arize-phoenix 0.0.40__py3-none-any.whl → 0.0.41__py3-none-any.whl

{arize_phoenix-0.0.40.dist-info → arize_phoenix-0.0.41.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: arize-phoenix
-Version: 0.0.40
+Version: 0.0.41
 Summary: ML Observability in your notebook
 Project-URL: Documentation, https://docs.arize.com/phoenix/
 Project-URL: Issues, https://github.com/Arize-ai/phoenix/issues
@@ -82,28 +82,28 @@ Description-Content-Type: text/markdown
 
 Phoenix provides MLOps and LLMOps insights at lightning speed with zero-config observability. Phoenix provides a notebook-first experience for monitoring your models and LLM Applications by providing:
 
--   **LLM App Tracing** - Trace through the execution of your LLM Application to understand the internals of your LLM Application and to troubleshoot problems related to things like retrieval and tool execution.
+-   **LLM Traces** - Trace through the execution of your LLM Application to understand the internals of your LLM Application and to troubleshoot problems related to things like retrieval and tool execution.
 -   **LLM Evals** - Leverage the power of large language models to evaluate your generative model or application's relevance, toxicity, and more.
 -   **Embedding Analysis** - Explore embedding point-clouds and identify clusters of high drift and performance degradation.
--   **RAG Introspection** - Visualize your generative application's search and retrieval process to solve improve your retrieval augmented generation.
+-   **RAG Analysis** - Visualize your generative application's search and retrieval process to solve improve your retrieval-augmented generation.
 -   **Structured Data Analysis** - Statistically analyze your structured data by performing A/B analysis, temporal drift analysis, and more.
 
 **Table of Contents**
 
-- [Installation](#installation)
-- [LLM App Tracing](#llm-app-tracing)
-  - [Tracing with LlamaIndex](#tracing-with-llamaindex)
-  - [Tracing with LangChain](#tracing-with-langchain)
-- [LLM Evals](#llm-evals)
-- [Embedding Analysis](#embedding-analysis)
-  - [UMAP-based Exploratory Data Analysis](#umap-based-exploratory-data-analysis)
-  - [Cluster-driven Drift and Performance Analysis](#cluster-driven-drift-and-performance-analysis)
-  - [Exportable Clusters](#exportable-clusters)
-- [Retrieval-Augmented Generation Analysis](#retrieval-augmented-generation-analysis)
-- [Structured Data Analysis](#structured-data-analysis)
-- [Community](#community)
-- [Thanks](#thanks)
-- [Copyright, Patent, and License](#copyright-patent-and-license)
+-   [Installation](#installation)
+-   [LLM Traces](#llm-traces)
+    -   [Tracing with LlamaIndex](#tracing-with-llamaindex)
+    -   [Tracing with LangChain](#tracing-with-langchain)
+-   [LLM Evals](#llm-evals)
+-   [Embedding Analysis](#embedding-analysis)
+    -   [UMAP-based Exploratory Data Analysis](#umap-based-exploratory-data-analysis)
+    -   [Cluster-driven Drift and Performance Analysis](#cluster-driven-drift-and-performance-analysis)
+    -   [Exportable Clusters](#exportable-clusters)
+-   [Retrieval-Augmented Generation Analysis](#retrieval-augmented-generation-analysis)
+-   [Structured Data Analysis](#structured-data-analysis)
+-   [Community](#community)
+-   [Thanks](#thanks)
+-   [Copyright, Patent, and License](#copyright-patent-and-license)
 
