lmnr 0.4.8__py3-none-any.whl → 0.4.10__py3-none-any.whl

{lmnr-0.4.8.dist-info → lmnr-0.4.10.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: lmnr
-Version: 0.4.8
+Version: 0.4.10
 Summary: Python SDK for Laminar AI
 License: Apache-2.0
 Author: lmnr.ai
@@ -11,11 +11,11 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
-Requires-Dist: asyncio (>=3.4.3,<4.0.0)
-Requires-Dist: backoff (>=2.2.1,<3.0.0)
-Requires-Dist: colorama (>=0.4.6,<0.5.0)
-Requires-Dist: deprecated (>=1.2.14,<2.0.0)
-Requires-Dist: jinja2 (>=3.1.2,<4.0.0)
+Requires-Dist: asyncio (>=3.0,<4.0)
+Requires-Dist: backoff (>=2.0,<3.0)
+Requires-Dist: colorama (>=0.4,<0.5)
+Requires-Dist: deprecated (>=1.0,<2.0)
+Requires-Dist: jinja2 (>=3.0,<4.0)
 Requires-Dist: opentelemetry-api (>=1.27.0,<2.0.0)
 Requires-Dist: opentelemetry-exporter-otlp-proto-grpc (>=1.26.0,<2.0.0)
 Requires-Dist: opentelemetry-exporter-otlp-proto-http (>=1.26.0,<2.0.0)
@@ -49,11 +49,11 @@ Requires-Dist: opentelemetry-instrumentation-watsonx (>=0.30.0,<0.31.0)
 Requires-Dist: opentelemetry-instrumentation-weaviate (>=0.30.0,<0.31.0)
 Requires-Dist: opentelemetry-sdk (>=1.27.0,<2.0.0)
 Requires-Dist: opentelemetry-semantic-conventions-ai (==0.4.1)
-Requires-Dist: posthog (>3.0.2,<4)
-Requires-Dist: pydantic (>=2.7.4,<3.0.0)
-Requires-Dist: python-dotenv (>=1.0.1,<2.0.0)
-Requires-Dist: requests (>=2.32.3,<3.0.0)
-Requires-Dist: tenacity (>=8.2.3,<9.0.0)
+Requires-Dist: posthog (>=3.0,<4.0)
+Requires-Dist: pydantic (>=2.7,<3.0)
+Requires-Dist: python-dotenv (>=1.0,<2.0)
+Requires-Dist: requests (>=2.0,<3.0)
+Requires-Dist: tenacity (>=8.0,<9.0)
 Description-Content-Type: text/markdown
 
 # Laminar Python
@@ -77,16 +77,19 @@ pip install lmnr
 And the in your main Python file
 
 ```python
-from lmnr import Laminar as L
+from lmnr import Laminar as L, Instruments
 
-L.initialize(project_api_key="<LMNR_PROJECT_API_KEY>")
+L.initialize(project_api_key="<LMNR_PROJECT_API_KEY>", instruments={Instruments.OPENAI, Instruments.ANTHROPIC})
 ```
 
-This will automatically instrument most of the LLM, Vector DB, and related
-calls with OpenTelemetry-compatible instrumentation.
+If you want to automatically instrument particular LLM, Vector DB, and related
+calls with OpenTelemetry-compatible instrumentation, then pass the appropriate instruments to `.initialize()`.
+
+You can pass an empty set as `instruments=set()` to disable any kind of automatic instrumentation. 
+Also if you want to automatically instrument all supported libraries, then pass `instruments=None` or don't pass `instruments` at all.
 
-We rely on the amazing [OpenLLMetry](https://github.com/traceloop/openllmetry), open-source package
-by TraceLoop, to achieve that.
+Our code is based on the [OpenLLMetry](https://github.com/traceloop/openllmetry), open-source package
+by TraceLoop. Also, we are grateful to Traceloop for implementing autoinstrumentations for many libraries.
 
