PyPI · #1267 most downloaded on PyPI

instructor

1.17.08.6M downloads/mo567-labs/instructor ↗New releases in your daily digest, changelog included.

structured outputs for llm

Last release 25 days ago
09 Sep 2026
Release timing varies
gaps range from 8 days to 2 months
Nearly every release is documented
notes for 59 of the last 60 stable releases
Nothing withdrawn
no release was ever pulled
3 years old
98 releases · first in 2023

Release timeline

98 releases since 2023

2023202420252026

20232026

One column per quarter.

Releases

1.17.09 Sept 2026Security2 sources agree
The proposed automatic execution in #2588 is deferred in favor of main's security fix for #2528 .
Includes the fixes previously planned for 1.16.1, which was not published. The
previous published version is 1.16.0.

Upgrade Notes

Cached responses use new keys and isolated per-client namespaces. Existing cache entries will miss. Set the same explicit cache_namespace only when clients are intended to share results; keep accounts, endpoints, and tenants isolated.

Response models with Instructor async-validator decorators are rejected before provider calls or cache lookup, including nested models. Use Pydantic validators or explicitly await application-level validation after extraction; automatic async-validator execution is deferred.

Remote media URLs must resolve to public addresses and cannot contain credentials. Redirects and connected peers are checked, and downloads have size limits.

Fixed

Cache isolation: Include provider identity and prepared generation settings, including nested GenAI and Bedrock configuration; reuse the lookup key when storing after retries. Cache hits preserve current validation context and strictness. Clients have separate namespaces by default; use an explicit cache_namespace for intentional reuse across instances. Requests with unsupported opaque values bypass caching rather than using ambiguous identities. (#2585, #2586)

GenAI cached content: Omit conflicting system instructions and tool declarations after resolving cached-content configuration, including plain responses, and preserve caller-owned configuration. Consolidates #2581, #2582, and #2591 for #2580.

GenAI request configuration: Preserve caller-owned generation_config dictionaries when preparing tools and JSON requests, so repeated requests retain their sampling settings and token limits. (#2596)

OpenAI SDK compatibility: Support OpenAI 3.x and its HTTPX2 transport when constructing sync and async clients through from_provider, while retaining OpenAI 2.x support on Python 3.9. (#2553)

Async validation policy: Fail closed for @async_field_validator and @async_model_validator response models instead of silently skipping policy checks. The proposed automatic execution in #2588 is deferred in favor of main's security fix for #2528.

Anthropic local PDFs: Read local PDF sources from disk instead of trying to fetch them over HTTP. (#2577)

Security

Route Anthropic PDF downloads through the bounded public-network fetcher and pin each media connection to a validated IP before sending HTTP.

Key cached responses by the complete prepared request, provider, validation context and strictness. Clients have isolated cache namespaces by default; cache_namespace explicitly enables sharing and must identify the endpoint and tenant. Revalidate cache hits with the current context and strictness.

Reject response models containing unsupported async-validator markers, including nested models, instead of silently skipping their policy checks.

Bound JSON extraction to 1 MiB of characters and 128 nesting levels, and avoid repeatedly scanning malformed suffixes.

Changed

Current model examples: Refresh 16 provider guides, including GPT-5.6 Luna, Sonnet 5, Gemini 3.8 Flash, and current hosted model IDs. Correct Luna tool-call parameters, Sonnet adaptive thinking, and audio transcription guidance; add real model-ID smoke tests and code-block lint checks. Normalize Google test model overrides and default to Gemini 3.8 Flash.

Documentation examples: Explain OpenAI-compatible JSON endpoints; correct typos, malformed client calls, missing imports, and code-block formatting across concepts and blog examples. Label displayed output separately from executable Python. (#2578, #2579, #2584, #2587, #2593)

CLI cost metadata: Add an explicit mapping annotation to the model-cost table so static analysis preserves its nested numeric value shape. (#2521)

Provider documentation: Correct the Mistral installation extra and xAI Python requirement, document Cerebras request-parameter forwarding with a runnable example, repair the Langfuse tracing examples, and clean up extraction typos. (#2550, #2554, #2556, #2561, #2562)

Live-provider CI signal: Retry only failed tests once in the mixed-provider and auto-client lanes so transient API failures do not obscure deterministic regressions, while setup, collection, repeated, and other failures remain red.

Security

Remote multimodal fetching: Block non-public and credential-bearing media URLs, revalidate redirects and connected peers, disable ambient proxy credentials, cap image, audio, and PDF downloads, and avoid caching decoded media payloads in process memory.

Supply-chain hardening: Require a patched urllib3 release and pin GitHub Actions to reviewed commit SHAs, including secret-bearing scheduled workflows.

Release workflow hardening: Avoid persisting checkout credentials, disable dependency-cache restoration in the PyPI publishing job, and pass release metadata to shell steps through environment variables instead of direct expression interpolation.

Additional Fixes

Anthropic batch messages: Preserve every system instruction when converting batch requests instead of keeping only the final system message. (#2552)

Anthropic batch accounting: Include canceled and expired requests in reported batch totals. (#2529)

Bedrock request safety: Reject unsupported numerical, string-length, and minItems > 1 constraints locally for native structured outputs, and preserve caller-owned nested inference configuration while normalizing requests. (#2530, #2532)

Cache key isolation: Include provider-hoisted system prompts in sync and async cache keys so requests with different instructions cannot share a cached response. (#2524)

Gemini safety settings: Copy caller-provided safety mappings before applying default thresholds so request preparation cannot mutate reusable application configuration. (#2551)

Google GenAI validation retries: Use the supported user role for function-response turns so Gemini can process correction requests. (#2557)

TypedDict response models: Preserve total=False, Required, and NotRequired key semantics for single and iterable response models so valid partial outputs do not trigger retries. (#2567, #2568)

Provider initialization: Reject provider strings with an empty provider or model component before client construction. (#2522)

Remote multimodal media types: Accept valid case-insensitive HTTP Content-Type values with optional parameters when loading images, audio, and PDFs. (#2525)

Message history: Preserve tool-call and other protocol fields when normalizing consecutive messages, and keep protocol messages as separate turns. (#2527)

v2 mode registry: Keep lazily loaded modes registered while their handlers initialize, preventing concurrent first calls from failing spuriously. (#2536, #2535)

1.16.027 Aug 2026Deprecated2 sources agree

Provider documentation : Refresh retired Cerebras model IDs, clarify current and deprecated Google provider prefixes, and fix the Vertex Google GenAI…

Added

Bedrock native structured outputs: Add explicit Mode.JSON_SCHEMA and Mode.TOOLS_STRICT support through Converse outputConfig.textFormat and strict tool schemas, with recursive schema normalization and a boto3 1.42.42 minimum. Model selection remains caller-controlled. (#2515, #2084, #2086)
Validation retry budgets: Add positive cumulative token_budget limits for structured non-streaming retries, immutable completion:usage snapshots, sync/async cutoff parity, and stable cumulative usage metadata. Valid responses still win after crossing the budget. When a budget is configured, a failed attempt with unavailable usage stops before another provider call. (#2512, #2391, #2392)

Changed

Contributor workflow: Align contributor setup and dependency management around locked uv sync environments, uv run commands, and uv add only for intentional project metadata changes. (#2516, #2354)

Fixed

Mistral SDK compatibility: Support the mistralai 2.x client export on Python 3.10+ while retaining the compatible 1.x fallback required by Python 3.9. (#2513, #2298, #2365)
Bedrock reasoning JSON: Parse the final complete JSON value after reasoning text or <think> blocks, preserve JSON escape sequences, and keep caller-owned messages unchanged during Bedrock request preparation and retries. (#2514, #2076, #2287)
Remote multimodal fetches: Apply the existing 30-second request timeout to image, audio, and PDF downloads so an unresponsive URL cannot block a caller indefinitely. (#2507)
OpenAI streaming retries: Keep TOOLS, JSON, JSON_SCHEMA, and MD_JSON retries on the streaming parser after the one-shot model marker is consumed, allowing corrected streamed responses to validate successfully. (#2508)
Iterable streaming unions: Parse PEP 604 unions (create_iterable(response_model=Weather | GoogleSearch), Iterable[Weather | GoogleSearch]) member by member instead of calling model_validate_json on types.UnionType. (#2509)
Package metadata: Point the published distribution's repository URL at the current 567-labs/instructor organization and validate it before release.
Retry usage accounting: Accumulate nested and newly added numeric usage fields across OpenAI and Anthropic retries, including prediction, cache-write, cache-creation, and server-tool counters, without treating boolean metadata as billable usage. (#2493, #2500)
OpenAI Responses reask: Add a fallback correction message when a RESPONSES_TOOLS response contains no tool calls (e.g. reasoning-only output), so retries carry validation feedback instead of resending the identical request. (#2498)
v2 parallel tools: Preserve raw iterable type hints through the sync and async patch wrappers so parallel tool schemas and results retain every requested model type. (#2501)
Credential redaction: Hide common OAuth and Google API credential aliases in nested v2 debug logging while preserving non-secret token configuration. (#2490, #2491)
Retry and message integrity: Preserve cache keys and caller-owned retry messages, retain empty-content legacy function calls, return Anthropic tool results for every parallel tool call, and handle missing OpenAI/Mistral tool calls as retryable parse failures. (#2454, #2455, #2464, #2484, #2485, #2486, #2448, #2453)
Streaming and DSL correctness: Isolate partial-model recursion guards, preserve partial nested models and explicit nulls, harden citation matching, derive useful Iterable union names, and continue scanning JSON streams after non-JSON or multiple balanced values. (#2422, #2430, #2431, #2452, #2456, #2461, #2463, #2476, #2487, #2489)
Provider request handling: Avoid mutating Gemini generation config and cached OpenAI schemas, disable Anthropic parallel calls for forced single-tool requests, forward Bedrock default models, and label OpenAI audio as WAV or MP3 without misrepresenting unsupported formats. (#2450, #2451, #2465, #2467, #2477, #2478, #2447, #2415)
Batch, CLI, and citation runtime: Accept valid empty batch objects, use typed OpenAI file attributes in the CLI, normalize None message content, and install regex as the direct dependency required by CitationMixin. (#2473, #2441, #2440, #2443)
Provider documentation: Refresh retired Cerebras model IDs, clarify current and deprecated Google provider prefixes, and fix the Vertex Google GenAI example so its default model is passed to from_genai(). (#2494, #2289, #2343, #2416, #2475)
Multimodal (Audio): Raise explicit ValueError or FileNotFoundError from Audio.from_url() and Audio.from_path() instead of relying on bare assert statements that can disappear under python -O. (#2361)
v2 message handling: Preserve caller-owned message lists and nested content across request preparation and retries for OpenAI-compatible, Cohere, Mistral, OpenRouter, Writer, and xAI handlers. (#2417, #2428)
v2 JSON extraction: Prefer the final complete top-level JSON value in text responses and retain every JSON object when multiple objects arrive in one streaming chunk.
v2 schemas: Treat fields with Pydantic default_factory values as optional in generated OpenAI tool schemas.
v2 partial streaming: Build model instances for present Optional[BaseModel] fields during incomplete streams instead of exposing raw dictionaries.
v2 iterable unions: Generate stable member-derived names such as IterableAOrB for both Union[A, B] and A | B response models.
Mistral/Vertex AI partial streaming: Avoid forwarding iterable-only parser arguments into completed Partial responses, preventing final Pydantic validation errors for sync and async streams.
Batch providers: Handle missing optional SDKs safely, validate OpenAI batch input before client setup, report exhausted output-file retries clearly, and remove unreachable fallbacks.
OpenAI/Writer tools: Raise clear response-parsing errors for completions with no choices or tool calls instead of leaking attribute and index errors.
Fireworks streaming: Keep non-streaming async calls non-streaming and return streaming async generators without incorrectly awaiting them.
GenAI uploads: Respect max_retries=0 without an unwanted sleep or polling request, allow recovery on the final permitted retry, and report nameless pending uploads clearly before polling.
Gemini/GenAI messages: Honor an explicit system message for unstructured requests, remove the unsupported raw system argument, and reject invalid scalar message content clearly.
Templating: Use populated contents when messages is empty, avoid mutating nested caller input, and preserve uncopyable metadata during template expansion.
Anthropic system messages: Reject invalid new system-message values even when no existing system message is present.
Python 3.9: Include the required type-evaluation backport in minimal installs, keep overload metadata available, and avoid runtime evaluation of unsupported union syntax in the core response path and offline tests.
v2 imports: Defer OpenAI SDK imports from core v2 modules until an OpenAI-specific path actually needs them, reducing import side effects for non-OpenAI usage. (#2390)
v2 response models: Treat list[A | B] PEP 604 unions of Pydantic models as iterable response models, matching list[Union[A, B]] schema behavior. (#2377)
OpenAI Responses API: Align RESPONSES_TOOLS text.format with the forced tool schema and add targeted retry guidance when tool calls return empty {} arguments. (#2300, #2304)

Security

LLM validator isolation: Send validation rules and candidate values as structured JSON data under a fixed trusted instruction to reduce prompt-injection risk, and raise ValueError for rejected values instead of relying on optimization-sensitive assertions. (#2511, #2056, #2307)

Tests / CI

Fork-safe contributor checks: Mark auto-client network tests explicitly and exclude them from core, coverage, and release lanes so fork PRs without provider secrets do not fail with empty authorization headers.
Coverage and test quality: Run the complete offline suite on Python 3.9-3.13, enforce fork-safe statement and branch coverage plus supported-version type checks in pull-request CI, add strict resource and thread warning checks, and provide a manual retry-mutation workflow. Consolidate typed response, stream, and SDK fixtures; remove duplicate tests and unreachable provider paths; and replace coverage-only stubs with meaningful edge-case and transport-backed provider checks.
Release safety: Validate the declared source, lockfile, changelog, tag, and built artifacts before any publication step; require an explicit version confirmation and publish opt-in; and publish the exact tested assets instead of rebuilding from a moving branch.

