You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: packages/ai-providers/server-ai-langchain/CHANGELOG.md
+7-27Lines changed: 7 additions & 27 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,48 +1,28 @@
1
1
# Changelog
2
2
3
+
All notable changes to the LaunchDarkly Python AI LangChain provider package will be documented in this file. This project adheres to [Semantic Versioning](http://semver.org).
* Split track_metrics_of into sync and async variants ([#112](https://github.com/launchdarkly/python-server-sdk-ai/issues/112))
10
-
* Remove node-scoped methods from AIGraphTracker (track_node_invocation, track_tool_call, track_node_judge_response), use related AIConfigTracker methods instead
11
-
* Extract shared utilities to openai_helper
12
-
* Extract shared utilities to langchain_helper
13
11
* Restructure provider factory and support additional create methods ([#102](https://github.com/launchdarkly/python-server-sdk-ai/issues/102))
12
+
* Extract shared utilities to langchain_helper
14
13
15
14
### Features
16
15
17
-
* Add get_ai_usage_from_response to openai_helper ([4fab18f](https://github.com/launchdarkly/python-server-sdk-ai/commit/4fab18fa62375b6c97cb12a89225805c81ca4ee8))
18
-
* Add get_tool_calls_from_response and sum_token_usage_from_messages to langchain_helper ([4fab18f](https://github.com/launchdarkly/python-server-sdk-ai/commit/4fab18fa62375b6c97cb12a89225805c81ca4ee8))
* Add ManagedAgentGraph support ([#111](https://github.com/launchdarkly/python-server-sdk-ai/issues/111)) ([56ce0fd](https://github.com/launchdarkly/python-server-sdk-ai/commit/56ce0fd63b4301b58f33c17c55c4ecd47e9f8559))
22
-
* Add ModelRunner ABC with invoke_model() and ([453c71c](https://github.com/launchdarkly/python-server-sdk-ai/commit/453c71c84adcc6b8a3e316a98907dcb511bc9d41))
* Add optional graph_key to all LDAIConfigTracker track_* methods for graph correlation ([4fab18f](https://github.com/launchdarkly/python-server-sdk-ai/commit/4fab18fa62375b6c97cb12a89225805c81ca4ee8))
27
-
* Add track_tool_call/track_tool_calls to LDAIConfigTracker ([4fab18f](https://github.com/launchdarkly/python-server-sdk-ai/commit/4fab18fa62375b6c97cb12a89225805c81ca4ee8))
* Bump minimum LangChain version to 1.0.0 ([dc592c5](https://github.com/launchdarkly/python-server-sdk-ai/commit/dc592c5a2e2bf3bf679af14a9aa63e81678a69ab))
30
-
* Deprecated Chat object in favor of ManagedModel ([453c71c](https://github.com/launchdarkly/python-server-sdk-ai/commit/453c71c84adcc6b8a3e316a98907dcb511bc9d41))
31
-
* Deprecated create_chat(), use create_model() on the LDAIClient ([453c71c](https://github.com/launchdarkly/python-server-sdk-ai/commit/453c71c84adcc6b8a3e316a98907dcb511bc9d41))
32
-
* Drop support for python 3.9 ([#114](https://github.com/launchdarkly/python-server-sdk-ai/issues/114)) ([dc592c5](https://github.com/launchdarkly/python-server-sdk-ai/commit/dc592c5a2e2bf3bf679af14a9aa63e81678a69ab))
33
17
* Extract shared utilities to langchain_helper ([453c71c](https://github.com/launchdarkly/python-server-sdk-ai/commit/453c71c84adcc6b8a3e316a98907dcb511bc9d41))
34
-
* Extract shared utilities to openai_helper ([453c71c](https://github.com/launchdarkly/python-server-sdk-ai/commit/453c71c84adcc6b8a3e316a98907dcb511bc9d41))
35
-
* Introduce ManagedAgent and AgentRunner implementations ([#110](https://github.com/launchdarkly/python-server-sdk-ai/issues/110)) ([53fd95e](https://github.com/launchdarkly/python-server-sdk-ai/commit/53fd95e2cfb66f4c53c6844cc41170077e6eee8c))
36
-
