v0.0.46

Fixes colab

What's Changed

• docs: Preserve output, clean eval notebooks by @pbadhe in #1590
• fix: failed imports from typing_extensions 4.5.0 in Colab by @RogerHYang in #1620
• chore: bump version for release by @RogerHYang in #1621

Full Changelog: v0.0.45...v0.0.46

v0.0.45

✨ What's new ✨

LLM Traces
We now support reranker spans so you can view how your documents are getting reranked for RAG use-cases! (s/o @RogerHYang). We also add search and filtering. For example you can now search within the IO of your spans as well as find spans that have high token counts.

LLM Evals

We now have support for gpt-3.5-turbo-instruct (s/o @RogerHYang) as well as verbose mode for you evaluations so you can easily debug the progress of a run (s/o @anticorrelator).

What's Changed

• chore: v0.0.44 by @axiomofjoy in #1582
• docs: OpenAIInstrumentor tutorial notebook by @axiomofjoy in #1580
• chore: openai notebook clean by @axiomofjoy in #1583
• feat: Verbose evals by @anticorrelator in #1558
• fix: precision at k calculation in notebooks by @axiomofjoy in #1592
• fix(evals): Set client type in bedrock.py for constructor by @lou-k in #1595
• fix(trace): remove unnecessary exclusion of semantic conventions for filter validation by @RogerHYang in #1597
• docs: remove langchain from llama_index tutorial by @mikeldking in #1601
• fix: remove quiet flags by @axiomofjoy in #1602
• feat(tracing): trace and span filter / search field by @mikeldking in #1577
• feat(traces): add reranking span kind for document reranking in llama index by @RogerHYang in #1588
• docs: contributing guide by @mikeldking in #1605
• feat: Add a general purpose LlamaIndex debug callback handler by @anticorrelator in #1608
• feat: add computed values (e.g. latency) to filterable quantities by @RogerHYang in #1609
• fix: LlamaIndex callback handler should fail gracefully by @anticorrelator in #1606
• feat(eval): add gpt-3.5-turbo-instruct to OpenAIModel by @RogerHYang in #1613
• fix: Remove trivial warnings by @anticorrelator in #1616

Full Changelog: v0.0.44...v0.0.45

v0.0.44

What's Changed

• chore: docs spelling by @mikeldking in #1529
• fix: server thread should be daemon by @RogerHYang in #1534
• fix: llm_eval_binary Argument Order in README.md by @lou-k in #1533
• docs: sync Oct 2, 2023 by @mikeldking in #1537
• docs: change llama-index repo url by @mikeldking in #1538
• docs: add code tour for tabular metrics by @RogerHYang in #1532
• chore: use semantic text color instead of white by @mikeldking in #1540
• feat: at exporter initialization, warn user if Phoenix is not running by @RogerHYang in #1535
• fix(notebook): missing experimental in pip install by @RogerHYang in #1549
• fix: pip install for eval notebooks by @RogerHYang in #1553
• chore: Add summary index builder script by @anticorrelator in #1552
• fix: type check for on_event_start for llama-index by @RogerHYang in #1557
• feat(trace): add live updating UI, stream on/off switch by @mikeldking in #1554
• docs: cleaned up ipynb notebooks to cleanly work in Colab environment by @jlopatec in #1530
• fix: notebook style by @axiomofjoy in #1563
• fix(evals): update prompt template for summarization eval and rails mapping to use lower case "good" / "bad" by @arizedatngo in #1562
• feat: Add default UMAP parameters in launch_app() by @pbadhe in #1224
• ci: add developer option for trace fixtures for simulating streaming span by @RogerHYang in #1564
• feat: openai instrumentor with chat completions support by @axiomofjoy in #1550
• feat(evals): add Azure parameters to OpenAIModel by @RogerHYang in #1566
• feat(evals): Add Bedrock model support to Evals by @lou-k in #1567
• fix: formatter complaint about extra space in session.py by @RogerHYang in #1575
• feat(tracing): gql validate_span_filter_condition by @mikeldking in #1578

New Contributors

• @lou-k made their first contribution in #1533

Full Changelog: v0.0.43...v0.0.44

v0.0.43

What's Changed

• docs(rag): Add RAG eval script and notebook by @fjcasti1 in #1520
• refactor: Move template functions to template module by @fjcasti1 in #1521
• docs: add getpass by @duncankmckinnon in #1523
• docs: docs sync 10/10/20203 by @mikeldking in #1525
• docs: re-organize integrations by @mikeldking in #1526
• docs: use one-click for llama_index by @mikeldking in #1527
• docs: sync by @mikeldking in #1528
• fix: Add uninmplemented methods to VertexAIModel from abstract class by @fjcasti1 in #1531

