Skip to content

Commit 6884583

Browse files
committed
Merge branch 'main' into me-claude-thinking-support
* main: updated readme for version install updated mix.exs version for release updated changelog for v0.3.3 added content part description to OpenAI module doc for file uploads fixed doc typo adds telemetry (#284) check that the requested tool_name exists - return an error if it does not exist in the chain added LLMChain.run_until_tool_used/3 (#292) Support for file with file_id in ChatOpenAI (#283) Fix options being passed to the ollama chat api (#179) Support for json_response in ChatModels.ChatGoogleAI (#277) support streaming responses from mistral (#287) feat: File urls for Google (#286)
2 parents 3d4d111 + 0e39f54 commit 6884583

26 files changed

+1963
-296
lines changed

.cursor/rules/changelog-rules.mdc

Lines changed: 33 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,33 @@
1+
---
2+
description: CHANGELOG release authoring rules
3+
globs:
4+
alwaysApply: false
5+
---
6+
Write a changelog entry in the [CHANGELOG.md](mdc:CHANGELOG.md) file for the requested new version. Search the git history for the previous verion's tagged release but omit any immediately following commits that updated the CHANGELOG, as those are essentially part of the previous release.
7+
8+
Break out all the changes in the groups of Added, Changed or breaking changes. Particularly pay attention to larger and more official changes that happen through a PR being merged. Any important changes that were NOT part of a PR but were included should also be called out.
9+
10+
A PR_LINK uses the PR number and the base project URL:
11+
12+
Example: https://github.com/brainlid/langchain/pull/261
13+
14+
# Changelog creation
15+
16+
A changelog entry for a specific version follows this format:
17+
18+
---
19+
20+
Callout any breaking changes.
21+
22+
### Upgrading from vPreviousVersion - vNewVersion
23+
24+
If there are breaking changes and migration or upgrade instructions are needed, those are included here. These typically come from PR descriptions.
25+
26+
### Added
27+
- Bullet list of new features or additions PR_LINK
28+
29+
### Changed
30+
- Bullet list of notable changes PR_LINK
31+
32+
### Fixed
33+
- Bullet list of bugs that were fixed PR_LINK

.envrc_template

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -6,4 +6,5 @@ export AWS_ACCESS_KEY_ID="YOUR_AWS_ACCESS_KEY_ID"
66
export AWS_SECRET_ACCESS_KEY="YOUR_AWS_SECRET_ACCESS_KEY"
77
export AZURE_OPENAI_ENDPOINT="YOUR_AZURE_MODEL_ENDPOINT"
88
export AZURE_OPENAI_KEY="YOUR_AZURE_ENDPOINT_KEY"
9-
export PERPLEXITY_API_KEY="YOUR_PERPLEXITY_API_KEY"
9+
export PERPLEXITY_API_KEY="YOUR_PERPLEXITY_API_KEY"
10+
export MISTRAL_API_KEY="YOUR_MISTRAL_API_KEY"

.github/workflows/elixir.yml

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -21,6 +21,7 @@ env:
2121
AWS_SECRET_ACCESS_KEY: invalid
2222
AWS_REGION: invalid
2323
PERPLEXITY_API_KEY: invalid
24+
MISTRAL_API_KEY: invalid
2425

2526
permissions:
2627
contents: read

CHANGELOG.md

Lines changed: 26 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -4,6 +4,32 @@
44

55

66

7+
## v0.3.3 (2025-03-17)
8+
9+
This is a milestone release before staring v0.4.0 which introduces breaking changes, but importantly adds support for "thinking" models.
10+
11+
### Added
12+
- Added telemetry support https://github.com/brainlid/langchain/pull/284
13+
- Added `LLMChain.run_until_tool_used/3` function https://github.com/brainlid/langchain/pull/292
14+
- Support for file uploads with file_id in ChatOpenAI https://github.com/brainlid/langchain/pull/283
15+
- Support for json_response in ChatGoogleAI https://github.com/brainlid/langchain/pull/277
16+
- Support for streaming responses from Mistral https://github.com/brainlid/langchain/pull/287
17+
- Support for file URLs in Google AI https://github.com/brainlid/langchain/pull/286
18+
- Support for PDF content with OpenAI model https://github.com/brainlid/langchain/pull/275
19+
- Support for caching tool results in Anthropic calls https://github.com/brainlid/langchain/pull/269
20+
- Support for choosing Anthropic beta headers https://github.com/brainlid/langchain/pull/273
21+
22+
### Changed
23+
- Fixed options being passed to the Ollama chat API https://github.com/brainlid/langchain/pull/179
24+
- Fixed media URIs for Google Vertex https://github.com/brainlid/langchain/pull/242
25+
- Fixed OpenAI verbose_api https://github.com/brainlid/langchain/pull/274
26+
- Improved documentation for callbacks and content parts
27+
- Upgraded gettext and migrated https://github.com/brainlid/langchain/pull/271
28+
29+
### Fixed
30+
- Added validation to check if requested tool_name exists in chain
31+
- Fixed various documentation issues and typos
32+
- Fixed callback links in documentation
733

834
## v0.3.2 (2025-03-17)
935

README.md

Lines changed: 12 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -68,7 +68,7 @@ in `mix.exs`:
6868
```elixir
6969
def deps do
7070
[
71-
{:langchain, "0.3.0"}
71+
{:langchain, "0.3.3"}
7272
]
7373
end
7474
```
@@ -240,13 +240,24 @@ See the [`LangChain.ChatModels.ChatBumblebee` documentation](https://hexdocs.pm/
240240

241241
## Testing
242242

243+
Before you can run the tests, make sure you have the environment variables set.
244+
245+
You can do this by running:
246+
247+
```
248+
source .envrc_template
249+
```
250+
251+
Or you can copy it to `.envrc` and populate it with your private API values.
252+
243253
To run all the tests including the ones that perform live calls against the OpenAI API, use the following command:
244254

245255
```
246256
mix test --include live_call
247257
mix test --include live_open_ai
248258
mix test --include live_ollama_ai
249259
mix test --include live_anthropic
260+
mix test --include live_mistral_ai
250261
mix test test/tools/calculator_test.exs --include live_call
251262
```
252263

0 commit comments

Comments
 (0)