tool / Function Calling Example throws function_call is not nullable error

  #5839 opened Sep 23, 2024

• [Bug]: Prisma trying to write to read-only `site-packages/prisma` in non_root image

  #5838 opened Sep 23, 2024

• [Bug]: Missing pricing for mistral/pixtral-12b-2409

  #5837 opened Sep 23, 2024

• [Feature]: improved diagnostic logging for invalid requests (litellm-proxy)

  #5836 opened Sep 23, 2024

• Dual GPU dual models load balancing with liteLLM, but performance can't be doubled

  #5835 opened Sep 23, 2024

• [Bug]: Helm Chart doesn't work

  #5830 opened Sep 22, 2024

• [Bug]: Model Status Healthy |Curl works - But when called from application using litellm completions or openai completion - ServiceUnavailableError

  #5822 opened Sep 21, 2024

• [Bug]: Need to reduce parallel requests for health check based on model provider (i.e. ollama)

  #5816 opened Sep 21, 2024

• [Feature]: Add support for CRUD operations on AzureOpenAI Vector Stores

  #5799 opened Sep 20, 2024

• [Feature]: Add logging callbacks for assistants API

  #5796 opened Sep 19, 2024

• [Bug]: Router not respecting TPM limits in concurrent async calls

  #5783 opened Sep 19, 2024

• [Bug]: wildcard model vendor weight bug

  #5781 opened Sep 19, 2024

• [Feature]: Support cloud zero cost tracking

  #5773 opened Sep 18, 2024

• [Feature]: JSON can be passed to the Gemini API

  #5766 opened Sep 18, 2024

• [Feature]: Allow setting guardrails default on

  #5758 opened Sep 18, 2024

• [Feature]: Add unit test for Gemini / Google AI Studio + Cloudflare AI Gateway

  #5757 opened Sep 18, 2024

• [Feature]: Use stream_options on Azure OpenAI

  #5751 opened Sep 17, 2024

115 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• Keywords AI Integration

  #5130 commented on Sep 20, 2024 • 5 new comments

• Upgrade dependencies

  #5665 commented on Sep 24, 2024 • 2 new comments

• Update ollama.py

  #4752 commented on Sep 19, 2024 • 0 new comments

• feat: read chat-template from tokenizer files for vllm

  #4737 commented on Sep 19, 2024 • 0 new comments

• fix(factory.py): Filter out empty messages before making llm api call

  #4678 commented on Sep 19, 2024 • 0 new comments

• Proxy (health endpoints): Add `/health/db endpoint` w/ Prisma metrics

  #4660 commented on Sep 19, 2024 • 0 new comments

• Solving the return value format issue during multiple function calls with the LLaMA 3 model.

  #4636 commented on Sep 19, 2024 • 0 new comments

• fix(azure.py): Allow using Cloudflare AI gateway for embedding

  #4629 commented on Sep 19, 2024 • 0 new comments

• fix(parallel_request_limiter.py): support spend tracking caching across multiple instances

  #4396 commented on Sep 19, 2024 • 0 new comments

• ci(config.yml): add pytest-xdist

  #4343 commented on Sep 19, 2024 • 0 new comments

• Linting Refactor: New `ModelResponseChunk` for streaming

  #4219 commented on Sep 19, 2024 • 0 new comments

• Use presigned urls for S3 cache

  #4190 commented on Sep 19, 2024 • 0 new comments

• Clarifai: Fixed model name error and streaming

  #4170 commented on Sep 19, 2024 • 0 new comments

• Fix black at circle ci

  #4161 commented on Sep 19, 2024 • 0 new comments

• astra-assistants api support

  #4118 commented on Sep 19, 2024 • 0 new comments

• `assistants.md`: Add `user_api_end_user_max_budget` metadata to `litellm_params`

  #4113 commented on Sep 19, 2024 • 0 new comments

• Fix: Trim message break possible infinite loop

  #4090 commented on Sep 19, 2024 • 0 new comments

• Added type hints for model_list parameter in RouterConfig

  #4074 commented on Sep 19, 2024 • 0 new comments

• Improve prediction response method

  #4073 commented on Sep 19, 2024 • 0 new comments

• Fix the workflow to update the price

  #4045 commented on Sep 19, 2024 • 0 new comments

• feat(router.py): set default priority

  #3998 commented on Sep 19, 2024 • 0 new comments

• fix(http_handler.py): fix async client ssl verify

  #3985 commented on Sep 19, 2024 • 0 new comments

• Code duplication in Handling Responses

  #3960 commented on Sep 19, 2024 • 0 new comments

• Fix function call arg

  #3917 commented on Sep 19, 2024 • 0 new comments

• Feature/improved semantic cache

  #3907 commented on Sep 19, 2024 • 0 new comments

• Support DashScope Compatible API For Qwen Series Models

  #3758 commented on Sep 19, 2024 • 0 new comments

• Fixes #542 allow system messages + chat for palm api

  #3718 commented on Sep 19, 2024 • 0 new comments

• Add support for upserting users automatically to a default team based on JWT key

