mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-26 19:24:27 +00:00
* LiteLLM Minor Fixes & Improvements (09/26/2024) (#5925)
* fix(litellm_logging.py): don't initialize prometheus_logger if non premium user
Prevents bad error messages in logs
Fixes https://github.com/BerriAI/litellm/issues/5897
* Add Support for Custom Providers in Vision and Function Call Utils (#5688)
* Add Support for Custom Providers in Vision and Function Call Utils Lookup
* Remove parallel function call due to missing model info param
* Add Unit Tests for Vision and Function Call Changes
* fix-#5920: set header value to string to fix "'int' object has no att… (#5922)
* LiteLLM Minor Fixes & Improvements (09/24/2024) (#5880)
* LiteLLM Minor Fixes & Improvements (09/23/2024) (#5842)
* feat(auth_utils.py): enable admin to allow client-side credentials to be passed
Makes it easier for devs to experiment with finetuned fireworks ai models
* feat(router.py): allow setting configurable_clientside_auth_params for a model
Closes https://github.com/BerriAI/litellm/issues/5843
* build(model_prices_and_context_window.json): fix anthropic claude-3-5-sonnet max output token limit
Fixes https://github.com/BerriAI/litellm/issues/5850
* fix(azure_ai/): support content list for azure ai
Fixes https://github.com/BerriAI/litellm/issues/4237
* fix(litellm_logging.py): always set saved_cache_cost
Set to 0 by default
* fix(fireworks_ai/cost_calculator.py): add fireworks ai default pricing
handles calling 405b+ size models
* fix(slack_alerting.py): fix error alerting for failed spend tracking
Fixes regression with slack alerting error monitoring
* fix(vertex_and_google_ai_studio_gemini.py): handle gemini no candidates in streaming chunk error
* docs(bedrock.md): add llama3-1 models
* test: fix tests
* fix(azure_ai/chat): fix transformation for azure ai calls
* feat(azure_ai/embed): Add azure ai embeddings support
Closes https://github.com/BerriAI/litellm/issues/5861
* fix(azure_ai/embed): enable async embedding
* feat(azure_ai/embed): support azure ai multimodal embeddings
* fix(azure_ai/embed): support async multi modal embeddings
* feat(together_ai/embed): support together ai embedding calls
* feat(rerank/main.py): log source documents for rerank endpoints to langfuse
improves rerank endpoint logging
* fix(langfuse.py): support logging `/audio/speech` input to langfuse
* test(test_embedding.py): fix test
* test(test_completion_cost.py): fix helper util
* fix-#5920: set header value to string to fix "'int' object has no attribute 'encode'"
---------
Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>
* Revert "fix-#5920: set header value to string to fix "'int' object has no att…" (#5926)
This reverts commit a554ae2695
.
* build(model_prices_and_context_window.json): add azure ai cohere rerank model pricing
Enables cost tracking for azure ai cohere rerank models
* fix(litellm_logging.py): fix debug log to be clearer
Closes https://github.com/BerriAI/litellm/issues/5909
* test(test_utils.py): fix test name
* fix(azure_ai/cost_calculator.py): support cost tracking for azure ai rerank models
* fix(azure_ai): fix azure ai base model cost tracking for rerank endpoints
* fix(converse_handler.py): support new llama 3-2 models
Fixes https://github.com/BerriAI/litellm/issues/5901
* fix(litellm_logging.py): ensure response is redacted for standard message logging
Fixes https://github.com/BerriAI/litellm/issues/5890#issuecomment-2378242360
* fix(cost_calculator.py): use 'get_model_info' for cohere rerank cost calculation
allows user to set custom cost for model
* fix(config.yml): fix docker hub auht
* build(config.yml): add docker auth to all tests
* fix(db/create_views.py): fix linting error
* fix(main.py): fix circular import
* fix(azure_ai/__init__.py): fix circular import
* fix(main.py): fix import
* fix: fix linting errors
* test: fix test
* fix(proxy_server.py): pass premium user value on startup
used for prometheus init
---------
Co-authored-by: Cole Murray <colemurray.cs@gmail.com>
Co-authored-by: bravomark <62681807+bravomark@users.noreply.github.com>
* handle streaming for azure ai studio error
* [Perf Proxy] parallel request limiter - use one cache update call (#5932)
* fix parallel request limiter - use one cache update call
* ci/cd run again
* run ci/cd again
* use docker username password
* fix config.yml
* fix config
* fix config
* fix config.yml
* ci/cd run again
* use correct typing for batch set cache
* fix async_set_cache_pipeline
* fix only check user id tpm / rpm limits when limits set
* fix test_openai_azure_embedding_with_oidc_and_cf
* test: fix test
* test(test_rerank.py): fix test
---------
Co-authored-by: Cole Murray <colemurray.cs@gmail.com>
Co-authored-by: bravomark <62681807+bravomark@users.noreply.github.com>
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
227 lines
7.1 KiB
Python
227 lines
7.1 KiB
Python
from typing import Any
|
|
|
|
from litellm import verbose_logger
|
|
|
|
_db = Any
|
|
|
|
|
|
async def create_missing_views(db: _db):
|
|
"""
|
|
--------------------------------------------------
|
|
NOTE: Copy of `litellm/db_scripts/create_views.py`.