* Introduce ManagedModel and ModelRunner (PR-3) ([#104](https://github.com/launchdarkly/python-server-sdk-ai/issues/104)) ([453c71c](https://github.com/launchdarkly/python-server-sdk-ai/commit/453c71c84adcc6b8a3e316a98907dcb511bc9d41))
37
-
* Restructure provider factory and support additional create methods ([#102](https://github.com/launchdarkly/python-server-sdk-ai/issues/102)) ([e6e4907](https://github.com/launchdarkly/python-server-sdk-ai/commit/e6e49076b3b89b9bf4996d3ba8e4b4c9fb7b2078))
38
-
* Split track_metrics_of into sync and async variants ([#112](https://github.com/launchdarkly/python-server-sdk-ai/issues/112)) ([4fab18f](https://github.com/launchdarkly/python-server-sdk-ai/commit/4fab18fa62375b6c97cb12a89225805c81ca4ee8))
18
+
* Add get_ai_usage_from_response to langchain_helper ([4fab18f](https://github.com/launchdarkly/python-server-sdk-ai/commit/4fab18fa62375b6c97cb12a89225805c81ca4ee8))
19
+
* Add get_tool_calls_from_response and sum_token_usage_from_messages to langchain_helper ([4fab18f](https://github.com/launchdarkly/python-server-sdk-ai/commit/4fab18fa62375b6c97cb12a89225805c81ca4ee8))
20
+
* Drop support for python 3.9 ([#114](https://github.com/launchdarkly/python-server-sdk-ai/issues/114)) ([dc592c5](https://github.com/launchdarkly/python-server-sdk-ai/commit/dc592c5a2e2bf3bf679af14a9aa63e81678a69ab))
39
21
40
22
41
23
### Bug Fixes
42
24
43
-
* make AIGraphTracker.track_total_tokens accept Optional[TokenUsage], skip when None or total <= 0 ([4fab18f](https://github.com/launchdarkly/python-server-sdk-ai/commit/4fab18fa62375b6c97cb12a89225805c81ca4ee8))
44
-
* Remove node-scoped methods from AIGraphTracker (track_node_invocation, track_tool_call, track_node_judge_response), use related AIConfigTracker methods instead ([4fab18f](https://github.com/launchdarkly/python-server-sdk-ai/commit/4fab18fa62375b6c97cb12a89225805c81ca4ee8))
45
-
* use time.perf_counter_ns() for sub-millisecond precision in duration calculations ([4fab18f](https://github.com/launchdarkly/python-server-sdk-ai/commit/4fab18fa62375b6c97cb12a89225805c81ca4ee8))
25
+
* Use time.perf_counter_ns() for sub-millisecond precision in duration calculations ([4fab18f](https://github.com/launchdarkly/python-server-sdk-ai/commit/4fab18fa62375b6c97cb12a89225805c81ca4ee8))
Copy file name to clipboardExpand all lines: packages/ai-providers/server-ai-openai/CHANGELOG.md
+6-18Lines changed: 6 additions & 18 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,34 +1,22 @@
1
1
# Changelog
2
2
3
+
All notable changes to the LaunchDarkly Python AI OpenAI provider package will be documented in this file. This project adheres to [Semantic Versioning](http://semver.org).
* Add ManagedAgentGraph support ([#111](https://github.com/launchdarkly/python-server-sdk-ai/issues/111)) ([56ce0fd](https://github.com/launchdarkly/python-server-sdk-ai/commit/56ce0fd63b4301b58f33c17c55c4ecd47e9f8559))
18
-
* Add ModelRunner ABC with invoke_model() and ([453c71c](https://github.com/launchdarkly/python-server-sdk-ai/commit/453c71c84adcc6b8a3e316a98907dcb511bc9d41))
* Bump minimum LangChain version to 1.0.0 ([dc592c5](https://github.com/launchdarkly/python-server-sdk-ai/commit/dc592c5a2e2bf3bf679af14a9aa63e81678a69ab))
24
-
* Deprecated Chat object in favor of ManagedModel ([453c71c](https://github.com/launchdarkly/python-server-sdk-ai/commit/453c71c84adcc6b8a3e316a98907dcb511bc9d41))
25
-
* Deprecated create_chat(), use create_model() on the LDAIClient ([453c71c](https://github.com/launchdarkly/python-server-sdk-ai/commit/453c71c84adcc6b8a3e316a98907dcb511bc9d41))
26
-
* Drop support for python 3.9 ([#114](https://github.com/launchdarkly/python-server-sdk-ai/issues/114)) ([dc592c5](https://github.com/launchdarkly/python-server-sdk-ai/commit/dc592c5a2e2bf3bf679af14a9aa63e81678a69ab))