New Contributors

• @duncankmckinnon made their first contribution in #1523

Full Changelog: v0.0.42...v0.0.43

v0.0.42

What's Changed

• feat(trace): show the model name in the LLM span info by @mikeldking in #1512
• chore(trace): update fixtures by @mikeldking in #1513
• fix: typo in comment for launch_app's optional parameter by @RogerHYang in #1514
• feat(trace): prompt template UI by @mikeldking in #1515
• feat: enhance input types of run_relevance_eval by @axiomofjoy in #1504
• feat: Add processing functions file and token methods to OpenAIModel by @fjcasti1 in #1511
• feat: add latency P50 and P99 to tracing page header by @RogerHYang in #1519

Full Changelog: v0.0.41...v0.0.42

v0.0.41

What's Changed

• docs(tracing): update langchain notebooks to use the instrumentor by @mikeldking in #1495
• fix: case-insensitive rails parsing by @axiomofjoy in #1496
• feat(trace): show document metadata by @mikeldking in #1500
• fix: toxicity notebook bug by @axiomofjoy in #1505
• fix: contain openai dependency by @axiomofjoy in #1507
• chore: update version to v0.0.41 by @axiomofjoy in #1509

Full Changelog: v0.0.40...v0.0.41

v0.0.40

What's Changed

• docs(vals): API documentaiton by @mikeldking in #1461
• fix(notebook): typo in import statement by @RogerHYang in #1483
• fix: typo in token count formula by @RogerHYang in #1484
• feat: add templating semantic conventions to llm spans by @axiomofjoy in #1475
• docs: update RAG terminology by @mikeldking in #1489
• docs: add session info for notebooks by @axiomofjoy in #1490
• docs: sync sept 26, 2023 by @mikeldking in #1491
• feat(tracing): add LangChainInstrumentor for nested chains by @mikeldking in #1472

Full Changelog: v0.0.39...v0.0.40

v0.0.39

What's Changed

• docs: llama_index_agent by @mikeldking in #1458
• docs: sync 9-24-2023 by @mikeldking in #1460
• fix: add tiktoken to langchain_tracing_tutorial.ipynb by @RogerHYang in #1463
• feat: add total token count for trace page header by @RogerHYang in #1465
• feat: add LLM_OUTPUT_MESSAGES and change LLM_MESSAGES to LLM_INPUT_MESSAGES by @RogerHYang in #1462
• docs: update development.md to highlight testing and linting instructions by @axiomofjoy in #1450
• feat(infra): server-side template for index.html by @mikeldking in #1459
• docs: Llama Index OpenAI Agent tutorial edits by @michaelschiff in #1466
• feat: error handling attributes for llama-index by @axiomofjoy in #1449
• feat: Add VertexAI model implementation by @fjcasti1 in #1470
• docs: langchain agent tutorial by @mikeldking in #1474
• fix: remove html as ensured-targets by @mikeldking in #1477

New Contributors

• @michaelschiff made their first contribution in #1466

Full Changelog: v0.0.38...v0.0.39

v0.0.38

What's Changed

• docs: Update docs 9-18-2023 by @mikeldking in #1391
• docs: sync sept-18-2023 by @mikeldking in #1392
• refactor: update strawberry union syntax by @RogerHYang in #1393
• fix: hide embedding vector in graphql attributes by @RogerHYang in #1395
• refactor: remove openai from import for llama-index tracer by @RogerHYang in #1396
• fix: unpin langchain version by @RogerHYang in #1397
• docs(development): app tour by @mikeldking in #1398
• fix: capture function call output in llama-index by @RogerHYang in #1405
• fix(notebook): change .chat to .query in llama-index agent call by @RogerHYang in #1406
• fix: handle templating event in llama-index by @RogerHYang in #1407
• fix: missing port value in error message by @RogerHYang in #1408
• fix: set max_level=1 in json_normalize to prevent splintering by @RogerHYang in #1409
• feat: langchain llm message attributes by @axiomofjoy in #1410
• fix: typo in requirements by @RogerHYang in #1414
• chore(tracing): updated styles by @mikeldking in #1420
• chore: tracing styles by @mikeldking in #1422
• ci: add fixture for langchain titanic.csv agent evaluator by @RogerHYang in #1425
• feat: agent span kind for langchain by @RogerHYang in #1436
• feat(tracing): highlight slow spans by @mikeldking in #1424
• fix: np.stack argument deprecation by @RogerHYang in #1441
• feat(tracing): make row clickable by @mikeldking in #1448
• docs: langchain and llama_index integration by @mikeldking in #1451
• docs: sync sept 22 2023 by @mikeldking in #1452
• docs: docs sync sept 23 2023 by @mikeldking in #1454
• docs: update README with tracing by @mikeldking in #1453
• docs: fill out the entire feature set in the README by @mikeldking in #1455

Full Changelog: v0.0.37...v0.0.38

v0.0.37

What's Changed

• feat: langchain llm.prompts semantic convention by @axiomofjoy in #1356
• feat(tracing): tool details ui by @mikeldking in #1386
• fix: document metadata by @RogerHYang in #1383
• feat: add prompts list to ui by @axiomofjoy in #1384
• chore: add dataframe export to end of google notebooks by @axiomofjoy in #1379
• chore(tracing): move tracing out of experimental by @mikeldking in #1387

Full Changelog: v0.0.36...v0.0.37