Open source →

1.15.428 Jun 2026

Instructor 1.15.4 is a patch release that consolidates the latest small fixes and docs cleanup after 1.15.3 .

What's Changed

Instructor 1.15.4 is a patch release that consolidates the latest small fixes and docs cleanup after 1.15.3.

Runtime Fixes

Fixed v2 response-model preparation so list and primitive response models are normalized before provider handler dispatch. This fixes crashes such as AttributeError: type object 'list' has no attribute 'model_json_schema' for list[Model] and scalar response models.
Fixed streamed JSON extraction so backticks inside JSON string values are preserved instead of being interpreted as markdown fence delimiters.
Fixed Image.autodetect() to accept raw JPEG, PNG, GIF, and WebP bytes, while raising clear errors for unsupported image inputs.
Added regression coverage for the existing Gemini empty-message path.
Fixed list[BaseModel] simple-type detection so model lists route through iterable handling instead of scalar wrapping.

CLI

Fixed fine-tuning job creation from local files to pass the uploaded validation file ID to OpenAI instead of the local validation file path.
Refreshed the CLI fine-tuning default model string in code and docs.

Docs

Updated stale OpenAI model strings across docs and tutorials.
Updated the Ollama example to use llama3.2, including the ollama pull command and from_provider() example.

Release

Bumped package metadata to 1.15.4 in pyproject.toml, instructor/__init__.py, and uv.lock.
Published the release to PyPI as both wheel and sdist.

Validation

PR #2398 passed Ruff, type-check, core tests, provider tests, live provider tests, auto client tests, and the Workers build before release.

Full Changelog: v1.15.3...v1.15.4

Open source →

Additional notes

Fixed

CLI fine-tuning: Use the uploaded validation file ID when creating a fine-tuning job from local files, instead of passing the local validation file path through to OpenAI. (#2397)
v2 core: Prepare list and primitive response models before provider handler dispatch, fixing list[Model] and scalar response-model crashes such as AttributeError: type object 'list' has no attribute 'model_json_schema'. (#2374)
v2 streaming: Preserve backticks inside JSON string values during streamed JSON extraction.
v2 multimodal: Accept raw bytes in Image.autodetect() for JPEG, PNG, GIF, and WebP, while raising clear errors for unsupported image inputs. (#2344)
Docs: Refresh stale OpenAI and Ollama model strings in documentation examples. (#2395)

Open source →

1.15.315 Jun 2026

fix(templating): skip non-text Parts in GENAI/VertexAI mode by @jxnl in #2259

What's Changed

fix(templating): skip non-text Parts in GENAI/VertexAI mode by @jxnl in #2259
chore(deps): bump the poetry group across 1 directory with 6 updates by @dependabot[bot] in #2258
fix: preserve descriptions in responses tools mode by @jxnl in #2261
test: cover partial streaming for PEP 604 unions by @jxnl in #2262
build(docs): use uv for pages deploy by @jxnl in #2266
fix(streaming): surface reasoning summary events in RESPONSES_TOOLS mode by @ayushh0110 in #2299
fix(logging): redact api_key and sensitive keys in handle_response_model debug log by @xodn348 in #2297
fix(anthropic): exclude None fields when serialising tool-use blocks on reask by @xodn348 in #2301
build: bump litellm upper bound to 1.83.7 by @Kcstring in #2292
fix(retry): let IncompleteOutputException propagate without wrapping by @RudrenduPaul in #2280
refactor(v2): complete migration cleanup and typing coverage by @jxnl-oai in #2303
ci: replace ai labeler with oss triage workflows by @jxnl-oai in #2349
chore(types): strengthen ty coverage by @jxnl-oai in #2348
fix(v2): consolidate minor runtime fixes by @jxnl in #2340
fix(v2): consolidate latest runtime and docs fixes by @jxnl in #2373

New Contributors

@ayushh0110 made their first contribution in #2299
@xodn348 made their first contribution in #2297
@Kcstring made their first contribution in #2292
@RudrenduPaul made their first contribution in #2280
@jxnl-oai made their first contribution in #2303

Full Changelog: v1.15.1...v1.15.3

Open source →

Additional notes

Fixed

Bedrock: Route top_k/topK through additionalModelRequestFields instead of leaving it as a top-level Converse kwarg. AWS InferenceConfiguration only supports maxTokens/stopSequences/temperature/topP, so a leftover top_k reached client.converse(top_k=...) and boto3 raised ParamValidationError: Unknown parameter "top_k".
Gemini/GenAI: Fold generation_config (and safety_settings/thinking_config) into config when response_model=None, so plain-text calls no longer raise generate_content() got an unexpected keyword argument 'generation_config' (#2366).
v2 cleanup: Consolidate small provider/runtime fixes for Gemini JSON prompts, Cohere templating, JSON array extraction, iterable streaming, missing jsonref dependency guidance, retry semantics and hook metadata, and multimodal autodetection.

Tests / CI

Type checking: Upgrade to ty 0.0.44, enforce warning-free checks with GitHub annotations, cover V2 tests, validate supported Python versions and platforms, and strengthen installed-package public API typing tests.

Open source →

1.15.13 Apr 2026

Bedrock : Block remote HTTP(S) image URL fetching in _openai_image_part_to_bedrock — only data: URLs accepted, preventing SSRF via user-controlled ima

Security

Bedrock: Block remote HTTP(S) image URL fetching in _openai_image_part_to_bedrock — only data: URLs accepted, preventing SSRF via user-controlled image URLs
Bedrock/PDF: Block remote URL and local file fetching in PDF.to_bedrock — only base64 data or s3:// sources supported, preventing SSRF and local file disclosure

Added

Hooks: completion:error and completion:last_attempt handlers now receive attempt_number, max_attempts, and is_last_attempt as keyword arguments. Old-style handlers remain fully backward-compatible.
Anthropic: from_provider("anthropic/...") now sets a User-Agent: instructor/<version> header on the Anthropic client

Fixed

Anthropic usage: Initialize usage correctly for ANTHROPIC_REASONING_TOOLS and ANTHROPIC_PARALLEL_TOOLS modes
OpenRouter: Use reask_md_json for OPENROUTER_STRUCTURED_OUTPUTS retries instead of reask_default (tool-call format)
Templating: Return kwargs unchanged instead of None in handle_templating when message list is empty or unrecognized
from_openai: Allow Mode.JSON_SCHEMA for the OpenAI provider
Bedrock: Pass through cachePoint dicts in message content unchanged (regression since v1.13.0)
Bedrock: Allow Mode.MD_JSON in from_bedrock
Parallel tools: ParallelBase generator consumed into ListResponse in both sync and async paths, fixing AttributeError

Dependencies

Bump anthropic 0.76.0 → 0.88.0
Bump litellm upper bound to ≤1.83.0
Bump aiohttp 3.13.3 → 3.13.5

Open source →

Additional notes

Security

Bedrock: Block remote HTTP(S) image URL fetching in _openai_image_part_to_bedrock — only data: URLs are now accepted, preventing SSRF via user-controlled image URLs
Bedrock/PDF: Block remote URL and local file fetching in PDF.to_bedrock — only base64 data or s3:// sources are now supported, preventing SSRF and local file disclosure

Added

Hooks: completion:error and completion:last_attempt handlers now receive attempt_number, max_attempts, and is_last_attempt as keyword arguments. Old-style handlers remain fully backward-compatible.
Anthropic: from_provider("anthropic/...") now sets a User-Agent: instructor/<version> header on the Anthropic client

Fixed

Anthropic usage: Initialize usage correctly for ANTHROPIC_REASONING_TOOLS and ANTHROPIC_PARALLEL_TOOLS modes — previously fell through to OpenAI usage tracking with wrong field names
OpenRouter: Use reask_md_json for OPENROUTER_STRUCTURED_OUTPUTS retries instead of reask_default (tool-call format), fixing malformed retry prompts
Templating: Return kwargs unchanged instead of None in handle_templating when message list is empty or format is unrecognized; process_message also now returns the original message unchanged for unrecognized formats instead of None
from_openai: Allow Mode.JSON_SCHEMA for the OpenAI provider — it was incorrectly blocked by the mode validation check
Bedrock: Pass through cachePoint dicts in message content unchanged — previously raised ValueError: Unsupported dict content for Bedrock, breaking prompt caching (regression since v1.13.0)
Bedrock: Allow Mode.MD_JSON in from_bedrock
Parallel tools: ParallelBase generator now consumed into ListResponse in both sync and async paths, fixing AttributeError when setting _raw_response on a generator

Open source →

1.15.02 Apr 2026

Validation : Fix Validator to require is_valid field

What's Changed

Validation: Fix Validator to require is_valid field (#2230)
Gemini: Handle GEMINI_TOOLS in async streaming paths (#2135)
CLI: Add --full-id flag to show complete batch IDs (#2068)
Providers: Remove opinionated system prompt from JSON mode (#2069)
Mode: Add missing GENAI and Responses modes to tool_modes() (#2072)
xAI: Make xai-sdk optional at runtime (#2043, #2094)
Docs: Add canonical OpenAI starter example (#2117)
Deps: Bump dependencies (#2042)

Full diff: v1.14.5...v1.15.0

Open source →

Additional notes

Security

Pin litellm to <=1.82.6 to block compromised versions 1.82.7 and 1.82.8 (#2219)
Make diskcache an optional dependency, removing it from all users' transitive dependency trees and mitigating CVE-2025-69872 (#2211)

Fixed

Usage tracking: Preserve response.usage subclass type (e.g. LiteLLM, Langfuse) when accumulating token counts across retries — fixes downstream .get() method loss (#2217, #2199)
Gemini: Exclude HARM_CATEGORY_IMAGE_* safety categories from standard Gemini API calls — these are Vertex AI-only and caused 400 INVALID_ARGUMENT errors (#2174)
Gemini: Detect truncated responses (finish_reason=MAX_TOKENS) in GENAI_STRUCTURED_OUTPUTS mode and raise IncompleteOutputException immediately instead of retrying with malformed JSON (#2232)
create_with_completion: Handle List[Model] response models that lack _raw_response attribute — previously raised AttributeError, now returns None for the completion (#2167)
Partial streaming: Preserve default Literal field values (e.g. type: Literal["Person"] = "Person") during streaming instead of emitting None before the field arrives (#2204)
Partial streaming: Support PEP 604 union syntax (str | int) in Partial models on Python 3.10+ (#2200)
Validators: Fix allow_override=True in llm_validator — the override branch was unreachable due to a misplaced assertion, so fixed_value was never returned (#2215)
Parallel tools: ParallelBase responses now return ListResponse (consistent with IterableBase) instead of a raw generator with _raw_response set on it (#2216)
Multimodal: Add missing continue in convert_messages after handling typed (audio/image) messages — previously fell through to message["role"] causing KeyError (#2139)
Anthropic: Fix dead code path for ANTHROPIC_REASONING_TOOLS mode — the mode was shadowed by a duplicate ANTHROPIC_TOOLS check and never routed correctly (#2140)

Added

Models: Add Claude 4 (Opus, Sonnet, Haiku), OpenAI GPT-4.1 series, o3/o4 reasoning models, xAI Grok 3, and DeepSeek R1/V3 to KnownModelName type (#2235)

Docs

Update GitHub organization links in README from instructor-ai to 567-labs (#2149)

Tests / CI

Fix test_xai_optional_dependency tests to use monkeypatch so they pass regardless of whether xai-sdk is installed
Update deprecated Anthropic model names (claude-3-5-haiku-latest -> claude-haiku-4-0-20250414, claude-3-7-sonnet-latest -> claude-sonnet-4-5-20250514)
Update deprecated OpenAI model names (gpt-3.5-turbo -> gpt-4.1-mini) across unit tests
Update stale provider model strings in shared_config.py: Writer palmyra-x5, Fireworks llama-v3p3, Perplexity sonar-pro

Open source →

1.14.529 Jan 2026

fix(metadata): populate author field for PyPI stats

Changes

fix(metadata): populate author field for PyPI stats

Separate author names from emails so hatchling populates the Author metadata field correctly. pypistats.org reads this field and was showing "None" because the names were only in author_email.