 ## Installation
 
@@ -119,7 +119,7 @@ Some functionality such as LLM evals are under the `experimental` subpackage.
 pip install arize-phoenix[experimental]
 ```
 
-## LLM App Tracing
+## LLM Traces
 
 ![LLM Application Tracing](https://github.com/Arize-ai/phoenix-assets/blob/main/gifs/langchain_rag_stuff_documents_chain_10mb.gif?raw=true)
 
@@ -129,7 +129,7 @@ With the advent of powerful LLMs, it is now possible to build LLM Applications t
 
 [![Open in Colab](https://img.shields.io/static/v1?message=Open%20in%20Colab&logo=googlecolab&labelColor=grey&color=blue&logoColor=orange&label=%20)](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/tracing/llama_index_tracing_tutorial.ipynb) [![Open in GitHub](https://img.shields.io/static/v1?message=Open%20in%20GitHub&logo=github&labelColor=grey&color=blue&logoColor=white&label=%20)](https://github.com/Arize-ai/phoenix/blob/main/tutorials/tracing/llama_index_tracing_tutorial.ipynb)
 
-![LLM App Tracing UI](https://storage.googleapis.com/arize-assets/phoenix/assets/images/trace_details_view.png)
+![LLM Traces UI](https://storage.googleapis.com/arize-assets/phoenix/assets/images/trace_details_view.png)
 
 To extract traces from your LlamaIndex application, you will have to add Phoenix's `OpenInferenceTraceCallback` to your LlamaIndex application. A callback (in this case an OpenInference `Tracer`) is a class that automatically accumulates `spans` that trac your application as it executes. The OpenInference `Tracer` is a tracer that is specifically designed to work with Phoenix and by default exports the traces to a locally running phoenix server.
 
@@ -199,12 +199,13 @@ import pandas as pd
 # Launch phoenix
 session = px.launch_app()
 
-# Once you have started a Phoenix server, you can start your LangChain application with the OpenInference Tracer as a callback. To do this, you will have to add the tracer to the initialization of your LangChain application:
+# Once you have started a Phoenix server, you can start your LangChain application with the OpenInferenceTracer as a callback. To do this, you will have to instrument your LangChain application with the tracer:
 
-from phoenix.trace.langchain import OpenInferenceTracer
+from phoenix.trace.langchain import OpenInferenceTracer, LangChainInstrumentor
 
 # If no exporter is specified, the tracer will export to the locally running Phoenix server
 tracer = OpenInferenceTracer()
+LangChainInstrumentor(tracer).instrument()
 
 # Initialize your LangChain application
 from langchain.chains import RetrievalQA

{arize_phoenix-0.0.40.dist-info → arize_phoenix-0.0.41.dist-info}/RECORD

@@ -1,4 +1,4 @@
-phoenix/__init__.py,sha256=N3O4mCm6Yw1lDqMoaH_HB4040C-hatB58wqjEv3PSTM,1255
+phoenix/__init__.py,sha256=6VUXCP54MN-nzyGzD4p7uCA3AznwSgDPGmg88D5iqhU,1255
 phoenix/config.py,sha256=TdMKmU7V490I38x_hvB1s14Y8pV3ldLSpJTKq6crzBY,1952
 phoenix/datetime_utils.py,sha256=D955QLrkgrrSdUM6NyqbCeAu2SMsjhR5rHVQEsVUdng,2773