 ### Project API key
 
@@ -105,8 +108,8 @@ import os
 from openai import OpenAI
 
 
-from lmnr import observe, Laminar as L
-L.initialize(project_api_key="<LMNR_PROJECT_API_KEY>")
+from lmnr import observe, Laminar as L, Instruments
+L.initialize(project_api_key="<LMNR_PROJECT_API_KEY>", instruments={Instruments.OPENAI})
 
 client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])
 
@@ -128,40 +131,32 @@ print(poem_writer(topic="laminar flow"))
 
 ### Manual instrumentation
 
-Our manual instrumentation is a very thin wrapper around OpenTelemetry's
-`trace.start_span`. Our wrapper sets the span into the active context.
-You don't have to explicitly pass the spans around, it is enough to
-just call `L.start_span`, and OpenTelemetry will handle the context management
+Also, you can `Laminar.start_as_current_span` if you want to record a chunk of your code.
 
 ```python
-from lmnr import observe, Laminar as L
-L.initialize(project_api_key="<LMNR_PROJECT_API_KEY>")
+from lmnr import observe, Laminar as L, Instruments
+L.initialize(project_api_key="<LMNR_PROJECT_API_KEY>", instruments={Instruments.OPENAI})
 
 def poem_writer(topic="turbulence"):
-    
-    span = L.start_span("poem_writer", topic) # start a span
-
     prompt = f"write a poem about {topic}"
-
-    # OpenAI calls are still automatically instrumented with OpenLLMetry
-    response = client.chat.completions.create(
-        model="gpt-4o",
-        messages=[
-            {"role": "system", "content": "You are a helpful assistant."},
-            {"role": "user", "content": prompt},
-        ],
-    )
-    poem = response.choices[0].message.content
-    # while within the span, you can attach laminar events to it
-    L.event("event_name", "event_value")
-
-    L.set_span_output(span, poem) # set an output
-    
-    # IMPORTANT: don't forget to end all the spans (usually in `finally` blocks)
-    # Otherwise, the trace may not be sent/displayed correctly
-    span.end()
-
-    return poem
+    messages = [
+        {"role": "system", "content": "You are a helpful assistant."},
+        {"role": "user", "content": prompt},
+    ]
+
+    with L.start_as_current_span(name="poem_writer", input=messages):
+        # OpenAI calls are still automatically instrumented with OpenLLMetry
+        response = client.chat.completions.create(
+            model="gpt-4o",
+            messages=messages,
+        )
+        poem = response.choices[0].message.content
+        # while within the span, you can attach laminar events to it
+        L.event("event_name", "event_value")
+
+        L.set_span_output(poem) # set an output
+
+        return poem
 ```
 