Open source →

Additional notes

Fixed

Google GenAI: thought_signature is now preserved across validation retries for thinking models (#2001)
Metadata: pyproject.toml author field corrected so PyPI correctly populates the Author field (#2015)
Deps: Dev dependencies moved to the correct [dependency-groups] section in pyproject.toml (#2030)

Open source →

1.14.416 Jan 2026

refactor(json_tracker): simplify using sibling heuristic by @thomasnormal in #2000

What's Changed

refactor(json_tracker): simplify using sibling heuristic by @thomasnormal in #2000
Responses API validation error by @jxnl in #2002
GenAI config labels loss by @jxnl in #2005
GenAI SafetySettings image content by @jxnl in #2007
List object crashes fix by @jxnl in #2011
New release preparation by @jxnl in #2013

Full Changelog: v1.14.3...v1.14.4

Open source →

Additional notes

Fixed

Responses API: Validation errors during structured output parsing are now caught and retried correctly (#2002)
Google GenAI: User-provided GenerationConfig labels and custom fields are no longer silently dropped when merging configs (#2005)
Google GenAI: SafetySettings now applied correctly when request contains image content (#2007)
List responses: Response wrappers no longer crash on attribute-style access (#2011)
_raw_response: Attribute access on list response wrappers works correctly (#2012)

Changed

json_tracker: Sibling-heuristic algorithm simplified for improved partial-streaming reliability (#2000)

Open source →

1.14.313 Jan 2026Deprecated

PartialLiteralMixin is now deprecated - completeness-based validation handles Literal/Enum types automatically

Added

Completeness-based validation for Partial streaming - only validates JSON structures that are structurally complete (#1999)
New JsonCompleteness class in instructor/dsl/json_tracker.py for tracking JSON completeness during streaming (#1999)

Fixed

Fixed Stream objects crashing reask handlers when using streaming with max_retries > 1 (#1992)
Field constraints (min_length, max_length, ge, le, etc.) now work correctly during streaming (#1999)

Deprecated

PartialLiteralMixin is now deprecated - completeness-based validation handles Literal/Enum types automatically (#1999)

Full Changelog: v1.14.2...v1.14.3

Open source →

Additional notes

Added

Partial streaming: Completeness-based streaming validation — fields are validated progressively rather than failing mid-stream (#1999)

Fixed

Streaming reask: Stream objects in reask handlers are now consumed correctly before retry, preventing stale-stream errors (#1992)

Open source →

1.14.213 Jan 2026

Fixed model validators crashing during partial streaming by skipping them until streaming completes

Fixed

Fixed model validators crashing during partial streaming by skipping them until streaming completes (#1994)
Fixed infinite recursion with self-referential models in Partial (e.g., TreeNode with children: List["TreeNode"]) (#1997)

Added

Added PartialLiteralMixin documentation for handling Literal/Enum types during streaming (#1994)
Added final validation against original model after streaming completes to enforce required fields (#1994)
Added tests for recursive Partial models (#1997)

Full Changelog: v1.14.1...v1.14.2

Open source →

Additional notes

Fixed

Partial streaming: Model validators now skip during partial streaming and run only once on the final complete object, preventing spurious errors (#1994)
Partial: Infinite recursion with self-referential models (e.g. TreeNode with children: List["TreeNode"]) is now prevented (#1997)

Tests / CI

Provider tests skipped in CI when API secrets are not available (#1990)

Open source →

1.14.18 Jan 2026

fix(genai): Support cached_content for Google context caching by @b-antosik-marcura in #1987

What's Changed

fix(genai): Support cached_content for Google context caching by @b-antosik-marcura in #1987

New Contributors

@b-antosik-marcura made their first contribution in #1987

Full Changelog: v1.14.0...v1.14.1

Open source →

Additional notes

Fixed

Google GenAI: cached_content parameter now correctly forwarded to support Google context caching (#1987)

Open source →

1.13.06 Nov 2025

fix: Gemini HARM_CATEGORY_JAILBREAK and Anthropic tool_result blocks by @jxnl in https://github.com/567-labs/instructor/pull/1867

What's Changed

fix: Gemini HARM_CATEGORY_JAILBREAK and Anthropic tool_result blocks by @jxnl in https://github.com/567-labs/instructor/pull/1867
fix(genai): fix Gemini streaming by @DaveOkpare in https://github.com/567-labs/instructor/pull/1864
fix(processing): ensure JSON decode errors are caught by retry; add regression tests for JSON mode (#1856) by @devin-ai-integration[bot] in https://github.com/567-labs/instructor/pull/1857
fix: resolve type checking diagnostics by @jxnl in https://github.com/567-labs/instructor/pull/1854
fix: update openai dependency version constraints in pyproject.toml and uv.lock to support v2 by @vishnu-itachi in https://github.com/567-labs/instructor/pull/1858
feat: add py.typed marker for type checking by @jxnl in https://github.com/567-labs/instructor/pull/1868
feat(Bedrock): add image support to Bedrock by @geekbass in https://github.com/567-labs/instructor/pull/1874
chore(deps): bump the poetry group across 1 directory with 162 updates by @dependabot[bot] in https://github.com/567-labs/instructor/pull/1859
Fix/ci uv migration by @jxnl in https://github.com/567-labs/instructor/pull/1886

New Contributors

@vishnu-itachi made their first contribution in https://github.com/567-labs/instructor/pull/1858
@geekbass made their first contribution in https://github.com/567-labs/instructor/pull/1874

Full Changelog: https://github.com/567-labs/instructor/compare/v1.12.0...v1.13.0

Open source →

Additional notes

Added

Bedrock: Image input support — converts OpenAI-style image parts to Bedrock's native format
py.typed: Marker file restored for PEP 561 type-checking support (#1868)

Fixed

disable_pydantic_error_url(): Now correctly suppresses Pydantic validation error URLs via monkey-patching ValidationError.__str__() (environment variable approach had no effect post-import)
JSON mode: JSON decode errors now trigger retry logic instead of surfacing as unhandled exceptions (#1856)
Gemini: Streaming fixed for the Google GenAI SDK (#1864)
Gemini: HARM_CATEGORY_JAILBREAK safety category and Anthropic tool_result content blocks now handled correctly (#1867)
Partial: Fields with default_factory no longer retain the factory when made optional during streaming
OpenAI: Dependency version constraint updated to support v2 (#1858)

Open source →

1.12.027 Oct 2025Deprecated

fix: replace deprecated gpt-3.5-turbo-0613 with gpt-4o-mini by @sergiobayona in https://github.com/567-labs/instructor/pull/1830

What's Changed

feat: add mkdocs-llmstxt plugin and llms.txt support by @jxnl in https://github.com/567-labs/instructor/pull/1795
Restore multimodal import compatibility by @jxnl in https://github.com/567-labs/instructor/pull/1797
feat(retry): add comprehensive tracking of all failed attempts and exceptions by @jxnl in https://github.com/567-labs/instructor/pull/1802
feat(hooks): add hook combination and per-call hooks support by @jxnl in https://github.com/567-labs/instructor/pull/1803
feat(retry): propagate failed attempts through reask handlers by @jxnl in https://github.com/567-labs/instructor/pull/1804
fix(responses): generalize tool call parsing for reasoning models by @sapountzis in https://github.com/567-labs/instructor/pull/1799
feat(xai): add streaming support for xAI provider by @jeongyoonm in https://github.com/567-labs/instructor/pull/1758
fix(openai): reask functionality broken in JSON mode since v1.9.0 by @pnkvalavala in https://github.com/567-labs/instructor/pull/1793
fix(openai): remove duplicate schema from messages in JSON_SCHEMA mode by @pnkvalavala in https://github.com/567-labs/instructor/pull/1761
Handle Anthropic tool_use retries on ValidationError by @kelvin-tran in https://github.com/567-labs/instructor/pull/1810
Investigate instructor client import errors by @jxnl in https://github.com/567-labs/instructor/pull/1818
fix: replace deprecated gpt-3.5-turbo-0613 with gpt-4o-mini by @sergiobayona in https://github.com/567-labs/instructor/pull/1830
Update blog post link for LLM validation examples by @Mr-Ruben in https://github.com/567-labs/instructor/pull/1824
Debug parse error hook not emitted by @jxnl in https://github.com/567-labs/instructor/pull/1819
only use thinking_config in GenerateContentConfig by @jonbuffington in https://github.com/567-labs/instructor/pull/1751
fix: Handle Gemini chunk.text ValueError when finish_reason=1 by @jxnl in https://github.com/567-labs/instructor/pull/1809
docs: replace deprecated validation_context with context parameter by @devin-ai-integration[bot] in https://github.com/567-labs/instructor/pull/1831
docs(validation): add context parameter examples and fix error output by @devin-ai-integration[bot] in https://github.com/567-labs/instructor/pull/1833
also add pop thinking_config to handle_genai_tools by @oegedijk in https://github.com/567-labs/instructor/pull/1834
update cohere text models. by @phlogisticfugu in https://github.com/567-labs/instructor/pull/1840
fix(cohere): improve V2 API version detection and add documentation by @jxnl in https://github.com/567-labs/instructor/pull/1844
doc(openrouter): use explicit async_client=False by @wongjiahau in https://github.com/567-labs/instructor/pull/1847
Fix json parsing by @NicolasPllr1 in https://github.com/567-labs/instructor/pull/1836
fix: Bedrock OpenAI models response parsing (reasoning before text) by @len-foss in https://github.com/567-labs/instructor/pull/1860
fix: Python 3.13 compatibility and import path corrections by @jxnl in https://github.com/567-labs/instructor/pull/1866

New Contributors

@sapountzis made their first contribution in https://github.com/567-labs/instructor/pull/1799
@jeongyoonm made their first contribution in https://github.com/567-labs/instructor/pull/1758
@pnkvalavala made their first contribution in https://github.com/567-labs/instructor/pull/1793
@kelvin-tran made their first contribution in https://github.com/567-labs/instructor/pull/1810
@sergiobayona made their first contribution in https://github.com/567-labs/instructor/pull/1830
@Mr-Ruben made their first contribution in https://github.com/567-labs/instructor/pull/1824
@jonbuffington made their first contribution in https://github.com/567-labs/instructor/pull/1751
@phlogisticfugu made their first contribution in https://github.com/567-labs/instructor/pull/1840
@wongjiahau made their first contribution in https://github.com/567-labs/instructor/pull/1847
@NicolasPllr1 made their first contribution in https://github.com/567-labs/instructor/pull/1836
@len-foss made their first contribution in https://github.com/567-labs/instructor/pull/1860

Full Changelog: https://github.com/567-labs/instructor/compare/1.11.2...v1.12.0

Open source →

Additional notes

Fixed

Python 3.13: Compatibility issues and import path corrections in multimodal processing
Bedrock: OpenAI-compatible models now correctly parse responses where reasoning appears before text content
Gemini: chunk.text ValueError when finish_reason=1 no longer crashes streaming
Gemini: thinking_config no longer unintentionally passed to the tools helper
OpenAI: parse:error hook now correctly fires for InstructorValidationError
JSON parsing: Broken regex patterns removed from JSON extraction function
Cohere: V2 API version detection improved (#1844)

Open source →

1.11.39 Sept 2025

feat: add mkdocs-llmstxt plugin and llms.txt support by @jxnl in https://github.com/567-labs/instructor/pull/1795

What's Changed

feat: add mkdocs-llmstxt plugin and llms.txt support by @jxnl in https://github.com/567-labs/instructor/pull/1795
Restore multimodal import compatibility by @jxnl in https://github.com/567-labs/instructor/pull/1797
feat(retry): add comprehensive tracking of all failed attempts and exceptions by @jxnl in https://github.com/567-labs/instructor/pull/1802
feat(hooks): add hook combination and per-call hooks support by @jxnl in https://github.com/567-labs/instructor/pull/1803

Full Changelog: https://github.com/567-labs/instructor/compare/1.11.2...v1.11.3

Open source →

Additional notes

Added

Hooks: Hook combination via __add__ / combine() — merge multiple hook handlers together
Hooks: Per-call hooks — pass hooks directly to individual .create() calls without registering globally
Retry: InstructorRetryException now tracks all failed attempts including exceptions and raw completions for better introspection
Docs: llms.txt support via mkdocs-llmstxt plugin for AI/LLM consumers