  #3717 commented on Sep 19, 2024 • 0 new comments

• Clean up prod prints - Convert print to log

  #3667 commented on Sep 19, 2024 • 0 new comments

• Fix base_url for replicate's http api

  #2434 commented on Sep 19, 2024 • 0 new comments

• drop imghdr

  #5736 commented on Sep 19, 2024 • 0 new comments

• Add Support for Custom Providers in Vision and Function Call Utils

  #5688 commented on Sep 24, 2024 • 0 new comments

• [Feat] Added Opik integration for logging and evaluation

  #5680 commented on Sep 19, 2024 • 0 new comments

• Bump the github-actions group across 1 directory with 6 updates

  #5670 commented on Sep 23, 2024 • 0 new comments

• Updates and improvements to watsonx provider

  #5654 commented on Sep 19, 2024 • 0 new comments

• Feat: Add Literal AI Integration

  #5653 commented on Sep 23, 2024 • 0 new comments

• [Pricing] Adjust Ollama models to chat instead of completions

  #5595 commented on Sep 19, 2024 • 0 new comments

• Fixed #5559 (asyncio tasks get detroyed while pending sometimes)

  #5561 commented on Sep 19, 2024 • 0 new comments

• Bump cryptography from 42.0.7 to 43.0.1

  #5496 commented on Sep 19, 2024 • 0 new comments

• Solving budget info update if the budget id exists

  #5465 commented on Sep 19, 2024 • 0 new comments

• Litellm azure ad token common helper

  #5440 commented on Sep 24, 2024 • 0 new comments

• Use patch instead of apatch for instructor

  #5404 commented on Sep 19, 2024 • 0 new comments

• Litellm current branch

  #5398 commented on Sep 19, 2024 • 0 new comments

• [Feat] add google ai studio ft models

  #5373 commented on Sep 19, 2024 • 0 new comments

• Fix regression ignoring SSL_VERIFY boolean values being set through e…

  #5361 commented on Sep 19, 2024 • 0 new comments

• Feat: Add Langtrace integration

  #5341 commented on Sep 19, 2024 • 0 new comments

• Update team_endpoints.py

  #5269 commented on Sep 19, 2024 • 0 new comments

• Fixes priority queue comparison to work with Redis cache enabled

  #5268 commented on Sep 19, 2024 • 0 new comments

• Add support for getAssistant endpoint

  #5155 commented on Sep 19, 2024 • 0 new comments

• fix: PII output parsing for multiple entities of same type

  #5068 commented on Sep 19, 2024 • 0 new comments

• Optimize Alpine Dockerfile by removing redundant apk commands

  #5016 commented on Sep 19, 2024 • 0 new comments

• Add `extra_headers` support for Databricks completion requests

  #5006 commented on Sep 19, 2024 • 0 new comments

• fix(spend_tracking): `/spend/logs` with no filter

  #4998 commented on Sep 19, 2024 • 0 new comments

• Integrating Not Diamond with LiteLLM

  #4971 commented on Sep 19, 2024 • 0 new comments

• fix parsing multi tool calls in stream_chunk_builder

  #4936 commented on Sep 19, 2024 • 0 new comments

• Print each model only once on startup

  #4867 commented on Sep 19, 2024 • 0 new comments

• Control running lakera prompt checks - pre api call OR in parallel

  #4832 commented on Sep 19, 2024 • 0 new comments

• Add `--config` arg to k8s Deployment example in docs

  #4795 commented on Sep 19, 2024 • 0 new comments

• chore(helm-chart): use default environment variable for master key

  #2432 commented on Sep 19, 2024 • 0 new comments

• fix(proxy_server.py): more efficient verification_token GET request

  #2392 commented on Sep 19, 2024 • 0 new comments

• [WIP] fix claude alternating messages

  #2374 commented on Sep 19, 2024 • 0 new comments

• fix(proxy_server.py): add better debug logging for sso callbacks

  #1965 commented on Sep 19, 2024 • 0 new comments

• allow users to create their own keys

  #1870 commented on Sep 19, 2024 • 0 new comments

• fix(caching.py): add more debug statements for caching

  #1858 commented on Sep 19, 2024 • 0 new comments

• ci: added typechecking

  #1537 commented on Sep 24, 2024 • 0 new comments

• fix(ollama): metrics handling

  #1514 commented on Sep 19, 2024 • 0 new comments

• feat(proxy_server.py): new /user/export endpoint

  #1486 commented on Sep 19, 2024 • 0 new comments

• Litellm user budget fix

  #1479 commented on Sep 19, 2024 • 0 new comments

• chore: sort imports using isort

  #1405 commented on Sep 19, 2024 • 0 new comments

• Format using black, change black within circleci to --check

  #1363 commented on Sep 19, 2024 • 0 new comments

• fix(utils.py): support complete_response=true for text completion streaming

  #1358 commented on Sep 19, 2024 • 0 new comments

• (feat) added experiemental guidance function calling