 phoenix/py.typed,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
@@ -17,10 +17,10 @@ phoenix/datasets/schema.py,sha256=bF1d2Md6NyqQZuC4Ym5A52f2_IcazkyxGFZ11HPqSg0,66
 phoenix/datasets/validation.py,sha256=dZ9lCFUV0EY7HCkQkQBrs-GLAEIZdpOqUxwD5l4dp88,8294
 phoenix/experimental/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 phoenix/experimental/evals/__init__.py,sha256=VddJA_rloCyFn4brDCW2YOhTBjvcoBsXJ0N1SdTKx6U,1124
-phoenix/experimental/evals/retrievals.py,sha256=B5M2OUXDNpRa6n-QSVXDiRmmJp8YODTff1XPMBTprp4,3822
+phoenix/experimental/evals/retrievals.py,sha256=Y3YupYrrzt_orTMEFFW3eDBrHcMnBsqTqEQu7BWAUlk,3828
 phoenix/experimental/evals/utils.py,sha256=ivrYuX5Xotjh12BWOpYk9O7TgOt8uGDfdnRpYfrybmQ,1102
 phoenix/experimental/evals/functions/__init__.py,sha256=8P3nB_xln-ofLvQV7enwkjYp-I12Ao09MlK7E8ZITxY,209
-phoenix/experimental/evals/functions/binary.py,sha256=ubX5_vbHSVR5ozRnl_I7Uo2-34DAbXiGmfQcCqCKnUo,8061
+phoenix/experimental/evals/functions/binary.py,sha256=wPekcqOxJonkXcSsqwf20aUilSrBKmw3p__nQGVYwYI,8300
 phoenix/experimental/evals/functions/common.py,sha256=u2M2GCSOQWvAnBSdN2qLFrVb4rh2tnVKkp_wgmN-Nm8,1587
 phoenix/experimental/evals/functions/generate.py,sha256=ZnKKfsRW8lSERwh6DWPAl0GCBeFWB6K8vCV_-d8WxXA,1825
 phoenix/experimental/evals/models/__init__.py,sha256=W8ExfTmJ7xWFZ41YYcPmCpBBFZTWqo1VX2KaTr4t09Y,161
@@ -109,7 +109,7 @@ phoenix/server/static/apple-touch-icon-76x76.png,sha256=CT_xT12I0u2i0WU8JzBZBuOQ
 phoenix/server/static/apple-touch-icon.png,sha256=fOfpjqGpWYbJ0eAurKsyoZP1EAs6ZVooBJ_SGk2ZkDs,3801
 phoenix/server/static/favicon.ico,sha256=bY0vvCKRftemZfPShwZtE93DiiQdaYaozkPGwNFr6H8,34494
 phoenix/server/static/index.css,sha256=KKGpx4iwF91VGRm0YN-4cn8oC-oIqC6HecoPf0x3ZM8,1885
-phoenix/server/static/index.js,sha256=u3r2txf2qVBThPYGyNwff8MphCr-RHuZrzvyBfBgfVg,3025945
+phoenix/server/static/index.js,sha256=A-pcB3LmArVtXFL4-WwYVrW97TuOk0AjvDckC8IumyQ,3026120
 phoenix/server/static/modernizr.js,sha256=mvK-XtkNqjOral-QvzoqsyOMECXIMu5BQwSVN_wcU9c,2564
 phoenix/server/templates/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 phoenix/server/templates/index.html,sha256=wvVyoBRx4J9IQuR86VamPLpinhCnCEN2V4Kd_npsxU0,1124
@@ -118,7 +118,7 @@ phoenix/session/session.py,sha256=PRRw4tsbII0d09P-guRKzh9VY3pPoj2m_hAuQWSGR_s,12
 phoenix/trace/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 phoenix/trace/exporter.py,sha256=Q1Gxw6vDW1quuv2qeHWvzCsfxoO9s-iFsWlZYXOON8s,2007
 phoenix/trace/filter.py,sha256=-UqIr9DT9IQLNGBWCvNe8nAlK8KGHgoj8wUWEWmOzZA,6313
-phoenix/trace/fixtures.py,sha256=Fmv2ASYZ3-FjlBpsu0S6_G2raLj_d3tazegsiEKw5QM,3069
+phoenix/trace/fixtures.py,sha256=FbUmz3a9MCpAWevdC2kSW53_W0RKchcprSvurlpspvU,3334
 phoenix/trace/schemas.py,sha256=XDtwisCiQvcAZbi81HBaWxaJXXQ97r6b2y7H4nvpktc,5183
 phoenix/trace/semantic_conventions.py,sha256=b-Vgp3By49mgCcq5p6YCOws6K9bEp-uDG5NDvnaxYzI,4691