Fixed

InstructorError.__str__(): Now correctly formats failed-attempt details
Retry: Failed attempts propagated through reask handlers
Imports: Backward compatibility imports restored for function_calls and validators modules

Open source →

1.11.227 Aug 2025

feat: Add automated bi-weekly scheduled releases by @jxnl in https://github.com/567-labs/instructor/pull/1787

What's Changed

feat: Add automated bi-weekly scheduled releases by @jxnl in https://github.com/567-labs/instructor/pull/1787
feat: Enhanced Google Cloud Storage Support for Multimodal Classes by @jxnl in https://github.com/567-labs/instructor/pull/1788
Fix GCS URI Support for PDF and Audio Classes by @DaveOkpare in https://github.com/567-labs/instructor/pull/1763
fix(exceptions): restore backwards compatibility for instructor.exceptions imports by @jxnl in https://github.com/567-labs/instructor/pull/1789

Full Changelog: https://github.com/567-labs/instructor/compare/v1.11.1...1.11.2

Open source →

1.11.027 Aug 2025Deprecated

Fix Pydantic v2 deprecation warnings by migrating from class Config to ConfigDict by @anistark in https://github.com/567-labs/instructor/pull/1782

What's Changed

fix(auto_client): add support for litellm provider in from_provider by @jxnl in https://github.com/567-labs/instructor/pull/1723
refactor(utils): complete provider-specific utility reorganization by @jxnl in https://github.com/567-labs/instructor/pull/1722
refactor: move provider-specific message conversion to handlers by @jxnl in https://github.com/567-labs/instructor/pull/1724
Update contributing docs for provider utilities by @jxnl in https://github.com/567-labs/instructor/pull/1725
Add consistent docstrings to utils modules by @jxnl in https://github.com/567-labs/instructor/pull/1726
feat: add xAI utils pattern following standard provider structure by @jxnl in https://github.com/567-labs/instructor/pull/1728
fix: implement missing hooks (completion:error and completion:last_attempt) by @jxnl in https://github.com/567-labs/instructor/pull/1729
Reorganize codebase from flat structure to modular architecture by @jxnl in https://github.com/567-labs/instructor/pull/1730
refactor: remove backward compatibility modules by @jxnl in https://github.com/567-labs/instructor/pull/1731
feat: Add comprehensive tests for XAI _raw_response functionality by @devin-ai-integration[bot] in https://github.com/567-labs/instructor/pull/1735
feat(batch): add in-memory batching support and improve error handling by @jxnl in https://github.com/567-labs/instructor/pull/1746
chore: update author joschka website by @joschkabraun in https://github.com/567-labs/instructor/pull/1765
fix(docs): correct broken tutorials navigation link by @cz3k in https://github.com/567-labs/instructor/pull/1768
feat(docs): Truefoundry AI Gateway integration with Instructor by @rishiraj-tf in https://github.com/567-labs/instructor/pull/1767
Fix Pydantic v2 deprecation warnings by migrating from class Config to ConfigDict by @anistark in https://github.com/567-labs/instructor/pull/1782
Add OpenRouter provider support to auto_client routing by @devin-ai-integration[bot] in https://github.com/567-labs/instructor/pull/1783

New Contributors

@cz3k made their first contribution in https://github.com/567-labs/instructor/pull/1768
@rishiraj-tf made their first contribution in https://github.com/567-labs/instructor/pull/1767
@anistark made their first contribution in https://github.com/567-labs/instructor/pull/1782

Full Changelog: https://github.com/567-labs/instructor/compare/1.10.0...v1.11.0

Open source →

Additional notes

Added

OpenRouter: Provider support in from_provider() using OPENROUTER_API_KEY
LiteLLM: Provider support in from_provider() (#1723)
xAI: Provider utilities following standard provider structure (#1728)
Batch API: In-memory batching support with improved error handling for OpenAI and Anthropic (#1746)
Hooks: completion:error and completion:last_attempt hooks now fully implemented (#1729)

Changed

Codebase reorganized from flat structure to modular provider-based architecture (#1730)
Provider-specific message conversion logic moved to dedicated handlers (#1724)

Fixed

Pydantic v2 deprecation warnings resolved by migrating from class Config to ConfigDict (#1782)

Open source →

1.10.018 Jul 2025Deprecated

Deprecate google-generativeai in favor of google-genai by @jxnl in https://github.com/567-labs/instructor/pull/1673

What's Changed

Update integrations to from_provider API by @jxnl in https://github.com/567-labs/instructor/pull/1668
feat: Add native caching support with AutoCache and RedisCache adapters by @jxnl in https://github.com/567-labs/instructor/pull/1674
feat: Enhance GitHub Actions workflow for testing by @jxnl in https://github.com/567-labs/instructor/pull/1675
Deprecate google-generativeai in favor of google-genai by @jxnl in https://github.com/567-labs/instructor/pull/1673
Fix batch request parsing by @jxnl in https://github.com/567-labs/instructor/pull/1677
Enhance batch API with multi-provider support and improved CLI by @jxnl in https://github.com/567-labs/instructor/pull/1678
split off dev dependencies by @hwong557 in https://github.com/567-labs/instructor/pull/1685
Add Claude Code GitHub Workflow by @jxnl in https://github.com/567-labs/instructor/pull/1688
fix(genai): handle response_model=None for GenAI modes by @jxnl in https://github.com/567-labs/instructor/pull/1694
fix: correct is_simple_type logic for list types with BaseModel contents by @jxnl in https://github.com/567-labs/instructor/pull/1698
fix(genai): add automatic Partial wrapping for streaming requests by @jxnl in https://github.com/567-labs/instructor/pull/1695
fix(bedrock): add Bedrock-native format conversion to OpenAI format by @jxnl in https://github.com/567-labs/instructor/pull/1696
fix(tests): improve prompt for UserExtract in gemini stream test by @jxnl in https://github.com/567-labs/instructor/pull/1700
feat(bedrock): improve documentation and auto client support by @jxnl in https://github.com/567-labs/instructor/pull/1686
chore(ci): run docs test monthly by @jxnl in https://github.com/567-labs/instructor/pull/1699
Enhance logging and docs by @jxnl in https://github.com/567-labs/instructor/pull/1702
chore: remove .vscode/settings.json from tracking by @jxnl in https://github.com/567-labs/instructor/pull/1705
fix(genai): forward thinking_config parameter to Gemini models by @jxnl in https://github.com/567-labs/instructor/pull/1704
Fix/decimal support genai by @jxnl in https://github.com/567-labs/instructor/pull/1712
docs: update provider syntax by @jxnl in https://github.com/567-labs/instructor/pull/1713
feat(provider): add deepseek support by @NasonZ in https://github.com/567-labs/instructor/pull/1715
feat(auto_client): add comprehensive api_key parameter support for all providers by @johnwlockwood in https://github.com/567-labs/instructor/pull/1717
Add Anthropic parallel tool support by @jxnl in https://github.com/567-labs/instructor/pull/1719

New Contributors

@hwong557 made their first contribution in https://github.com/567-labs/instructor/pull/1685
@johnwlockwood made their first contribution in https://github.com/567-labs/instructor/pull/1717

Full Changelog: https://github.com/567-labs/instructor/compare/1.9.2...1.10.0

Open source →

1.9.27 Jul 2025

Fix docs build path by @jxnl in https://github.com/567-labs/instructor/pull/1662

What's Changed

Fix docs build path by @jxnl in https://github.com/567-labs/instructor/pull/1662
Revert "refactor: simplify safety settings configuration for Gemini API" by @jxnl in https://github.com/567-labs/instructor/pull/1664
Skip LLM tests without API keys by @jxnl in https://github.com/567-labs/instructor/pull/1665
Add xAI provider by @jxnl in https://github.com/567-labs/instructor/pull/1661
Fix GenAI image harm categories by @jxnl in https://github.com/567-labs/instructor/pull/1667

Full Changelog: https://github.com/567-labs/instructor/compare/1.9.1...1.9.2

Open source →

1.9.17 Jul 2025

feat: add Azure OpenAI support to auto_client.py by @jxnl in https://github.com/567-labs/instructor/pull/1633

What's Changed

feat: add Azure OpenAI support to auto_client.py by @jxnl in https://github.com/567-labs/instructor/pull/1633
fix: expose exception classes in public API by @ivanleomk in https://github.com/567-labs/instructor/pull/1613
Update TaskAction method description for clarity on task creation and… by @eaedk in https://github.com/567-labs/instructor/pull/1637
Fix SambaNova capitalization by @jxnl in https://github.com/567-labs/instructor/pull/1651
refactor: simplify safety settings configuration for Gemini API by @DaveOkpare in https://github.com/567-labs/instructor/pull/1659
Json schema fix by @Canttuchdiz in https://github.com/567-labs/instructor/pull/1657

New Contributors

@eaedk made their first contribution in https://github.com/567-labs/instructor/pull/1637
@Canttuchdiz made their first contribution in https://github.com/567-labs/instructor/pull/1657

Full Changelog: https://github.com/567-labs/instructor/compare/1.9.0...1.9.1

Open source →

1.9.021 Jun 2025

feat: Improve error handling with comprehensive exception hierarchy by @jxnl in https://github.com/567-labs/instructor/pull/1549

What's Changed

feat: Improve error handling with comprehensive exception hierarchy by @jxnl in https://github.com/567-labs/instructor/pull/1549
Remove enable_prompt_caching from Anthropic integration since we ha… by @ivanleomk in https://github.com/567-labs/instructor/pull/1562
Fix/docs by @ivanleomk in https://github.com/567-labs/instructor/pull/1561
lock by @jxnl in https://github.com/567-labs/instructor/pull/1565
Fix/gemini config by @ivanleomk in https://github.com/567-labs/instructor/pull/1563
feat(deps): allow rich version 14+ by @devin-ai-integration in https://github.com/567-labs/instructor/pull/1566
chore(deps): bump the poetry group across 1 directory with 26 updates by @dependabot in https://github.com/567-labs/instructor/pull/1569
chore(deps): bump anthropic from 0.52.0 to 0.52.1 in the poetry group by @dependabot in https://github.com/567-labs/instructor/pull/1571
Standardize async parameter naming in VertexAI client by @devin-ai-integration in https://github.com/567-labs/instructor/pull/1555
Add Claude Code GitHub Workflow by @ivanleomk in https://github.com/567-labs/instructor/pull/1575
feat: update README to reflect 3M monthly downloads milestone by @ivanleomk in https://github.com/567-labs/instructor/pull/1577
fix(deps): add dev and docs to project.optional-dependencies for uv compatibility by @devin-ai-integration in https://github.com/567-labs/instructor/pull/1581
docs: add Gemini thought parts filtering explanation to GenAI integration by @devin-ai-integration in https://github.com/567-labs/instructor/pull/1583
fix: filter out Gemini thought parts in genai tool parsing by @indigoviolet in https://github.com/567-labs/instructor/pull/1578
Fix documentation for dynamic model creation example by @devin-ai-integration in https://github.com/567-labs/instructor/pull/1567
chore(deps): bump the poetry group across 1 directory with 11 updates by @dependabot in https://github.com/567-labs/instructor/pull/1595
feat: implementation of JSON mode for Writer proider by @yanomaly in https://github.com/567-labs/instructor/pull/1559
feat(auto_client): add Ollama provider support by @jxnl in https://github.com/567-labs/instructor/pull/1602
fix: respect timeout parameter in retry mechanism for Ollama compatibility by @jxnl in https://github.com/567-labs/instructor/pull/1603
fix(reask): handle ThinkingBlock in reask_anthropic_json by @jxnl in https://github.com/567-labs/instructor/pull/1604
feat(docs): Add cross-links to blog posts for better navigation by @jxnl in https://github.com/567-labs/instructor/pull/1605
docs: improve clarity and consistency across documentation by @jxnl in https://github.com/567-labs/instructor/pull/1606
feat: Enable Audio module to work with Windows by @ish-codes-magic in https://github.com/567-labs/instructor/pull/1619
fix(deps): relax tenacity requirement to support google-genai 1.21.1 by @jxnl in https://github.com/567-labs/instructor/pull/1625
fix: resolve pyright TypedDict key access error in dump_message by @jxnl in https://github.com/567-labs/instructor/pull/1626
feat(docs): improve SEO for asyncio and tenacity documentation by @jxnl in https://github.com/567-labs/instructor/pull/1620
Resolve dependency version conflicts by @jxnl in https://github.com/567-labs/instructor/pull/1627
Feat/add gemini optional support by @ivanleomk in https://github.com/567-labs/instructor/pull/1618

New Contributors

@ish-codes-magic made their first contribution in https://github.com/567-labs/instructor/pull/1619