 
@@ -204,7 +199,7 @@ Example use:
 ```python
 from lmnr import Laminar as L
 
-L.initialize('<YOUR_PROJECT_API_KEY>')
+L.initialize('<YOUR_PROJECT_API_KEY>', instruments=set())
 
 result = l.run(
     pipeline = 'my_pipeline_name',

{lmnr-0.4.8.dist-info → lmnr-0.4.10.dist-info}/RECORD

@@ -1,22 +1,21 @@
-lmnr/__init__.py,sha256=wQwnHl662Xcz7GdSofFsEjmAK0nxioYA2Yq6Q78m4ps,194
+lmnr/__init__.py,sha256=bA1f7JsEdSdU93HTz3SQLSanq-UgZGvb5I2OE0CWGR8,233
 lmnr/sdk/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-lmnr/sdk/decorators.py,sha256=0dLKWeKMmG_ryyK285GNsWBZSCWIyRhHgaDHlsJnDeM,2318
+lmnr/sdk/decorators.py,sha256=W46diLcINe0HAhxktrjbfQnaIfklSb0AydBHHxiko9U,2314
 lmnr/sdk/evaluations.py,sha256=EaRcwbdXxj4w2yzak1xFv-YhDuxRVentQcJ-CypBoH0,6307
-lmnr/sdk/laminar.py,sha256=d5Tt_OyrhtZTfm_ehd3QZev7T6-AKTJU5xAan0-3yPA,20070
+lmnr/sdk/laminar.py,sha256=M8HdP6ZYJHdngUVrGj4GMZxz_EZyx3woHm-UpfWmIvs,18439
 lmnr/sdk/log.py,sha256=EgAMY77Zn1bv1imCqrmflD3imoAJ2yveOkIcrIP3e98,1170
-lmnr/sdk/types.py,sha256=yTOoVHlg_wpce4Zx1ZSE3y7Qpwh9mcLCPKUi_1nfdk4,4071
+lmnr/sdk/types.py,sha256=w7BJsoEPHiNps62cQt3Hd6tEZ7ZFCKRTPzcwdD6rNak,4050
 lmnr/sdk/utils.py,sha256=ZsGJ86tq8lIbvOhSb1gJWH5K3GylO_lgX68FN6rG2nM,3358
 lmnr/traceloop_sdk/.flake8,sha256=bCxuDlGx3YQ55QHKPiGJkncHanh9qGjQJUujcFa3lAU,150
 lmnr/traceloop_sdk/.python-version,sha256=9OLQBQVbD4zE4cJsPePhnAfV_snrPSoqEQw-PXgPMOs,6
-lmnr/traceloop_sdk/README.md,sha256=XIfEytq1qYs6Nn3dD0JP002doQI94-AA_mFR3R7_OC8,614
-lmnr/traceloop_sdk/__init__.py,sha256=bK8TNuIwInehlhyn11hK5ACx_k6o2G3Oj4nabsamlqE,4693
+lmnr/traceloop_sdk/__init__.py,sha256=J-zVw6j0DmceVvJVZXAFcCzN_scz9hB3X17NQgPMgOg,4420
 lmnr/traceloop_sdk/config/__init__.py,sha256=EGN3ixOt_ORbMxqaQdLaC14kmO-gyG4mnGJ2GfN-R-E,364
-lmnr/traceloop_sdk/decorators/__init__.py,sha256=mU2eOvqpkkAd_ve56oQ52c8QOGbjDrjg8IJOTjXJJPg,3359
-lmnr/traceloop_sdk/decorators/base.py,sha256=ZkVXagdHNlrqC0kmhjMx6G9PENRMKp0KD5RNVzaf6l4,8184
+lmnr/traceloop_sdk/decorators/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+lmnr/traceloop_sdk/decorators/base.py,sha256=wcqXF0iVQgRXMyWTcJ5QvL_6q2y_gttwsX8dllmAtWM,4891
 lmnr/traceloop_sdk/instruments.py,sha256=G5EFAbpc20WD3M6xK6rlbj-Yy_r_f1m3gidY6UXzSRQ,701
 lmnr/traceloop_sdk/metrics/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 lmnr/traceloop_sdk/metrics/metrics.py,sha256=AlQ2a2os1WcZbfBd155u_UzBbPrbuPia6O_HbojV9Wc,5055
-lmnr/traceloop_sdk/tests/__init__.py,sha256=cepcpBRcyraU0ce09CYomy_qkHsCJBO9iePorZVkxBk,18
+lmnr/traceloop_sdk/tests/__init__.py,sha256=RYnG0-8zbXL0-2Ste1mEBf5sN4d_rQjGTCgPBuaZC74,20