27
-
* Extract shared utilities to langchain_helper ([453c71c](https://github.com/launchdarkly/python-server-sdk-ai/commit/453c71c84adcc6b8a3e316a98907dcb511bc9d41))
* Extract shared utilities to openai_helper ([453c71c](https://github.com/launchdarkly/python-server-sdk-ai/commit/453c71c84adcc6b8a3e316a98907dcb511bc9d41))
29
-
* Introduce ManagedAgent and AgentRunner implementations ([#110](https://github.com/launchdarkly/python-server-sdk-ai/issues/110)) ([53fd95e](https://github.com/launchdarkly/python-server-sdk-ai/commit/53fd95e2cfb66f4c53c6844cc41170077e6eee8c))
30
-
* Introduce ManagedModel and ModelRunner (PR-3) ([#104](https://github.com/launchdarkly/python-server-sdk-ai/issues/104)) ([453c71c](https://github.com/launchdarkly/python-server-sdk-ai/commit/453c71c84adcc6b8a3e316a98907dcb511bc9d41))
31
-
* Restructure provider factory and support additional create methods ([#102](https://github.com/launchdarkly/python-server-sdk-ai/issues/102)) ([e6e4907](https://github.com/launchdarkly/python-server-sdk-ai/commit/e6e49076b3b89b9bf4996d3ba8e4b4c9fb7b2078))
18
+
* Add get_ai_usage_from_response to openai_helper ([4fab18f](https://github.com/launchdarkly/python-server-sdk-ai/commit/4fab18fa62375b6c97cb12a89225805c81ca4ee8))
19
+
* Drop support for python 3.9 ([#114](https://github.com/launchdarkly/python-server-sdk-ai/issues/114)) ([dc592c5](https://github.com/launchdarkly/python-server-sdk-ai/commit/dc592c5a2e2bf3bf679af14a9aa63e81678a69ab))
Copy file name to clipboardExpand all lines: packages/sdk/server-ai/CHANGELOG.md
+6-21Lines changed: 6 additions & 21 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -7,44 +7,29 @@ All notable changes to the LaunchDarkly Python AI package will be documented in
7
7
8
8
### ⚠ BREAKING CHANGES
9
9
10
-
*Bump minimum LangChain version to 1.0.0
10
+
*Restructure provider factory and support additional create methods ([#102](https://github.com/launchdarkly/python-server-sdk-ai/issues/102))
11
11
* Split track_metrics_of into sync and async variants ([#112](https://github.com/launchdarkly/python-server-sdk-ai/issues/112))
12
12
* Remove node-scoped methods from AIGraphTracker (track_node_invocation, track_tool_call, track_node_judge_response), use related AIConfigTracker methods instead
13
-
* Extract shared utilities to openai_helper
14
-
* Extract shared utilities to langchain_helper
15
-
* Restructure provider factory and support additional create methods ([#102](https://github.com/launchdarkly/python-server-sdk-ai/issues/102))
16
13
17
14
### Features
18
15
19
-
* Add get_ai_usage_from_response to openai_helper ([4fab18f](https://github.com/launchdarkly/python-server-sdk-ai/commit/4fab18fa62375b6c97cb12a89225805c81ca4ee8))
20
-
* Add get_tool_calls_from_response and sum_token_usage_from_messages to langchain_helper ([4fab18f](https://github.com/launchdarkly/python-server-sdk-ai/commit/4fab18fa62375b6c97cb12a89225805c81ca4ee8))
* Add ManagedAgentGraph support ([#111](https://github.com/launchdarkly/python-server-sdk-ai/issues/111)) ([56ce0fd](https://github.com/launchdarkly/python-server-sdk-ai/commit/56ce0fd63b4301b58f33c17c55c4ecd47e9f8559))
24
-
* Add ModelRunner ABC with invoke_model() and ([453c71c](https://github.com/launchdarkly/python-server-sdk-ai/commit/453c71c84adcc6b8a3e316a98907dcb511bc9d41))
* Add ModelRunner protocol with invoke_model() and invoke_structured_model() ([453c71c](https://github.com/launchdarkly/python-server-sdk-ai/commit/453c71c84adcc6b8a3e316a98907dcb511bc9d41))
28
21