|
|
--------------------------------------------------
|
|
Checks if the LiteLLM_VerificationTokenView and MonthlyGlobalSpend exists in the user's db.
|
|
|
|
LiteLLM_VerificationTokenView: This view is used for getting the token + team data in user_api_key_auth
|
|
|
|
MonthlyGlobalSpend: This view is used for the admin view to see global spend for this month
|
|
|
|
If the view doesn't exist, one will be created.
|
|
"""
|
|
try:
|
|
# Try to select one row from the view
|
|
await db.query_raw("""SELECT 1 FROM "LiteLLM_VerificationTokenView" LIMIT 1""")
|
|
print("LiteLLM_VerificationTokenView Exists!") # noqa
|
|
except Exception as e:
|
|
# If an error occurs, the view does not exist, so create it
|
|
await db.execute_raw(
|
|
"""
|
|
CREATE VIEW "LiteLLM_VerificationTokenView" AS
|
|
SELECT
|
|
v.*,
|
|
t.spend AS team_spend,
|
|
t.max_budget AS team_max_budget,
|
|
t.tpm_limit AS team_tpm_limit,
|
|
t.rpm_limit AS team_rpm_limit
|
|
FROM "LiteLLM_VerificationToken" v
|
|
LEFT JOIN "LiteLLM_TeamTable" t ON v.team_id = t.team_id;
|
|
"""
|
|
)
|
|
|
|
print("LiteLLM_VerificationTokenView Created!") # noqa
|
|
|
|
try:
|
|
await db.query_raw("""SELECT 1 FROM "MonthlyGlobalSpend" LIMIT 1""")
|
|
print("MonthlyGlobalSpend Exists!") # noqa
|
|
except Exception as e:
|
|
sql_query = """
|
|
CREATE OR REPLACE VIEW "MonthlyGlobalSpend" AS
|
|
SELECT
|
|
DATE("startTime") AS date,
|
|
SUM("spend") AS spend
|
|
FROM
|
|
"LiteLLM_SpendLogs"
|
|
WHERE
|
|
"startTime" >= (CURRENT_DATE - INTERVAL '30 days')
|
|
GROUP BY
|
|
DATE("startTime");
|
|
"""
|
|
await db.execute_raw(query=sql_query)
|
|
|
|
print("MonthlyGlobalSpend Created!") # noqa
|
|
|
|
try:
|
|
await db.query_raw("""SELECT 1 FROM "Last30dKeysBySpend" LIMIT 1""")
|
|
print("Last30dKeysBySpend Exists!") # noqa
|
|
except Exception as e:
|
|
sql_query = """
|
|
CREATE OR REPLACE VIEW "Last30dKeysBySpend" AS
|
|
SELECT
|
|
L."api_key",
|
|
V."key_alias",
|
|
V."key_name",
|
|
SUM(L."spend") AS total_spend
|
|
FROM
|
|
"LiteLLM_SpendLogs" L
|
|
LEFT JOIN
|
|
"LiteLLM_VerificationToken" V
|
|
ON
|
|
L."api_key" = V."token"
|
|
WHERE
|
|
L."startTime" >= (CURRENT_DATE - INTERVAL '30 days')
|
|
GROUP BY
|
|
L."api_key", V."key_alias", V."key_name"
|
|
ORDER BY
|
|
total_spend DESC;
|
|
"""
|
|
await db.execute_raw(query=sql_query)
|
|
|
|
print("Last30dKeysBySpend Created!") # noqa
|
|
|
|
try:
|
|
await db.query_raw("""SELECT 1 FROM "Last30dModelsBySpend" LIMIT 1""")
|
|
print("Last30dModelsBySpend Exists!") # noqa
|
|
except Exception as e:
|
|
sql_query = """
|
|
CREATE OR REPLACE VIEW "Last30dModelsBySpend" AS
|
|
SELECT
|
|
"model",
|
|
SUM("spend") AS total_spend
|
|
FROM
|
|
"LiteLLM_SpendLogs"
|
|
WHERE
|
|
"startTime" >= (CURRENT_DATE - INTERVAL '30 days')
|
|
AND "model" != ''
|
|
GROUP BY
|
|
"model"
|
|
ORDER BY
|
|
total_spend DESC;
|
|
"""
|
|
await db.execute_raw(query=sql_query)
|
|
|
|
print("Last30dModelsBySpend Created!") # noqa
|
|
try:
|
|
await db.query_raw("""SELECT 1 FROM "MonthlyGlobalSpendPerKey" LIMIT 1""")
|
|
print("MonthlyGlobalSpendPerKey Exists!") # noqa
|
|
except Exception as e:
