fix(key_management_endpoints.py): override metadata field value on up… (#7008 )

* fix(key_management_endpoints.py): override metadata field value on update

allow user to override tags

* feat(__init__.py): expose new disable_end_user_cost_tracking_prometheus_only metric

allow disabling end user cost tracking on prometheus - fixes cardinality issue

* fix(litellm_pre_call_utils.py): add key/team level enforced params

Fixes https://github.com/BerriAI/litellm/issues/6652

* fix(key_management_endpoints.py): allow user to pass in `enforced_params` as a top level param on /key/generate and /key/update

* docs(enterprise.md): add docs on enforcing required params for llm requests

* Add support of Galadriel API (#7005)

* fix(router.py): robust retry after handling

set retry after time to 0 if >0 healthy deployments. handle base case = 1 deployment

* test(test_router.py): fix test

* feat(bedrock/): add support for 'nova' models

also adds explicit 'converse/' route for simpler routing

* fix: fix 'supports_pdf_input'

return if model supports pdf input on get_model_info

* feat(converse_transformation.py): support bedrock pdf input

* docs(document_understanding.md): add document understanding to docs

* fix(litellm_pre_call_utils.py): fix linting error

* fix(init.py): fix passing of bedrock converse models

* feat(bedrock/converse): support 'response_format={"type": "json_object"}'

* fix(converse_handler.py): fix linting error

* fix(base_llm_unit_tests.py): fix test

* fix: fix test

* test: fix test

* test: fix test

* test: remove duplicate test

---------

Co-authored-by: h4n0 <4738254+h4n0@users.noreply.github.com>

2024-12-03 23:03:50 -08:00

4.4 KiB

Raw Blame History

import Tabs from '@theme/Tabs'; import TabItem from '@theme/TabItem';

Using PDF Input

How to send / receieve pdf's (other document types) to a /chat/completions endpoint

Works for:

Vertex AI models (Gemini + Anthropic)
Bedrock Models
Anthropic API Models

Quick Start

url

from litellm.utils import supports_pdf_input, completion

# set aws credentials
os.environ["AWS_ACCESS_KEY_ID"] = ""
os.environ["AWS_SECRET_ACCESS_KEY"] = ""
os.environ["AWS_REGION_NAME"] = ""


# pdf url
image_url = "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf"

# model
model = "bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0"

image_content = [
    {"type": "text", "text": "What's this file about?"},
    {
        "type": "image_url",
        "image_url": image_url, # OR {"url": image_url}
    },
]


if not supports_pdf_input(model, None):
    print("Model does not support image input")

response = completion(
    model=model,
    messages=[{"role": "user", "content": image_content}],
)
assert response is not None

Setup config.yaml

model_list:
  - model_name: bedrock-model
    litellm_params:
      model: bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0
      aws_access_key_id: os.environ/AWS_ACCESS_KEY_ID
      aws_secret_access_key: os.environ/AWS_SECRET_ACCESS_KEY
      aws_region_name: os.environ/AWS_REGION_NAME

Start the proxy

litellm --config /path/to/config.yaml

Test it!

curl -X POST 'http://0.0.0.0:4000/chat/completions' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer sk-1234' \
-d '{
    "model": "bedrock-model",
    "messages": [
        {"role": "user", "content": {"type": "text", "text": "What's this file about?"}},
        {
            "type": "image_url",
            "image_url": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf",
        }
    ]
}'

base64

from litellm.utils import supports_pdf_input, completion

# set aws credentials
os.environ["AWS_ACCESS_KEY_ID"] = ""
os.environ["AWS_SECRET_ACCESS_KEY"] = ""
os.environ["AWS_REGION_NAME"] = ""


# pdf url
image_url = "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf"
response = requests.get(url)
file_data = response.content

encoded_file = base64.b64encode(file_data).decode("utf-8")
base64_url = f"data:application/pdf;base64,{encoded_file}"

# model
model = "bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0"

image_content = [
    {"type": "text", "text": "What's this file about?"},
    {
        "type": "image_url",
        "image_url": base64_url, # OR {"url": base64_url}
    },
]


if not supports_pdf_input(model, None):
    print("Model does not support image input")

response = completion(
    model=model,
    messages=[{"role": "user", "content": image_content}],
)
assert response is not None

Checking if a model supports pdf input

Use litellm.supports_pdf_input(model="bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0") -> returns True if model can accept pdf input

assert litellm.supports_pdf_input(model="bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0") == True

Define bedrock models on config.yaml

model_list:
  - model_name: bedrock-model # model group name
    litellm_params:
      model: bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0
      aws_access_key_id: os.environ/AWS_ACCESS_KEY_ID
      aws_secret_access_key: os.environ/AWS_SECRET_ACCESS_KEY
      aws_region_name: os.environ/AWS_REGION_NAME
    model_info: # OPTIONAL - set manually
      supports_pdf_input: True

Run proxy server

litellm --config config.yaml

Call /model_group/info to check if a model supports pdf input

curl -X 'GET' \
  'http://localhost:4000/model_group/info' \
  -H 'accept: application/json' \
  -H 'x-api-key: sk-1234'

Expected Response

{
  "data": [
    {
      "model_group": "bedrock-model",
      "providers": ["bedrock"],
      "max_input_tokens": 128000,
      "max_output_tokens": 16384,
      "mode": "chat",
      ...,
      "supports_pdf_input": true, # 👈 supports_pdf_input is true
    }
  ]
}

4.4 KiB Raw Blame History

Using PDF Input

Quick Start

url

base64

Checking if a model supports pdf input

4.4 KiB

Raw Blame History