Commit graph

939 commits

Author SHA1 Message Date
Ishaan Jaff
75fba18c9f fix langfuse hardcoded public key 2024-08-02 07:21:02 -07:00
Krrish Dholakia
f506eb341b feat(litellm_logging.py): log exception response headers to langfuse 2024-08-01 18:07:47 -07:00
Ishaan Jaff
026e380b92 enforce premium user cheks on gcs bucket 2024-08-01 18:07:38 -07:00
Ishaan Jaff
781bfd1517 fix type errors 2024-08-01 18:07:38 -07:00
Ishaan Jaff
fc447dee5e delete object from gcs 2024-08-01 18:07:38 -07:00
Ishaan Jaff
357a1b87df feat gcs bucket log payload 2024-08-01 18:07:38 -07:00
Ishaan Jaff
008fbdfea6 fix _handle_failure for otel 2024-08-01 18:07:38 -07:00
Ishaan Jaff
285925e10a log output from /audio on langfuse 2024-07-29 08:21:22 -07:00
Ishaan Jaff
95f063f978 fix default input/output values for /audio/trancription logging 2024-07-29 08:03:08 -07:00
Ishaan Jaff
19fb5cc11c use common helpers for writing to otel 2024-07-27 11:40:39 -07:00
Ishaan Jaff
2a89486948 move _get_parent_otel_span_from_kwargs to otel.py 2024-07-27 11:12:13 -07:00
Idris Mokhtarzada
c2c5877afa
Fix Datadog JSON serialization
Nested dicts were not being serialized properly
2024-07-27 02:16:36 -04:00
Krrish Dholakia
fe0b55f2ca fix(utils.py): fix cache hits for streaming
Fixes https://github.com/BerriAI/litellm/issues/4109
2024-07-26 19:04:08 -07:00
Idris Mokhtarzada
e8d4234dbd
Better JSON serialization for Datadog logs
Dicts are now properly serialized to JSON so that Datadog can parse the child attributes.  Also, numbers and nulls are sent as numbers and nulls instead of strings.
2024-07-26 17:02:05 -04:00
Idris Mokhtarzada
a7e877d15f
Use milliseconds for response_time in Datadog logs
milliseconds is more commonly used and more standard than seconds
2024-07-26 16:43:21 -04:00
Idris Mokhtarzada
9b89280a90
Use underscores
Datadog does not play nice with special characters (as in "(seconds)").  Also just makes sense to standardize on either underscores or camelCase, but not mix-and-match.
2024-07-26 16:38:54 -04:00
Krish Dholakia
67115a56c0
Merge pull request #4869 from maamalama/anthropic-tools
Fixed tool_call for Helicone integration
2024-07-26 10:42:10 -07:00
Ishaan Jaff
fcd834b277 fix logfire - don't load_dotenv 2024-07-25 19:22:26 -07:00
maamalama
a3e4e4d412 anthropic gateway fixes 2024-07-25 11:37:29 -07:00
maamalama
41811218b2 tab 2024-07-24 17:42:07 -07:00
maamalama
98bed2a248 tools_call to Helicone 2024-07-24 17:40:20 -07:00
Ishaan Jaff
adfd6ab900 langsmith - support logging tags 2024-07-24 07:08:40 -07:00
Krish Dholakia
e770ac48a2
Merge branch 'main' into litellm_braintrust_integration 2024-07-22 22:40:39 -07:00
Krrish Dholakia
548e4f53f8 feat(redact_messages.py): allow remove sensitive key information before passing to logging integration 2024-07-22 20:58:02 -07:00
Krrish Dholakia
92b1262caa test(test_braintrust.py): add testing for braintrust integration 2024-07-22 18:05:11 -07:00
Krrish Dholakia
e4ab50e1a1 feat(braintrust_logging.py): working braintrust logging for successful calls 2024-07-22 17:04:55 -07:00
Krrish Dholakia
1ce029c80e feat(braintrust.py): initial commit for braintrust integration 2024-07-22 15:06:15 -07:00
Ishaan Jaff
41e6c4a573 feat - arize ai log llm i/o 2024-07-22 13:47:58 -07:00
Ishaan Jaff
0436eba2fa otel - log to arize ai 2024-07-22 13:40:42 -07:00
Ishaan Jaff
1a5aaee386 add arize.py 2024-07-22 11:27:51 -07:00
Ishaan Jaff
68f8fe87e4 feat - arize ai open inference types 2024-07-22 11:07:48 -07:00
Ishaan Jaff
91cd3ab7f8 fix langsmith logging test 2024-07-17 18:34:49 -07:00
Ishaan Jaff
f945e7009b test streaming logs to langsmith 2024-07-17 16:25:32 -07:00
Ishaan Jaff
5f04f7b7c1 fix langsmith logging for streaming 2024-07-17 16:04:45 -07:00
Ishaan Jaff
b2b180e254 langsmith use verbose logger 2024-07-17 15:23:20 -07:00
Ishaan Jaff
1334bca371 fix use AsyncHTTPHandler for logging langsmith requests 2024-07-17 11:49:48 -07:00
Ishaan Jaff
2c720214fa fix langsmith log user api key, user_id etc 2024-07-17 11:19:08 -07:00
Ishaan Jaff
df446c52e4 test api_key not logged on langsmith 2024-07-17 10:56:33 -07:00
Ishaan Jaff
0119ca1ce1 fix langsmith - don't log api_key 2024-07-17 10:04:36 -07:00
Krrish Dholakia
0cc273d77b feat(pass_through_endpoint.py): support enforcing key rpm limits on pass through endpoints
Closes https://github.com/BerriAI/litellm/issues/4698
2024-07-13 13:29:44 -07:00
Krrish Dholakia
fd743aaefd feat(opentelemetry.py): support logging call metadata to otel 2024-07-12 15:41:34 -07:00
Andrea Ponti
496445481d Rollback to metadata deepcopy 2024-07-12 11:25:23 +02:00
Krish Dholakia
d72bcdbce3
Merge pull request #4669 from BerriAI/litellm_logging_only_masking
Flag for PII masking on Logging only
2024-07-11 22:03:37 -07:00
Krish Dholakia
5ad341d0ff
Merge pull request #4607 from maamalama/helicone-cohere
Helicone Headers & Cohere support
2024-07-11 22:01:44 -07:00
Krrish Dholakia
9d918d2ac7 fix(presidio_pii_masking.py): support logging_only pii masking 2024-07-11 18:04:12 -07:00
Krrish Dholakia
9deb9b4e3f feat(guardrails): Flag for PII Masking on Logging
Fixes https://github.com/BerriAI/litellm/issues/4580
2024-07-11 16:09:34 -07:00
Marc Abramowitz
fe27182e8e Add missing space in "Failed Tracking Cost" msg
Fixes stuff like this:

```
Message: Failed Tracking Cost forerror in tracking cost callback - Traceback (most recent call last):
                              ^^^^^^^^
```
2024-07-11 13:26:59 -07:00
Krrish Dholakia
2163434ff3 fix(llm_cost_calc/google.py): fix google embedding cost calculation
Fixes https://github.com/BerriAI/litellm/issues/4630
2024-07-11 11:55:48 -07:00
Ishaan Jaff
e3470d8e91
Merge pull request #4658 from BerriAI/litellm_check_otel_spans
[Test-Proxy] Otel Traces
2024-07-11 10:41:51 -07:00
Ishaan Jaff
02ab3cb73d test- otel span recording 2024-07-11 08:47:16 -07:00