|
|
sql_query = """
|
|
CREATE OR REPLACE VIEW "MonthlyGlobalSpendPerKey" AS
|
|
SELECT
|
|
DATE("startTime") AS date,
|
|
SUM("spend") AS spend,
|
|
api_key as api_key
|
|
FROM
|
|
"LiteLLM_SpendLogs"
|
|
WHERE
|
|
"startTime" >= (CURRENT_DATE - INTERVAL '30 days')
|
|
GROUP BY
|
|
DATE("startTime"),
|
|
api_key;
|
|
"""
|
|
await db.execute_raw(query=sql_query)
|
|
|
|
print("MonthlyGlobalSpendPerKey Created!") # noqa
|
|
try:
|
|
await db.query_raw(
|
|
"""SELECT 1 FROM "MonthlyGlobalSpendPerUserPerKey" LIMIT 1"""
|
|
)
|
|
print("MonthlyGlobalSpendPerUserPerKey Exists!") # noqa
|
|
except Exception as e:
|
|
sql_query = """
|
|
CREATE OR REPLACE VIEW "MonthlyGlobalSpendPerUserPerKey" AS
|
|
SELECT
|
|
DATE("startTime") AS date,
|
|
SUM("spend") AS spend,
|
|
api_key as api_key,
|
|
"user" as "user"
|
|
FROM
|
|
"LiteLLM_SpendLogs"
|
|
WHERE
|
|
"startTime" >= (CURRENT_DATE - INTERVAL '30 days')
|
|
GROUP BY
|
|
DATE("startTime"),
|
|
"user",
|
|
api_key;
|
|
"""
|
|
await db.execute_raw(query=sql_query)
|
|
|
|
print("MonthlyGlobalSpendPerUserPerKey Created!") # noqa
|
|
|
|
try:
|
|
await db.query_raw("""SELECT 1 FROM DailyTagSpend LIMIT 1""")
|
|
print("DailyTagSpend Exists!") # noqa
|
|
except Exception as e:
|
|
sql_query = """
|
|
CREATE OR REPLACE VIEW DailyTagSpend AS
|
|
SELECT
|
|
jsonb_array_elements_text(request_tags) AS individual_request_tag,
|
|
DATE(s."startTime") AS spend_date,
|
|
COUNT(*) AS log_count,
|
|
SUM(spend) AS total_spend
|
|
FROM "LiteLLM_SpendLogs" s
|
|
GROUP BY individual_request_tag, DATE(s."startTime");
|
|
"""
|
|
await db.execute_raw(query=sql_query)
|
|
|
|
print("DailyTagSpend Created!") # noqa
|
|
|
|
try:
|
|
await db.query_raw("""SELECT 1 FROM "Last30dTopEndUsersSpend" LIMIT 1""")
|
|
print("Last30dTopEndUsersSpend Exists!") # noqa
|
|
except Exception as e:
|
|
sql_query = """
|
|
CREATE VIEW "Last30dTopEndUsersSpend" AS
|
|
SELECT end_user, COUNT(*) AS total_events, SUM(spend) AS total_spend
|
|
FROM "LiteLLM_SpendLogs"
|
|
WHERE end_user <> '' AND end_user <> user
|
|
AND "startTime" >= CURRENT_DATE - INTERVAL '30 days'
|
|
GROUP BY end_user
|
|
ORDER BY total_spend DESC
|
|
LIMIT 100;
|
|
"""
|
|
await db.execute_raw(query=sql_query)
|
|
|
|
print("Last30dTopEndUsersSpend Created!") # noqa
|
|
|
|
return
|
|
|
|
|
|
async def should_create_missing_views(db: _db) -> bool:
|
|
"""
|
|
Run only on first time startup.
|
|
|
|
If SpendLogs table already has values, then don't create views on startup.
|
|
"""
|
|
|
|
sql_query = """
|
|
SELECT reltuples::BIGINT
|
|
FROM pg_class
|
|
WHERE oid = '"LiteLLM_SpendLogs"'::regclass;
|
|
"""
|
|
|
|
result = await db.query_raw(query=sql_query)
|
|
|
|
verbose_logger.debug("Estimated Row count of LiteLLM_SpendLogs = {}".format(result))
|
|
if (
|
|
result
|
|
and isinstance(result, list)
|
|
and len(result) > 0
|
|
and isinstance(result[0], dict)
|
|
and "reltuples" in result[0]
|
|
and result[0]["reltuples"]
|
|
and (result[0]["reltuples"] == 0 or result[0]["reltuples"] == -1)
|
|
):
|
|
verbose_logger.debug("Should create views")
|
|
return True
|
|
|
|
return False
|