 lmnr/traceloop_sdk/tests/cassettes/test_association_properties/test_langchain_and_external_association_properties.yaml,sha256=26g0wRA0juicHg_XrhcE8H4vhs1lawDs0o0aLFn-I7w,3103
 lmnr/traceloop_sdk/tests/cassettes/test_association_properties/test_langchain_association_properties.yaml,sha256=FNlSWlYCsWc3w7UPZzfGjDnxS3gAOhL-kpsu4BTxsDE,3061
 lmnr/traceloop_sdk/tests/cassettes/test_manual/test_manual_report.yaml,sha256=iq_U_DBKNyM8mhgwGZrqw1OMalIb3g1422cqkvsrPHw,2956
@@ -28,26 +27,26 @@ lmnr/traceloop_sdk/tests/cassettes/test_tasks/test_task_io_serialization_with_la
 lmnr/traceloop_sdk/tests/cassettes/test_workflows/test_simple_aworkflow.yaml,sha256=xbol_wTn-SeEanT4kLY4Y2_HLCTZf0ZHRFkPw402gqI,2944
 lmnr/traceloop_sdk/tests/cassettes/test_workflows/test_simple_workflow.yaml,sha256=ueiJY_6pyKQwbuMpeTAqHui4Ux7kYq_KTBZSob-cAjc,5866
 lmnr/traceloop_sdk/tests/cassettes/test_workflows/test_streaming_workflow.yaml,sha256=flOkiaW0DnQfD4rn_9F9dA0nIGMFjqwR3UzPyaanVjE,7947
-lmnr/traceloop_sdk/tests/conftest.py,sha256=_J8iz6z3CIf8Aj1UTlUtwZMsxUMtiS_-qrIUy4QNNJg,2873
-lmnr/traceloop_sdk/tests/test_association_properties.py,sha256=xHb-bEyF6qB2X3UxuBYmgqSg6qw7xvf6CzzkC2Bdr54,6331
-lmnr/traceloop_sdk/tests/test_manual.py,sha256=EtifedICZPtesGSzIqdAQCOITpydfcwxp-VaMRaajBc,1677
-lmnr/traceloop_sdk/tests/test_nested_tasks.py,sha256=QD5FKOj_ShJcgR09OV6HB97-P6D28CSljLy9UDcEXYI,1301
-lmnr/traceloop_sdk/tests/test_privacy_no_prompts.py,sha256=aJ8qSceWr85pxo6yZCTc0FE-FkiWnDylHUGiKc--jsA,1398
-lmnr/traceloop_sdk/tests/test_sdk_initialization.py,sha256=Dft8iJpjUcQBzF0ZfWokrfZhDBaim6WpFCion2I9FEI,1397
-lmnr/traceloop_sdk/tests/test_tasks.py,sha256=QDmanD1YiAzD3CGcCzCa-OyrOgewJbBJ0gx_EV219S0,858
-lmnr/traceloop_sdk/tests/test_workflows.py,sha256=zEIZjRE0D2uGSXHLSbLoU2JubuOZQqCUKCtWCovnbog,8751
-lmnr/traceloop_sdk/tracing/__init__.py,sha256=4C_umX0uMp--Gh-TPE4oeV3lvNzj2nKOBw516-yRqP0,131
+lmnr/traceloop_sdk/tests/conftest.py,sha256=XG6U9T6OyQliJUS8sBTXStjIP7Bb6ZChWTt0fulvHuc,3039
+lmnr/traceloop_sdk/tests/test_association_properties.py,sha256=D_LxhiVLwyXE0eW70uztmvZh3RRbVucM0L2C7O1oaFk,6735
+lmnr/traceloop_sdk/tests/test_manual.py,sha256=YHmVYfDfFUalAzYQsz50PIzXdj3Jfjcl4erpBU4ae4A,1759
+lmnr/traceloop_sdk/tests/test_nested_tasks.py,sha256=o7GPLVdgQOI5YH5HMBjInW4sprY4Nlu4SuwjMr1dxWU,1377
+lmnr/traceloop_sdk/tests/test_privacy_no_prompts.py,sha256=lS8bwg_xOS4gcwwzrrWflMkTSn8eZWyTmAxL3h3hZA0,1478
+lmnr/traceloop_sdk/tests/test_sdk_initialization.py,sha256=fRaf6lrxFzJIN94P1Tav_z_eywOsF5JXLPWzbJPMMyQ,1477
+lmnr/traceloop_sdk/tests/test_tasks.py,sha256=xlEx8BKp4yG83SCjK5WkPGfyC33JSrx4h8VyjVwGbgw,906