Full Changelog: https://github.com/567-labs/instructor/compare/1.8.3...1.9.0

Open source →

1.8.322 May 2025

docs: improve CLAUDE.md with better architecture description by @jxnl in https://github.com/567-labs/instructor/pull/1525

What's Changed

docs: improve CLAUDE.md with better architecture description by @jxnl in https://github.com/567-labs/instructor/pull/1525
fix(bedrock): minimal working example with from_bedrock client by @dogonthehorizon in https://github.com/567-labs/instructor/pull/1528
docs(blog): fix code block formatting in blog post by @workwithpurwarkrishna in https://github.com/567-labs/instructor/pull/1526
feat(bedrock): sort of add support for async bedrock client by @dogonthehorizon in https://github.com/567-labs/instructor/pull/1530
fix(bedrock): handle default message format for converse endpoint by @dogonthehorizon in https://github.com/567-labs/instructor/pull/1529
Add semantic validation documentation by @jxnl in https://github.com/567-labs/instructor/pull/1541
Implementing support for responses by @ivanleomk in https://github.com/567-labs/instructor/pull/1520
fix: remove failing test by @ivanleomk in https://github.com/567-labs/instructor/pull/1544
fix: bump version by @ivanleomk in https://github.com/567-labs/instructor/pull/1545

New Contributors

@dogonthehorizon made their first contribution in https://github.com/567-labs/instructor/pull/1528
@workwithpurwarkrishna made their first contribution in https://github.com/567-labs/instructor/pull/1526

Full Changelog: https://github.com/567-labs/instructor/compare/1.8.2...1.8.3

Open source →

1.8.215 May 2025

fix: removed print statement by @ivanleomk in https://github.com/567-labs/instructor/pull/1524

What's Changed

fix: removed print statement by @ivanleomk in https://github.com/567-labs/instructor/pull/1524

Full Changelog: https://github.com/567-labs/instructor/compare/1.8.1...1.8.2

Open source →

1.8.19 May 2025

docs(blog): add Anthropic web search structured data blog post by @jxnl in https://github.com/567-labs/instructor/pull/1515

What's Changed

docs(blog): add Anthropic web search structured data blog post by @jxnl in https://github.com/567-labs/instructor/pull/1515
fix: added support for calling streaming from the create method by @ivanleomk in https://github.com/567-labs/instructor/pull/1502
Fix/mkdocs by @ivanleomk in https://github.com/567-labs/instructor/pull/1517
docs(blog): announce unified provider interface (from_provider) by @jxnl in https://github.com/567-labs/instructor/pull/1516
Fix/anthropic web search by @ivanleomk in https://github.com/567-labs/instructor/pull/1519

Full Changelog: https://github.com/567-labs/instructor/compare/1.8.0...1.8.1

Open source →

1.8.07 May 2025

Fix typo by @tdhopper in https://github.com/567-labs/instructor/pull/1468

What's Changed

Fix typo by @tdhopper in https://github.com/567-labs/instructor/pull/1468
bunch of other typos in blog posts fixed by @0xRaduan in https://github.com/567-labs/instructor/pull/1477
remove duplicate providers from integrations page by @0xRaduan in https://github.com/567-labs/instructor/pull/1475
Fix typos in docs/tutorials/ directory by @0xRaduan in https://github.com/567-labs/instructor/pull/1474
Simplify learning docs for new users by @jxnl in https://github.com/567-labs/instructor/pull/1479
fix(google-genai): Add more helpful error messages by @stephen-iezzi in https://github.com/567-labs/instructor/pull/1484
Fix is_simple_type function for list[int | str] in Python 3.10 by @paulelliotco in https://github.com/567-labs/instructor/pull/1458
fix typo by @jss367 in https://github.com/567-labs/instructor/pull/1497
Fix: simple test failure by @ivanleomk in https://github.com/567-labs/instructor/pull/1505
Added a check for genai response by @ivanleomk in https://github.com/567-labs/instructor/pull/1506
Add unified provider interface with string-based initialization by @jxnl in https://github.com/567-labs/instructor/pull/1490

New Contributors

@tdhopper made their first contribution in https://github.com/567-labs/instructor/pull/1468
@0xRaduan made their first contribution in https://github.com/567-labs/instructor/pull/1477
@jss367 made their first contribution in https://github.com/567-labs/instructor/pull/1497

Full Changelog: https://github.com/567-labs/instructor/compare/1.7.9...1.8.0

Open source →

1.7.93 Apr 2025

add async partial streaming support for genai by @oegedijk in https://github.com/instructor-ai/instructor/pull/1441

What's Changed

add async partial streaming support for genai by @oegedijk in https://github.com/instructor-ai/instructor/pull/1441
Update from_litellm type hints to properly return AsyncInstructor by @jonchun in https://github.com/instructor-ai/instructor/pull/1324
docs: add cookbook on tracing with Langfuse by @jannikmaierhoefer in https://github.com/instructor-ai/instructor/pull/1452
Gemini Config Options Documentation by @fjooord in https://github.com/instructor-ai/instructor/pull/1455
feat: add mistral PDF support by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1459
Fix: resolve pyright issues with PDF by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1465

New Contributors

@oegedijk made their first contribution in https://github.com/instructor-ai/instructor/pull/1441
@jonchun made their first contribution in https://github.com/instructor-ai/instructor/pull/1324
@jannikmaierhoefer made their first contribution in https://github.com/instructor-ai/instructor/pull/1452

Full Changelog: https://github.com/instructor-ai/instructor/compare/1.7.8...1.7.9

Open source →

1.7.829 Mar 2025

docs: Add Cursor rules documentation by @jxnl in https://github.com/instructor-ai/instructor/pull/1423

What's Changed

docs: Add Cursor rules documentation by @jxnl in https://github.com/instructor-ai/instructor/pull/1423
docs: improve contributing guidelines with UV installation and conventional comments by @jxnl in https://github.com/instructor-ai/instructor/pull/1424
docs: add LLM documentation and update mkdocs.yml with redirect by @jxnl in https://github.com/instructor-ai/instructor/pull/1425
docs(github): update cursor rules with proper website link and multiline PR instructions by @jxnl in https://github.com/instructor-ai/instructor/pull/1427
Adding Streaming for Mistral and VertexAI by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1420
docs(blog): add post about Cursor rules for Git best practices by @jxnl in https://github.com/instructor-ai/instructor/pull/1430
docs(blog): announce llms.txt implementation by @jxnl in https://github.com/instructor-ai/instructor/pull/1431
chore: add pr_body.md to gitignore by @jxnl in https://github.com/instructor-ai/instructor/pull/1432
docs: add OpenAI audio extraction example by @jxnl in https://github.com/instructor-ai/instructor/pull/1433
feat: added new article by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1446
Bugfix: [minor] Do not fail with google genai models if the content is longer then max file name. Closes #1439 by @sztanko in https://github.com/instructor-ai/instructor/pull/1440

New Contributors

@sztanko made their first contribution in https://github.com/instructor-ai/instructor/pull/1440

Full Changelog: https://github.com/instructor-ai/instructor/compare/1.7.7...1.7.8

Open source →

1.7.717 Mar 2025

feat: adding sync and async example for sambanova by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1415

What's Changed

feat: adding sync and async example for sambanova by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1415
fix: bump version + fix deps by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1417

Full Changelog: https://github.com/instructor-ai/instructor/compare/1.7.6...1.7.7

Open source →

1.7.617 Mar 2025

fix: fixing incorrect import issue by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1414

What's Changed

fix: fixing incorrect import issue by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1414

Full Changelog: https://github.com/instructor-ai/instructor/compare/1.7.5...1.7.6

Open source →

1.7.516 Mar 2025

docs: improve documentation structure with visual diagrams by @jxnl in https://github.com/instructor-ai/instructor/pull/1399

What's Changed

docs: improve documentation structure with visual diagrams by @jxnl in https://github.com/instructor-ai/instructor/pull/1399
Adding Structured Outputs for Mistral by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1391
Docs/update contributing guide by @jxnl in https://github.com/instructor-ai/instructor/pull/1407
Updated SQL Model Example Docs for using SkipJsonSchema by @fjooord in https://github.com/instructor-ai/instructor/pull/1410
Adding support for the GenAI Sdk by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1393
Update UV reps by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1411

New Contributors

@fjooord made their first contribution in https://github.com/instructor-ai/instructor/pull/1410

Full Changelog: https://github.com/instructor-ai/instructor/compare/1.7.4...1.7.5

Open source →

1.7.412 Mar 2025

fix: adding static assets so that we can use them in our tests by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1387

What's Changed

fix: adding static assets so that we can use them in our tests by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1387
fix: update links to point to our repo files by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1388
feat: Adding support for Open Router by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1386
Updating docs and bumping Anthropic version by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1396

Full Changelog: https://github.com/instructor-ai/instructor/compare/1.7.3...1.7.4

Open source →

1.7.36 Mar 2025

feat: add new article on migrating to uv by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1284

What's Changed

feat: add new article on migrating to uv by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1284
Fix Markdown Titles by @Vinnie-Palazeti in https://github.com/instructor-ai/instructor/pull/1298
chore: update run.py by @eltociear in https://github.com/instructor-ai/instructor/pull/1295
Use GEMINI_JSON as default by @dylanjcastillo in https://github.com/instructor-ai/instructor/pull/1286
Add Deepseek Reasoning example by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1334
fix: vertex async example by @domenicocinque in https://github.com/instructor-ai/instructor/pull/1355
Programmatically remove control characters from LLM response by @xtzie in https://github.com/instructor-ai/instructor/pull/1367
feat: Add support for perplexity sonar by @charlieyou in https://github.com/instructor-ai/instructor/pull/1319
Update vertex.md by @aryzle in https://github.com/instructor-ai/instructor/pull/1321
Support for Sonnet 3.7 Reasoning for ANTRHOPIC_JSON by @A-F-V in https://github.com/instructor-ai/instructor/pull/1361
Support for aws bedrock using boto3 by @imZain448 in https://github.com/instructor-ai/instructor/pull/1287
Standardize docs with claude code by @jxnl in https://github.com/instructor-ai/instructor/pull/1369
feat: optimizations by @jxnl in https://github.com/instructor-ai/instructor/pull/1373

New Contributors

@Vinnie-Palazeti made their first contribution in https://github.com/instructor-ai/instructor/pull/1298
@domenicocinque made their first contribution in https://github.com/instructor-ai/instructor/pull/1355
@xtzie made their first contribution in https://github.com/instructor-ai/instructor/pull/1367
@charlieyou made their first contribution in https://github.com/instructor-ai/instructor/pull/1319
@aryzle made their first contribution in https://github.com/instructor-ai/instructor/pull/1321
@A-F-V made their first contribution in https://github.com/instructor-ai/instructor/pull/1361
@imZain448 made their first contribution in https://github.com/instructor-ai/instructor/pull/1287

Full Changelog: https://github.com/instructor-ai/instructor/compare/1.7.2...1.7.3

Open source →

1.7.226 Dec 2024

Migrate to UV by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1280

What's Changed

Migrate to UV by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1280

Full Changelog: https://github.com/instructor-ai/instructor/compare/1.7.1...1.7.2

Open source →

1.7.125 Dec 2024

feat: added cortex documentation by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1225

What's Changed

feat: added cortex documentation by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1225
chore(deps): bump the poetry group across 1 directory with 24 updates by @dependabot in https://github.com/instructor-ai/instructor/pull/1236
docs: Add missing section headers and fix broken links by @devin-ai-integration in https://github.com/instructor-ai/instructor/pull/1232
feat: added a new dag article by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1246
feat: added new article on generating llm metadata by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1249
fixes #1252 by @hnalla in https://github.com/instructor-ai/instructor/pull/1254
Update google.md by @Filimoa in https://github.com/instructor-ai/instructor/pull/1251
fix: BatchJob is updated to work with current OpenAi batch request format by @aomi in https://github.com/instructor-ai/instructor/pull/1240
Update simple_type.py by @stevenbedrick in https://github.com/instructor-ai/instructor/pull/1247
Fixing Pyright Errors by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1267
feat: add Parallel Tool mode for Vertex AI by @devjn in https://github.com/instructor-ai/instructor/pull/1217
fix: Updated broken contributors profile link in README.md by @gokborayilmaz in https://github.com/instructor-ai/instructor/pull/1275
Adding support for Gemini-8b and 2.0 by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1274
fix: update poetry.lock by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1278

New Contributors

@hnalla made their first contribution in https://github.com/instructor-ai/instructor/pull/1254
@Filimoa made their first contribution in https://github.com/instructor-ai/instructor/pull/1251
@aomi made their first contribution in https://github.com/instructor-ai/instructor/pull/1240
@stevenbedrick made their first contribution in https://github.com/instructor-ai/instructor/pull/1247
@devjn made their first contribution in https://github.com/instructor-ai/instructor/pull/1217
@gokborayilmaz made their first contribution in https://github.com/instructor-ai/instructor/pull/1275