* Add optional graph_key to all LDAIConfigTracker track_* methods for graph correlation ([4fab18f](https://github.com/launchdarkly/python-server-sdk-ai/commit/4fab18fa62375b6c97cb12a89225805c81ca4ee8))
29
22
* Add track_tool_call/track_tool_calls to LDAIConfigTracker ([4fab18f](https://github.com/launchdarkly/python-server-sdk-ai/commit/4fab18fa62375b6c97cb12a89225805c81ca4ee8))
* Bump minimum LangChain version to 1.0.0 ([dc592c5](https://github.com/launchdarkly/python-server-sdk-ai/commit/dc592c5a2e2bf3bf679af14a9aa63e81678a69ab))
32
23
* Deprecated Chat object in favor of ManagedModel ([453c71c](https://github.com/launchdarkly/python-server-sdk-ai/commit/453c71c84adcc6b8a3e316a98907dcb511bc9d41))
33
24
* Deprecated create_chat(), use create_model() on the LDAIClient ([453c71c](https://github.com/launchdarkly/python-server-sdk-ai/commit/453c71c84adcc6b8a3e316a98907dcb511bc9d41))
34
25
* Drop support for python 3.9 ([#114](https://github.com/launchdarkly/python-server-sdk-ai/issues/114)) ([dc592c5](https://github.com/launchdarkly/python-server-sdk-ai/commit/dc592c5a2e2bf3bf679af14a9aa63e81678a69ab))
35
-
* Extract shared utilities to langchain_helper ([453c71c](https://github.com/launchdarkly/python-server-sdk-ai/commit/453c71c84adcc6b8a3e316a98907dcb511bc9d41))
36
-
* Extract shared utilities to openai_helper ([453c71c](https://github.com/launchdarkly/python-server-sdk-ai/commit/453c71c84adcc6b8a3e316a98907dcb511bc9d41))
37
-
* Introduce ManagedAgent and AgentRunner implementations ([#110](https://github.com/launchdarkly/python-server-sdk-ai/issues/110)) ([53fd95e](https://github.com/launchdarkly/python-server-sdk-ai/commit/53fd95e2cfb66f4c53c6844cc41170077e6eee8c))
38
-
* Introduce ManagedModel and ModelRunner (PR-3) ([#104](https://github.com/launchdarkly/python-server-sdk-ai/issues/104)) ([453c71c](https://github.com/launchdarkly/python-server-sdk-ai/commit/453c71c84adcc6b8a3e316a98907dcb511bc9d41))
39
-
* Restructure provider factory and support additional create methods ([#102](https://github.com/launchdarkly/python-server-sdk-ai/issues/102)) ([e6e4907](https://github.com/launchdarkly/python-server-sdk-ai/commit/e6e49076b3b89b9bf4996d3ba8e4b4c9fb7b2078))
40
-
* Split track_metrics_of into sync and async variants ([#112](https://github.com/launchdarkly/python-server-sdk-ai/issues/112)) ([4fab18f](https://github.com/launchdarkly/python-server-sdk-ai/commit/4fab18fa62375b6c97cb12a89225805c81ca4ee8))
41
26
42
27
43
28
### Bug Fixes
44
29
45
-
*make AIGraphTracker.track_total_tokens accept Optional[TokenUsage], skip when None or total <= 0 ([4fab18f](https://github.com/launchdarkly/python-server-sdk-ai/commit/4fab18fa62375b6c97cb12a89225805c81ca4ee8))
30
+
*Make AIGraphTracker.track_total_tokens accept Optional[TokenUsage], skip when None or total <= 0 ([4fab18f](https://github.com/launchdarkly/python-server-sdk-ai/commit/4fab18fa62375b6c97cb12a89225805c81ca4ee8))
46
31
* Remove node-scoped methods from AIGraphTracker (track_node_invocation, track_tool_call, track_node_judge_response), use related AIConfigTracker methods instead ([4fab18f](https://github.com/launchdarkly/python-server-sdk-ai/commit/4fab18fa62375b6c97cb12a89225805c81ca4ee8))
47
-
*use time.perf_counter_ns() for sub-millisecond precision in duration calculations ([4fab18f](https://github.com/launchdarkly/python-server-sdk-ai/commit/4fab18fa62375b6c97cb12a89225805c81ca4ee8))
32
+
*Use time.perf_counter_ns() for sub-millisecond precision in duration calculations ([4fab18f](https://github.com/launchdarkly/python-server-sdk-ai/commit/4fab18fa62375b6c97cb12a89225805c81ca4ee8))
0 commit comments