 phoenix/trace/span_json_decoder.py,sha256=pc6KtjleTf13blMm9dNCm7rXLXjZMY8jCQhqZ_gxwQ8,3089
@@ -134,8 +134,8 @@ phoenix/trace/llama_index/callback.py,sha256=tuEJl5VXh2jDyuOq5BUjlGI9-MyVBQfqJtA
 phoenix/trace/v1/__init__.py,sha256=FYL2u6f5prFtbQohQf_x-yR0hVflm7OAunO1fvo2KXg,17032
 phoenix/trace/v1/trace_pb2.py,sha256=DPDwoF4HOa3T2R-Qi7c2uXkbypOXcrOkCysMB-yrKXw,5580
 phoenix/trace/v1/trace_pb2.pyi,sha256=2JpgiYz3s8HrxnVIi5Brk7c3RJB4LqDGzwRYonhliRA,16258
-arize_phoenix-0.0.40.dist-info/METADATA,sha256=wdRVwxFrfpz4Kc9OOoi-D73mOEuGb8qMB5ne_E05Inc,25464
-arize_phoenix-0.0.40.dist-info/WHEEL,sha256=9QBuHhg6FNW7lppboF2vKVbCGTVzsFykgRQjjlajrhA,87
-arize_phoenix-0.0.40.dist-info/licenses/IP_NOTICE,sha256=JBqyyCYYxGDfzQ0TtsQgjts41IJoa-hiwDrBjCb9gHM,469
-arize_phoenix-0.0.40.dist-info/licenses/LICENSE,sha256=HFkW9REuMOkvKRACuwLPT0hRydHb3zNg-fdFt94td18,3794
-arize_phoenix-0.0.40.dist-info/RECORD,,
+arize_phoenix-0.0.41.dist-info/METADATA,sha256=aHxTG23lJnfr0pL6fj4Fn-rDRHHCTGYebzPfC20-48Y,25524
+arize_phoenix-0.0.41.dist-info/WHEEL,sha256=9QBuHhg6FNW7lppboF2vKVbCGTVzsFykgRQjjlajrhA,87
+arize_phoenix-0.0.41.dist-info/licenses/IP_NOTICE,sha256=JBqyyCYYxGDfzQ0TtsQgjts41IJoa-hiwDrBjCb9gHM,469
+arize_phoenix-0.0.41.dist-info/licenses/LICENSE,sha256=HFkW9REuMOkvKRACuwLPT0hRydHb3zNg-fdFt94td18,3794
+arize_phoenix-0.0.41.dist-info/RECORD,,

phoenix/__init__.py

@@ -5,7 +5,7 @@ from .session.session import Session, active_session, close_app, launch_app
 from .trace.fixtures import load_example_traces
 from .trace.trace_dataset import TraceDataset
 
-__version__ = "0.0.40"
+__version__ = "0.0.41"
 
 # module level doc-string
 __doc__ = """

phoenix/experimental/evals/functions/binary.py

@@ -183,8 +183,16 @@ def _extract_rail(string: str, positive_rail: str, negative_rail: str) -> Option
 
         string = "regular..irregular" - contains both rails
         Output: None
+
+        string = "Irregular"
+        Output: "irregular"
     """
 
+    # Convert the inputs to lowercase for case-insensitive matching
+    string = string.lower()
+    positive_rail = positive_rail.lower()
+    negative_rail = negative_rail.lower()
+
     positive_pos, negative_pos = string.find(positive_rail), string.find(negative_rail)
 
     # If both positive and negative rails are in the string

phoenix/experimental/evals/retrievals.py

@@ -4,7 +4,6 @@ Helper functions for evaluating the retrieval step of retrieval-augmented genera
 
 from typing import List, Optional
 
-from openai import ChatCompletion
 from tenacity import (
     retry,
     stop_after_attempt,
@@ -75,6 +74,9 @@ def classify_relevance(query: str, document: str, model_name: str) -> Optional[b
             (True meaning relevant, False meaning irrelevant), or None if the LLM produces an
             unparseable output.
     """
+
+    from openai import ChatCompletion
+
     prompt = _QUERY_CONTEXT_PROMPT_TEMPLATE.format(
         query=query,
         reference=document,