Full Changelog: https://github.com/instructor-ai/instructor/compare/1.7.0...1.7.1

Open source →

1.7.027 Nov 2024

feat: adding new article on gemini citations by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1186

What's Changed

feat: adding new article on gemini citations by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1186
docs: restructure navigation and fix code formatting by @devin-ai-integration in https://github.com/instructor-ai/instructor/pull/1191
fix: remove table by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1196
Remove instructor-hub by @devin-ai-integration in https://github.com/instructor-ai/instructor/pull/1197
feat: Writer integration by @yanomaly in https://github.com/instructor-ai/instructor/pull/1167
Adding new tidy table article by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1204
Update cumulative_reason.md by @OxfordOutlander in https://github.com/instructor-ai/instructor/pull/1205
docs: add learnprompting to prompting docs description by @attanavaid in https://github.com/instructor-ai/instructor/pull/1176
Fix tools for OpenAI messages by @chris-sanders in https://github.com/instructor-ai/instructor/pull/1194
Edits to batch.py to support Anthropic batch API by @economy in https://github.com/instructor-ai/instructor/pull/1193
Support nested generics with partial by @mwildehahn in https://github.com/instructor-ai/instructor/pull/1207
docs: update installation and usage examples for LLM integrations by @jxnl in https://github.com/instructor-ai/instructor/pull/1210
feat: enhance multimodal support for images and audio in instructor by @jxnl in https://github.com/instructor-ai/instructor/pull/1212
fix: adding type ignore for pyright by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1215
feat: added deepseek page by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1214

New Contributors

@devin-ai-integration made their first contribution in https://github.com/instructor-ai/instructor/pull/1191
@yanomaly made their first contribution in https://github.com/instructor-ai/instructor/pull/1167
@attanavaid made their first contribution in https://github.com/instructor-ai/instructor/pull/1176
@chris-sanders made their first contribution in https://github.com/instructor-ai/instructor/pull/1194
@economy made their first contribution in https://github.com/instructor-ai/instructor/pull/1193

Full Changelog: https://github.com/instructor-ai/instructor/compare/1.6.4...1.7.0

Open source →

1.6.414 Nov 2024

docs: fix typo in multimodal by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1101

What's Changed

docs: fix typo in multimodal by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1101
fix: added requests as a dependency by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1102
feat: add blog post and example for LLM-based reranker by @jxnl in https://github.com/instructor-ai/instructor/pull/1115
ci: add AI labeler workflow for issues and pull requests by @jxnl in https://github.com/instructor-ai/instructor/pull/1126
fix: typo changes by @nawed2611 in https://github.com/instructor-ai/instructor/pull/1125
gpt 3.5 turbo updated to gpt-40-mini since July 2024 it is recommende… by @sahibpreetsingh12 in https://github.com/instructor-ai/instructor/pull/1122
chore(deps): bump the poetry group across 1 directory with 18 updates by @dependabot in https://github.com/instructor-ai/instructor/pull/1117
doc(blog): added Burr link; fixed date and formatting by @zilto in https://github.com/instructor-ai/instructor/pull/1099
Fixing lint errors in concepts including hooks by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1088
Fix spelling and grammar error by @terrchen in https://github.com/instructor-ai/instructor/pull/1121
Patching Anthropic System by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1130
fix: updated scope of pytest fixture to be function based by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1131
Fix AI Labeler YAML formatting by @jlowin in https://github.com/instructor-ai/instructor/pull/1127
fix: OpenAI prompt details and completion tokens details missing from total usage by @ivanbelenky in https://github.com/instructor-ai/instructor/pull/1105
fix: max_retries typing by @jordyjwilliams in https://github.com/instructor-ai/instructor/pull/1135
feat: Adding new blog post by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1162
fix: use SandboxedEnvironment in templating by @dylanjcastillo in https://github.com/instructor-ai/instructor/pull/1168
feat: Add Gemini PDF example by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1163
fix: fixed up tenacity link by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1173
feat: added new mixin to modify partial parsing behaviour by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1152
fix: removed use_async flag in cerebras client by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1179
fix: bump jiter dep by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1180
fix: bump 1.6.3 to 1.6.4 by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1181

New Contributors

@nawed2611 made their first contribution in https://github.com/instructor-ai/instructor/pull/1125
@sahibpreetsingh12 made their first contribution in https://github.com/instructor-ai/instructor/pull/1122
@dependabot made their first contribution in https://github.com/instructor-ai/instructor/pull/1117
@terrchen made their first contribution in https://github.com/instructor-ai/instructor/pull/1121
@jlowin made their first contribution in https://github.com/instructor-ai/instructor/pull/1127
@ivanbelenky made their first contribution in https://github.com/instructor-ai/instructor/pull/1105
@jordyjwilliams made their first contribution in https://github.com/instructor-ai/instructor/pull/1135
@dylanjcastillo made their first contribution in https://github.com/instructor-ai/instructor/pull/1168

Full Changelog: https://github.com/instructor-ai/instructor/compare/1.6.3...1.6.4

Open source →

1.6.321 Oct 2024

docs: update example to use file_path arg; reflecting updated BatchJob.create_from_messages by @goutham794 in https://github.com/instructor-ai/instruc

What's Changed

docs: update example to use file_path arg; reflecting updated BatchJob.create_from_messages by @goutham794 in https://github.com/instructor-ai/instructor/pull/1096
blog: Youtube flashcards with Instructor + Burr by @zilto in https://github.com/instructor-ai/instructor/pull/1094
docs: update complexity_based.md by @eltociear in https://github.com/instructor-ai/instructor/pull/1098
feat: anthropic batching code by @jxnl in https://github.com/instructor-ai/instructor/pull/1064
Feat: Enhance multimodality by @arcaputo3 in https://github.com/instructor-ai/instructor/pull/1070
feat: add audio support with new Audio class and update documentation by @jxnl in https://github.com/instructor-ai/instructor/pull/1095

New Contributors

@goutham794 made their first contribution in https://github.com/instructor-ai/instructor/pull/1096
@zilto made their first contribution in https://github.com/instructor-ai/instructor/pull/1094

Full Changelog: https://github.com/instructor-ai/instructor/compare/1.6.2...1.6.3

Open source →

1.6.217 Oct 2024

fix: Added off and clear proeprty to Instructor base class by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1087

What's Changed

fix: Added off and clear proeprty to Instructor base class by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1087
Bumping version to 1.6.2 by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1090

Full Changelog: https://github.com/instructor-ai/instructor/compare/1.6.1...1.6.2

Open source →

1.6.117 Oct 2024

Added Jinja2 as a dependency by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1084

What's Changed

Added Jinja2 as a dependency by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1084

Full Changelog: https://github.com/instructor-ai/instructor/compare/1.6.0...1.6.1

Open source →

1.6.017 Oct 2024

Fix compatibility with custom dicts for multimodal message content by @mjvdvlugt in https://github.com/instructor-ai/instructor/pull/1053

What's Changed

Fix compatibility with custom dicts for multimodal message content by @mjvdvlugt in https://github.com/instructor-ai/instructor/pull/1053
Upgrade tenacity dependencity to include 9.0.0 by @Cokral in https://github.com/instructor-ai/instructor/pull/1042
Updating examples by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1049
Adding support for getattrs so that we can access normal methods on wrapped clients by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1061
fix: clean up cohere templating by @jxnl in https://github.com/instructor-ai/instructor/pull/1030
feat: implement hooks by @jxnl in https://github.com/instructor-ai/instructor/pull/1065
Disabling Prompting Tips by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1069
fix: Refactor reasking logic by @jxnl in https://github.com/instructor-ai/instructor/pull/1071
fix: update gemini's safety_settings by @alxpez in https://github.com/instructor-ai/instructor/pull/1057
Fix examples by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1077
Docs: Clean up failing example tests by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1079
Add Fireworks Client by @ivanleomk in https://github.com/instructor-ai/instructor/pull/1073

New Contributors

@mjvdvlugt made their first contribution in https://github.com/instructor-ai/instructor/pull/1053
@Cokral made their first contribution in https://github.com/instructor-ai/instructor/pull/1042
@alxpez made their first contribution in https://github.com/instructor-ai/instructor/pull/1057

Full Changelog: https://github.com/instructor-ai/instructor/compare/1.5.2...1.6.0

Open source →

1.5.28 Oct 2024

Add github dependabot to keep dependencies updated by @noxan in https://github.com/jxnl/instructor/pull/895

What's Changed

Add github dependabot to keep dependencies updated by @noxan in https://github.com/jxnl/instructor/pull/895
Fixed up Cerebras Article edits by @ivanleomk in https://github.com/jxnl/instructor/pull/1043
feat: support multimodal by @jxnl in https://github.com/jxnl/instructor/pull/1045
fix: Add parse_from_string method to BatchJob by @kwilsonmg in https://github.com/jxnl/instructor/pull/1033
Fix Build Errors and update copy by @ivanleomk in https://github.com/jxnl/instructor/pull/1044
Bump version and add partial support by @ivanleomk in https://github.com/jxnl/instructor/pull/1047

Full Changelog: https://github.com/jxnl/instructor/compare/1.5.1...1.5.2

Open source →

1.5.14 Oct 2024

Update fake-data.md by @CodyBontecou in https://github.com/jxnl/instructor/pull/1034

What's Changed

Update fake-data.md by @CodyBontecou in https://github.com/jxnl/instructor/pull/1034
fix: refactor handle_response_model by @jxnl in https://github.com/jxnl/instructor/pull/1032
Added temperature parameter to RequestBody by @kwilsonmg in https://github.com/jxnl/instructor/pull/1019
docs: move mention of max_retries to the correct section by @hartshorne in https://github.com/jxnl/instructor/pull/1017
doc : Add missing import in documentation example by @geekloper in https://github.com/jxnl/instructor/pull/1016

New Contributors

@CodyBontecou made their first contribution in https://github.com/jxnl/instructor/pull/1034
@hartshorne made their first contribution in https://github.com/jxnl/instructor/pull/1017
@geekloper made their first contribution in https://github.com/jxnl/instructor/pull/1016

Full Changelog: https://github.com/jxnl/instructor/compare/1.5.0...1.5.1

Open source →

1.5.030 Sept 2024

doc: add newsletter link by @jxnl in https://github.com/jxnl/instructor/pull/1012

What's Changed

doc: add newsletter link by @jxnl in https://github.com/jxnl/instructor/pull/1012
Updated Caching concepts to update prompt by @ivanleomk in https://github.com/jxnl/instructor/pull/998
Expand litellm anthropic compatibility by @JohanBekker in https://github.com/jxnl/instructor/pull/958
feat: implement jinja templating and rename kwarg to context by @jxnl in https://github.com/jxnl/instructor/pull/1011
Fixed new templating feature throwing an error for gemini by @ivanleomk in https://github.com/jxnl/instructor/pull/1021
Added new Response Body article by @ivanleomk in https://github.com/jxnl/instructor/pull/1024
Fixed up poetry dependencies and google gemini bug with jinja templating by @ivanleomk in https://github.com/jxnl/instructor/pull/1023
Bump version to 1.5 by @ivanleomk in https://github.com/jxnl/instructor/pull/1028

New Contributors

@JohanBekker made their first contribution in https://github.com/jxnl/instructor/pull/958

Full Changelog: https://github.com/jxnl/instructor/compare/1.4.3...1.5.0

Open source →

1.4.319 Sept 2024

Fixed up a new article for prompt caching by @ivanleomk in https://github.com/jxnl/instructor/pull/997

What's Changed

Fixed up a new article for prompt caching by @ivanleomk in https://github.com/jxnl/instructor/pull/997
fix(rag-and-beyond.md): Formatting by @PLNech in https://github.com/jxnl/instructor/pull/1006
chore(exact_citations.md): Fix punctuation (extra . after a !) by @PLNech in https://github.com/jxnl/instructor/pull/1004
Fixed up failing test cases for partial parsing by @ivanleomk in https://github.com/jxnl/instructor/pull/1001
Bump Anthropic Version by @ivanleomk in https://github.com/jxnl/instructor/pull/1002
test: add partial parsing check by @mrdkucher in https://github.com/jxnl/instructor/pull/1007
Tentative Fix for Mistral Fix by @ivanleomk in https://github.com/jxnl/instructor/pull/985
Fixed up support for list content types when used with Gemini by @ivanleomk in https://github.com/jxnl/instructor/pull/999

New Contributors

@PLNech made their first contribution in https://github.com/jxnl/instructor/pull/1006

Full Changelog: https://github.com/jxnl/instructor/compare/1.4.2...1.4.3

Open source →

1.4.214 Sept 2024

Fixed typo in the installation command by @ivanleomk in https://github.com/jxnl/instructor/pull/983