  #1258 commented on Sep 19, 2024 • 0 new comments

• feat: add aphrodite support

  #1153 commented on Sep 19, 2024 • 0 new comments

• Added CLOVA studio Hyperclova X API support

  #853 commented on Sep 19, 2024 • 0 new comments

• add function call response parser for non openai models

  #768 commented on Sep 19, 2024 • 0 new comments

• router.py fixes

  #721 commented on Sep 19, 2024 • 0 new comments

• [Bug]: Re-add/fix upstream Langfuse support

  #3731 commented on Sep 24, 2024 • 0 new comments

• [Feature]: Upgrade python & general dependencies

  #5630 commented on Sep 24, 2024 • 0 new comments

• New Models/Endpoints/Providers

  #4922 commented on Sep 24, 2024 • 0 new comments

• [Bug]: Missing mode when adding a model via UI

  #5270 commented on Sep 20, 2024 • 0 new comments

• [Feature]: Add support for reading secrets from Hashicorp vault

  #2815 commented on Sep 20, 2024 • 0 new comments

• [Bug]: In litellm version 1.46.1, AnthropicException thrown when making calls with tools

  #5747 commented on Sep 19, 2024 • 0 new comments

• Add aws knowledgebase support

  #4840 commented on Sep 18, 2024 • 0 new comments

• [Feature-Master List]: O-1 Support

  #5672 commented on Sep 18, 2024 • 0 new comments

• [Feature]: support dbrx client for getting credentials in spark notebooks

  #5732 commented on Sep 17, 2024 • 0 new comments

• 🎅 I WISH LITELLM HAD...

  #361 commented on Sep 17, 2024 • 0 new comments

• [Optimize] Optimize the code for remove time complexity in llms bedro…

  #3665 commented on Sep 19, 2024 • 0 new comments

• Adding multiple public keys test

  #3649 commented on Sep 19, 2024 • 0 new comments

• Fixed JWT public key finding

  #3648 commented on Sep 19, 2024 • 0 new comments

• fix: remove --accept_data_loss flag

  #3565 commented on Sep 19, 2024 • 0 new comments

• fix(router.py): fix default cooldown time to be 60s

  #3529 commented on Sep 19, 2024 • 0 new comments

• Fix exception handling gemini

  #3493 commented on Sep 19, 2024 • 0 new comments

• feat(bedrock.py): Add Cloudflare AI Gateway support

  #3467 commented on Sep 19, 2024 • 0 new comments

• fixes #3264 and adds team_alias to /global/spend/teams

  #3454 commented on Sep 19, 2024 • 0 new comments

• Supporting api key from the headers as well

  #3418 commented on Sep 19, 2024 • 0 new comments

• fix(main.py): use model_api_key determined from get_api_key

  #3348 commented on Sep 19, 2024 • 0 new comments

• Support dashscope API for Qwen models

  #3344 commented on Sep 19, 2024 • 0 new comments

• OpenAI chat completion message type annotation

  #3284 commented on Sep 19, 2024 • 0 new comments

• fix(router.py): check cache hits before making router.completion calls

  #3227 commented on Sep 19, 2024 • 0 new comments

• Litellm fix async text completions

  #3215 commented on Sep 19, 2024 • 0 new comments

• fix(main.py): support 'custom_llm_provider' in acompletion

  #3121 commented on Sep 19, 2024 • 0 new comments

• The Spark API supports the completion method from the Litellm

  #3058 commented on Sep 19, 2024 • 0 new comments

• fix: fix embedding response to return pydantic object

  #2784 commented on Sep 19, 2024 • 0 new comments

• Fix bug where 'custom_llm_provider' argument is not passed correctly in 'acompletion'

  #2758 commented on Sep 19, 2024 • 0 new comments

• fix(utils.py): default usage tokens to 0

  #2736 commented on Sep 19, 2024 • 0 new comments

• [NEW-MODEL] Add Solar model

  #2717 commented on Sep 19, 2024 • 0 new comments

• feat(main.py): support calling text completione endpoint for openai compatible providers

  #2709 commented on Sep 19, 2024 • 0 new comments

• (feat) allow users to opt out of message merge - Anthropic

  #2671 commented on Sep 19, 2024 • 0 new comments

• fix(main.py): Correctly route to `/completions` (if supported) when called for openai-compatible endpoints

  #2595 commented on Sep 19, 2024 • 0 new comments

• add Lite llm docker proxy (Gemini ver)

  #2574 commented on Sep 19, 2024 • 0 new comments

• add JP readme & docker minimal

  #2569 commented on Sep 19, 2024 • 0 new comments

• support ZhipuAI models

  #2514 commented on Sep 19, 2024 • 0 new comments

• Integration with Canonical Neural Cache

  #2504 commented on Sep 19, 2024 • 0 new comments

• :wrench: add credentials parameter to completion

  #2463 commented on Sep 19, 2024 • 0 new comments

• Litellm update redisvl

  #2444 commented on Sep 19, 2024 • 0 new comments