+lmnr/traceloop_sdk/tests/test_workflows.py,sha256=RVcfY3WAFIDZC15-aSua21aoQyYeWE7KypDyUsm-2EM,9372
+lmnr/traceloop_sdk/tracing/__init__.py,sha256=Ckq7zCM26VdJVB5tIZv0GTPyMZKyfso_KWD5yPHaqdo,66
 lmnr/traceloop_sdk/tracing/content_allow_list.py,sha256=3feztm6PBWNelc8pAZUcQyEGyeSpNiVKjOaDk65l2ps,846
 lmnr/traceloop_sdk/tracing/context_manager.py,sha256=csVlB6kDmbgSPsROHwnddvGGblx55v6lJMRj0wsSMQM,304
 lmnr/traceloop_sdk/tracing/manual.py,sha256=RPwEreHHdzmw7g15u4G21GqhHOvRp7d72ylQNLG1jRM,1841
-lmnr/traceloop_sdk/tracing/tracing.py,sha256=iArjof6BC-VU9KXnd5aLXY_3RfWElBBbTsFUKbjubHE,42435
+lmnr/traceloop_sdk/tracing/tracing.py,sha256=VFrf5D6CC3DquLy_19_5I_L_w1kO2X61KvPW0XD26-k,42347
 lmnr/traceloop_sdk/utils/__init__.py,sha256=pNhf0G3vTd5ccoc03i1MXDbricSaiqCbi1DLWhSekK8,604
 lmnr/traceloop_sdk/utils/in_memory_span_exporter.py,sha256=H_4TRaThMO1H6vUQ0OpQvzJk_fZH0OOsRAM1iZQXsR8,2112
 lmnr/traceloop_sdk/utils/json_encoder.py,sha256=dK6b_axr70IYL7Vv-bu4wntvDDuyntoqsHaddqX7P58,463
 lmnr/traceloop_sdk/utils/package_check.py,sha256=TZSngzJOpFhfUZLXIs38cpMxQiZSmp0D-sCrIyhz7BA,251
 lmnr/traceloop_sdk/version.py,sha256=OlatFEFA4ttqSSIiV8jdE-sq3KG5zu2hnC4B4mzWF3s,23
-lmnr-0.4.8.dist-info/LICENSE,sha256=67b_wJHVV1CBaWkrKFWU1wyqTPSdzH77Ls-59631COg,10411
-lmnr-0.4.8.dist-info/METADATA,sha256=biZj3jg_XUVTA4Xgpq66VNfhfvCPi6aDmE2VK4UXXFQ,10792
-lmnr-0.4.8.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-lmnr-0.4.8.dist-info/entry_points.txt,sha256=Qg7ZRax4k-rcQsZ26XRYQ8YFSBiyY2PNxYfq4a6PYXI,41
-lmnr-0.4.8.dist-info/RECORD,,
+lmnr-0.4.10.dist-info/LICENSE,sha256=67b_wJHVV1CBaWkrKFWU1wyqTPSdzH77Ls-59631COg,10411
+lmnr-0.4.10.dist-info/METADATA,sha256=VPXsfYwAy1uTv_qucCqgAmyGyZMngr0HuysSSdpX8Jw,10999
+lmnr-0.4.10.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+lmnr-0.4.10.dist-info/entry_points.txt,sha256=Qg7ZRax4k-rcQsZ26XRYQ8YFSBiyY2PNxYfq4a6PYXI,41
+lmnr-0.4.10.dist-info/RECORD,,

lmnr/traceloop_sdk/README.md

@@ -1,16 +0,0 @@
-# traceloop-sdk
-
-Traceloop’s Python SDK allows you to easily start monitoring and debugging your LLM execution. Tracing is done in a non-intrusive way, built on top of OpenTelemetry. You can choose to export the traces to Traceloop, or to your existing observability stack.
-
-```python
-Traceloop.init(app_name="joke_generation_service")
-
-@workflow(name="joke_creation")
-def create_joke():
-    completion = openai.ChatCompletion.create(
-        model="gpt-3.5-turbo",
-        messages=[{"role": "user", "content": "Tell me a joke about opentelemetry"}],
-    )
-
-    return completion.choices[0].message.content
-```