What's Changed

Fixed typo in the installation command by @ivanleomk in https://github.com/jxnl/instructor/pull/983
Adding support for O1 by @ivanleomk in https://github.com/jxnl/instructor/pull/991
fix: handle whitespace in json streams by @mrdkucher in https://github.com/jxnl/instructor/pull/995
Bumping the version of instructor to 1.4.2 by @ivanleomk in https://github.com/jxnl/instructor/pull/992
Fixing blog typo for post "Should I Be Using Structured Outputs?" by @kwilsonmg in https://github.com/jxnl/instructor/pull/993

New Contributors

@mrdkucher made their first contribution in https://github.com/jxnl/instructor/pull/995
@kwilsonmg made their first contribution in https://github.com/jxnl/instructor/pull/993

Full Changelog: https://github.com/jxnl/instructor/compare/1.4.1...1.4.2

Open source →

1.4.16 Sept 2024

Correct small typos on Structured Output post by @ivanleomk in https://github.com/jxnl/instructor/pull/945

What's Changed

Correct small typos on Structured Output post by @ivanleomk in https://github.com/jxnl/instructor/pull/945
Modified Conclusion of Structured Outputs Post by @ivanleomk in https://github.com/jxnl/instructor/pull/950
Bugfix: Literal while streaming does not work by @roeybc in https://github.com/jxnl/instructor/pull/948
Helping fix some Gemini errors by @ivanleomk in https://github.com/jxnl/instructor/pull/955
skip test if version less than 3.10 by @sreeprasannar in https://github.com/jxnl/instructor/pull/944
Adding support for multi-modal file input for Vertex AI by @smwitkowski in https://github.com/jxnl/instructor/pull/947
Fix Issues by @ivanleomk in https://github.com/jxnl/instructor/pull/966
feat: gemini tool calling support by @ssonal in https://github.com/jxnl/instructor/pull/726
fix: ensure that utf-8 characters are not translated into \uXXXX format by @ivanleomk in https://github.com/jxnl/instructor/pull/965
See if refusal attribute exists in ChatCompletionMessage before referencing it by @callmephilip in https://github.com/jxnl/instructor/pull/962
Fixed up a warning for the relevant clients by @ivanleomk in https://github.com/jxnl/instructor/pull/974
Fix: Bump version for Jiter by @paulelliotco in https://github.com/jxnl/instructor/pull/964
Change Gemini to use Tools by default by @ivanleomk in https://github.com/jxnl/instructor/pull/981

New Contributors

@roeybc made their first contribution in https://github.com/jxnl/instructor/pull/948
@sreeprasannar made their first contribution in https://github.com/jxnl/instructor/pull/944
@smwitkowski made their first contribution in https://github.com/jxnl/instructor/pull/947
@callmephilip made their first contribution in https://github.com/jxnl/instructor/pull/962
@paulelliotco made their first contribution in https://github.com/jxnl/instructor/pull/964

Full Changelog: https://github.com/jxnl/instructor/compare/1.4.0...1.4.1

Open source →

1.4.022 Aug 2024

Fix debug log exception in retry_async by @mattheath in https://github.com/jxnl/instructor/pull/884

What's Changed

Fix debug log exception in retry_async by @mattheath in https://github.com/jxnl/instructor/pull/884
Formatted Docs by @ivanleomk in https://github.com/jxnl/instructor/pull/864
Anthropic IncompleteOutputException was never triggered for tools and JSON modes by @palako in https://github.com/jxnl/instructor/pull/848
Fix for Flaky Test Issue #853 by @DonovanAD in https://github.com/jxnl/instructor/pull/891
revise prompt design docs [zero-shot] by @shreya-51 in https://github.com/jxnl/instructor/pull/865
Corrected some typos. by @atbradley in https://github.com/jxnl/instructor/pull/905
Pyright Errors by @ivanleomk in https://github.com/jxnl/instructor/pull/900
Update 4-validation.ipynb by @ashkanrdn in https://github.com/jxnl/instructor/pull/932
Fix typo in handle_response_model (anthropic system message): responsd -> respond by @timlod in https://github.com/jxnl/instructor/pull/904
Remove Async Validation in process async by @ivanleomk in https://github.com/jxnl/instructor/pull/933
Adding support for structured outputs by @ivanleomk in https://github.com/jxnl/instructor/pull/938
Update vertexai.md fix typo by @lawrencecchen in https://github.com/jxnl/instructor/pull/943
Resolve duplicate test function name by @noxan in https://github.com/jxnl/instructor/pull/894

New Contributors

@mattheath made their first contribution in https://github.com/jxnl/instructor/pull/884
@palako made their first contribution in https://github.com/jxnl/instructor/pull/848
@DonovanAD made their first contribution in https://github.com/jxnl/instructor/pull/891
@atbradley made their first contribution in https://github.com/jxnl/instructor/pull/905
@ashkanrdn made their first contribution in https://github.com/jxnl/instructor/pull/932
@timlod made their first contribution in https://github.com/jxnl/instructor/pull/904
@lawrencecchen made their first contribution in https://github.com/jxnl/instructor/pull/943

Full Changelog: https://github.com/jxnl/instructor/compare/1.3.7...1.4.0

Open source →

1.3.724 Jul 2024

Moved Cohere import by @ivanleomk in https://github.com/jxnl/instructor/pull/874

What's Changed

Moved Cohere import by @ivanleomk in https://github.com/jxnl/instructor/pull/874

Full Changelog: https://github.com/jxnl/instructor/compare/1.3.6...1.3.7

Open source →

1.3.623 Jul 2024

Nothing published for this version

1.3.517 Jul 2024

prompting docs by @shreya-51 in https://github.com/jxnl/instructor/pull/786

What's Changed

prompting docs by @shreya-51 in https://github.com/jxnl/instructor/pull/786
Fixed up an example for RAR and RE2 by @ivanleomk in https://github.com/jxnl/instructor/pull/790
Added an index page by @ivanleomk in https://github.com/jxnl/instructor/pull/791
fix: async from_litellm by @adrienbrault in https://github.com/jxnl/instructor/pull/783
Update maybe.md by @r41ng3l in https://github.com/jxnl/instructor/pull/781
Update usage.md 'constructor usage list' command documentation by @r41ng3l in https://github.com/jxnl/instructor/pull/770
Add prompting docs tests by @jxnl in https://github.com/jxnl/instructor/pull/794
docs: typo fix by @rishabgit in https://github.com/jxnl/instructor/pull/795
Add explicit check for jsonref dep in vertexai client import guard by @lemontheme in https://github.com/jxnl/instructor/pull/797
Fixed up Self-Ask Example by @ivanleomk in https://github.com/jxnl/instructor/pull/792
Added some new prompt techniques by @ivanleomk in https://github.com/jxnl/instructor/pull/809
prompt docs by @shreya-51 in https://github.com/jxnl/instructor/pull/793
Validate anthropic_tool function args as json by @woodbridge in https://github.com/jxnl/instructor/pull/779
Fix: Resolve create_model() TypeError in Partial class by @slavakurilyak in https://github.com/jxnl/instructor/pull/801
add client parameter to instructor.Intructions by @bhomass in https://github.com/jxnl/instructor/pull/814
Added new techniques by @ivanleomk in https://github.com/jxnl/instructor/pull/810
prompt docs by @shreya-51 in https://github.com/jxnl/instructor/pull/813
render gpt4o url by @rshah713 in https://github.com/jxnl/instructor/pull/826
skeleton of thought prompting doc by @shreya-51 in https://github.com/jxnl/instructor/pull/824
Bugfix: enable anthropic streaming support with partials by @ssonal in https://github.com/jxnl/instructor/pull/825
docs(examples, navigation): add local classification tutorial and update navigation by @jxnl in https://github.com/jxnl/instructor/pull/830
sg_icl prompting doc by @shreya-51 in https://github.com/jxnl/instructor/pull/829
Synthetic Data Notebook by @ivanleomk in https://github.com/jxnl/instructor/pull/839
feat: add blog post and example script for extracting YouTube video chapters using OpenAI models by @jxnl in https://github.com/jxnl/instructor/pull/831
Added COSP by @ivanleomk in https://github.com/jxnl/instructor/pull/823
Fixed up Max Mutual information example by @ivanleomk in https://github.com/jxnl/instructor/pull/842
Added support for Anthropic system parameter by @ivanleomk in https://github.com/jxnl/instructor/pull/833
knn prompting doc by @shreya-51 in https://github.com/jxnl/instructor/pull/845
Fixed up additional functionality for the batch job article by @ivanleomk in https://github.com/jxnl/instructor/pull/843
Fixed up new pydantic version by @ivanleomk in https://github.com/jxnl/instructor/pull/847
Bump Tenacity Version by @ivanleomk in https://github.com/jxnl/instructor/pull/851

New Contributors

@adrienbrault made their first contribution in https://github.com/jxnl/instructor/pull/783
@r41ng3l made their first contribution in https://github.com/jxnl/instructor/pull/781
@woodbridge made their first contribution in https://github.com/jxnl/instructor/pull/779
@slavakurilyak made their first contribution in https://github.com/jxnl/instructor/pull/801
@bhomass made their first contribution in https://github.com/jxnl/instructor/pull/814
@rshah713 made their first contribution in https://github.com/jxnl/instructor/pull/826

Full Changelog: https://github.com/jxnl/instructor/compare/1.3.4...1.3.5

Open source →

1.3.425 Jun 2024

typo fix and rephrasing suggestion by @lukaskf in https://github.com/jxnl/instructor/pull/756

What's Changed

typo fix and rephrasing suggestion by @lukaskf in https://github.com/jxnl/instructor/pull/756
Fix the link to use the cloudflare docs by @ivanleomk in https://github.com/jxnl/instructor/pull/753
Updated the Documentation by @ivanleomk in https://github.com/jxnl/instructor/pull/751
Fixed Cohere retries by @ionflow in https://github.com/jxnl/instructor/pull/761
Added Vertex AI JSON Mode by @ajac-zero in https://github.com/jxnl/instructor/pull/750
Fix heading indentation in the getting started section of the docs by @RensDimmendaal in https://github.com/jxnl/instructor/pull/744
Anthropic client. Prevent empty generator when streaming by @lemontheme in https://github.com/jxnl/instructor/pull/728
Add Gemini via OpenAI Client Support Documentation by @bllchmbrs in https://github.com/jxnl/instructor/pull/736
rename batch to bulk/async, to avoid confusion with OpenAI's batch APIs by @avyfain in https://github.com/jxnl/instructor/pull/765
Disabling Pydantic Error by @ivanleomk in https://github.com/jxnl/instructor/pull/757
feat: add support for typeddicts by @ivanleomk in https://github.com/jxnl/instructor/pull/758
feat: prompt engineering cookbooks by @shreya-51 in https://github.com/jxnl/instructor/pull/764
feat: new cli for batch jobs by @ivanleomk in https://github.com/jxnl/instructor/pull/754
zero-shot prompting docs by @shreya-51 in https://github.com/jxnl/instructor/pull/780

New Contributors

@lukaskf made their first contribution in https://github.com/jxnl/instructor/pull/756
@RensDimmendaal made their first contribution in https://github.com/jxnl/instructor/pull/744
@avyfain made their first contribution in https://github.com/jxnl/instructor/pull/765

Full Changelog: https://github.com/jxnl/instructor/compare/1.3.3...1.3.4

What's Changed

typo fix and rephrasing suggestion by @lukaskf in https://github.com/jxnl/instructor/pull/756
Fix the link to use the cloudflare docs by @ivanleomk in https://github.com/jxnl/instructor/pull/753
Updated the Documentation by @ivanleomk in https://github.com/jxnl/instructor/pull/751
Fixed Cohere retries by @ionflow in https://github.com/jxnl/instructor/pull/761
Added Vertex AI JSON Mode by @ajac-zero in https://github.com/jxnl/instructor/pull/750
Fix heading indentation in the getting started section of the docs by @RensDimmendaal in https://github.com/jxnl/instructor/pull/744
Anthropic client. Prevent empty generator when streaming by @lemontheme in https://github.com/jxnl/instructor/pull/728
Add Gemini via OpenAI Client Support Documentation by @bllchmbrs in https://github.com/jxnl/instructor/pull/736
rename batch to bulk/async, to avoid confusion with OpenAI's batch APIs by @avyfain in https://github.com/jxnl/instructor/pull/765
Disabling Pydantic Error by @ivanleomk in https://github.com/jxnl/instructor/pull/757
feat: add support for typeddicts by @ivanleomk in https://github.com/jxnl/instructor/pull/758
feat: prompt engineering cookbooks by @shreya-51 in https://github.com/jxnl/instructor/pull/764
feat: new cli for batch jobs by @ivanleomk in https://github.com/jxnl/instructor/pull/754
zero-shot prompting docs by @shreya-51 in https://github.com/jxnl/instructor/pull/780
Updated Pyproject.toml to publish a new version of Instructor by @ivanleomk in https://github.com/jxnl/instructor/pull/785

New Contributors

@lukaskf made their first contribution in https://github.com/jxnl/instructor/pull/756
@RensDimmendaal made their first contribution in https://github.com/jxnl/instructor/pull/744
@avyfain made their first contribution in https://github.com/jxnl/instructor/pull/765

Full Changelog: https://github.com/jxnl/instructor/compare/1.3.3...1.3.4

Open source →

1.3.311 Jun 2024

refactor(simple_type, ModelAdapter): update type checking and refactor model creation by @jxnl in https://github.com/jxnl/instructor/pull/710

What's Changed

refactor(simple_type, ModelAdapter): update type checking and refactor model creation by @jxnl in https://github.com/jxnl/instructor/pull/710
Fix response UnboundError when request fails and custom tenacity.Retrying is used by @lazyhope in https://github.com/jxnl/instructor/pull/713
[fixes #721] Switch away from Anthropic beta interface for tools. by @lemontheme in https://github.com/jxnl/instructor/pull/723
Add Support for VertexAI Gemini by @ajac-zero in https://github.com/jxnl/instructor/pull/711
async gemini support by @Cruppelt in https://github.com/jxnl/instructor/pull/719
fix: parallel unions by @vinchg in https://github.com/jxnl/instructor/pull/734
typo fix document_segmentation.md by @NicolaiLolansen in https://github.com/jxnl/instructor/pull/730
Sync pyproject.toml and poetry.lock files by @jlondonobo in https://github.com/jxnl/instructor/pull/729
Added Jiter Support by @ivanleomk in https://github.com/jxnl/instructor/pull/745
Iterable Workaround by @ivanleomk in https://github.com/jxnl/instructor/pull/737

New Contributors

@lemontheme made their first contribution in https://github.com/jxnl/instructor/pull/723
@ajac-zero made their first contribution in https://github.com/jxnl/instructor/pull/711
@vinchg made their first contribution in https://github.com/jxnl/instructor/pull/734
@NicolaiLolansen made their first contribution in https://github.com/jxnl/instructor/pull/730

Full Changelog: https://github.com/jxnl/instructor/compare/1.3.2...1.3.3

Open source →

1.3.227 May 2024

Adding gpt4o vision example by @karbon0x in https://github.com/jxnl/instructor/pull/702

What's Changed

Adding gpt4o vision example by @karbon0x in https://github.com/jxnl/instructor/pull/702
Fixed incorrect/missing arguments by @Elektra58 in https://github.com/jxnl/instructor/pull/708
Fixed incorrect argument by @Elektra58 in https://github.com/jxnl/instructor/pull/707
Fixed a typo by @yasoob in https://github.com/jxnl/instructor/pull/705
restore async groq functionality by @cmishra in https://github.com/jxnl/instructor/pull/704
Improve gemini model robustness by @ssonal in https://github.com/jxnl/instructor/pull/701

New Contributors

@karbon0x made their first contribution in https://github.com/jxnl/instructor/pull/702
@Elektra58 made their first contribution in https://github.com/jxnl/instructor/pull/708
@yasoob made their first contribution in https://github.com/jxnl/instructor/pull/705
@cmishra made their first contribution in https://github.com/jxnl/instructor/pull/704

Full Changelog: https://github.com/jxnl/instructor/compare/1.3.1...1.3.2

Open source →

1.3.123 May 2024

Fix typos in README.md by @AmgadHasan in https://github.com/jxnl/instructor/pull/699

What's Changed

Fix typos in README.md by @AmgadHasan in https://github.com/jxnl/instructor/pull/699
Fix failure checking for "google.generativeai' import spec by @dbmikus in https://github.com/jxnl/instructor/pull/698

New Contributors

@AmgadHasan made their first contribution in https://github.com/jxnl/instructor/pull/699
@dbmikus made their first contribution in https://github.com/jxnl/instructor/pull/698

Full Changelog: https://github.com/jxnl/instructor/compare/1.3.0...1.3.1

Open source →

1.3.023 May 2024

Update groq.md by @frankbaele in https://github.com/jxnl/instructor/pull/651

What's Changed

Update groq.md by @frankbaele in https://github.com/jxnl/instructor/pull/651
Added gpt-4o to model costs and model names by @st4r0 in https://github.com/jxnl/instructor/pull/671
Update Groq documentation and examples to use preferred patching method by @NasonZ in https://github.com/jxnl/instructor/pull/663
anthropic force tool by @Cruppelt in https://github.com/jxnl/instructor/pull/681
maybe results typo fix by @rbraddev in https://github.com/jxnl/instructor/pull/686
Parea Blogpost by @joschkabraun in https://github.com/jxnl/instructor/pull/673
Fix typo in philosophy.md by @deeplook in https://github.com/jxnl/instructor/pull/677
Update mode.py to warn in Mode.FUNCTIONS access vs. in __new__ by @boydgreenfield in https://github.com/jxnl/instructor/pull/678
Fix handling of snapshot_ids ("gpt-4-turbo-2024-04-09" and "gpt-4o-2024-05-13") and alias "gpt-4-turbo". by @st4r0 in https://github.com/jxnl/instructor/pull/672
Update ollama.md by @MeDott29 in https://github.com/jxnl/instructor/pull/635
Fixed up discord link by @ivanleomk in https://github.com/jxnl/instructor/pull/690
Enrich IncompleteOutputException with completion context by @lukszamarcin in https://github.com/jxnl/instructor/pull/683
Anthropic streaming support by @ssonal in https://github.com/jxnl/instructor/pull/682
results rename by @rbraddev in https://github.com/jxnl/instructor/pull/692
Updates to Parea blog by @joschkabraun in https://github.com/jxnl/instructor/pull/695
Fix typo in blog by @joschkabraun in https://github.com/jxnl/instructor/pull/696
Update Mode.MD_JSON and add Provider.DATABRICKS by @arcaputo3 in https://github.com/jxnl/instructor/pull/691
Add basic support for gemini models by @ssonal in https://github.com/jxnl/instructor/pull/684

New Contributors

@frankbaele made their first contribution in https://github.com/jxnl/instructor/pull/651
@st4r0 made their first contribution in https://github.com/jxnl/instructor/pull/671
@NasonZ made their first contribution in https://github.com/jxnl/instructor/pull/663
@rbraddev made their first contribution in https://github.com/jxnl/instructor/pull/686
@deeplook made their first contribution in https://github.com/jxnl/instructor/pull/677
@lukszamarcin made their first contribution in https://github.com/jxnl/instructor/pull/683
@ssonal made their first contribution in https://github.com/jxnl/instructor/pull/682
@arcaputo3 made their first contribution in https://github.com/jxnl/instructor/pull/691

Full Changelog: https://github.com/jxnl/instructor/compare/1.2.6...1.3.0

Open source →

1.2.69 May 2024

Import typing related imports only when type checking by @noxan in https://github.com/jxnl/instructor/pull/645

What's Changed

Import typing related imports only when type checking by @noxan in https://github.com/jxnl/instructor/pull/645
New Logfire Article ( Fixes #640 ) by @ivanleomk in https://github.com/jxnl/instructor/pull/647
Updated the Logfire and Fastapi article by @ivanleomk in https://github.com/jxnl/instructor/pull/648
[docs] index watsonx example by @h0rv in https://github.com/jxnl/instructor/pull/642
doc: Update self_critique.md by @sgrimee in https://github.com/jxnl/instructor/pull/652
fix: Update llama-cpp-python examples to use patch instead of from_openai by @abetlen in https://github.com/jxnl/instructor/pull/656

New Contributors

@noxan made their first contribution in https://github.com/jxnl/instructor/pull/645
@sgrimee made their first contribution in https://github.com/jxnl/instructor/pull/652
@abetlen made their first contribution in https://github.com/jxnl/instructor/pull/656

Full Changelog: https://github.com/jxnl/instructor/compare/1.2.5...1.2.6

Open source →

1.2.51 May 2024Deprecated

Avoid deprecated class property stacking by @max-muoto in https://github.com/jxnl/instructor/pull/637

What's Changed

feat: add watsonx support by @h0rv in https://github.com/jxnl/instructor/pull/620
Implement Pyright for Type-Checking by @max-muoto in https://github.com/jxnl/instructor/pull/630
Enable PyUpgrade Ruff Rule-Set by @max-muoto in https://github.com/jxnl/instructor/pull/633
Avoid deprecated class property stacking by @max-muoto in https://github.com/jxnl/instructor/pull/637
Instructor with Logfire by @ivanleomk in https://github.com/jxnl/instructor/pull/639
ANTHROPIC_JSON: allow control characters in JSON strings if strict=False by @voberoi in https://github.com/jxnl/instructor/pull/644
Allow newer Pydantic patch versions by @bencrouse in https://github.com/jxnl/instructor/pull/643

New Contributors

@h0rv made their first contribution in https://github.com/jxnl/instructor/pull/620
@max-muoto made their first contribution in https://github.com/jxnl/instructor/pull/630
@voberoi made their first contribution in https://github.com/jxnl/instructor/pull/644
@bencrouse made their first contribution in https://github.com/jxnl/instructor/pull/643

Full Changelog: https://github.com/jxnl/instructor/compare/1.2.4...1.2.5

Open source →

1.2.429 Apr 2024

feat: update and allow strict mode by @jxnl in https://github.com/jxnl/instructor/pull/618

What's Changed

feat: update and allow strict mode by @jxnl in https://github.com/jxnl/instructor/pull/618
fix: allow openai-like clients into from_openai

Full Changelog: https://github.com/jxnl/instructor/compare/1.2.3...1.2.4

Open source →

1.2.327 Apr 2024

Fix bullet list in README.md by @xingweitian in https://github.com/jxnl/instructor/pull/621

What's Changed

Fix bullet list in README.md by @xingweitian in https://github.com/jxnl/instructor/pull/621
Update README.md by @eltociear in https://github.com/jxnl/instructor/pull/625
fix typo about Enum 'and' → 'an' by @inn-0 in https://github.com/jxnl/instructor/pull/626
Fix anthropic usage and tools by @lazyhope in https://github.com/jxnl/instructor/pull/622

New Contributors

@xingweitian made their first contribution in https://github.com/jxnl/instructor/pull/621
@eltociear made their first contribution in https://github.com/jxnl/instructor/pull/625

Full Changelog: https://github.com/jxnl/instructor/compare/1.2.2...1.2.3

Open source →

1.2.220 Apr 2024

From mistral by @wassim-trabelsi in https://github.com/jxnl/instructor/pull/599

What's Changed

From mistral by @wassim-trabelsi in https://github.com/jxnl/instructor/pull/599
feat: custom exceptions by @jxnl in https://github.com/jxnl/instructor/pull/614

New Contributors

@wassim-trabelsi made their first contribution in https://github.com/jxnl/instructor/pull/599

Full Changelog: https://github.com/jxnl/instructor/compare/1.2.1...1.2.2

Open source →

1.2.118 Apr 2024

feat: basic sentiment analysis eval tests by @meta-boy in https://github.com/jxnl/instructor/pull/610

What's Changed

feat: basic sentiment analysis eval tests by @meta-boy in https://github.com/jxnl/instructor/pull/610
[Ellipsis] docstring-parser 0.16 by @ellipsis-dev in https://github.com/jxnl/instructor/pull/608
Added support for MD_JSON for Anyscale and Together by @jpetrantoni in https://github.com/jxnl/instructor/pull/611

New Contributors

@meta-boy made their first contribution in https://github.com/jxnl/instructor/pull/610

Full Changelog: https://github.com/jxnl/instructor/compare/1.2.0...1.2.1

Open source →

Your coding agent can read these notes before it upgrades. Set up the MCP server →

instructor

Release timeline

Releases

Upgrade Notes

Fixed

Security

Changed

Security

Additional Fixes

Added

Changed

Fixed

Security

Tests / CI

What's Changed

Runtime Fixes

CLI

Docs

Release

Validation

Fixed

What's Changed

New Contributors

Fixed

Tests / CI

Security

Added

Fixed

Dependencies

Security

Added

Fixed

What's Changed

Security

Fixed

Added

Docs

Tests / CI

Changes

Fixed

What's Changed

Fixed

Changed

Added

Fixed

Deprecated

Added

Fixed

Fixed

Added

Fixed

Tests / CI

What's Changed

New Contributors

Fixed

What's Changed

New Contributors

Added

Fixed

What's Changed

New Contributors

Fixed

What's Changed

Added

Fixed

What's Changed

What's Changed

New Contributors

Added

Changed

Fixed

What's Changed

New Contributors

What's Changed

What's Changed

New Contributors

What's Changed

New Contributors

What's Changed

New Contributors