Skip to content
Permalink

Comparing changes

Choose two branches to see what’s changed or to start a new pull request. If you need to, you can also or learn more about diff comparisons.

Open a pull request

Create a new pull request by comparing changes across two branches. If you need to, you can also . Learn more about diff comparisons here.
base repository: langchain-ai/langchain
Failed to load repositories. Confirm that selected base ref is valid, then try again.
Loading
base: v0.0.307
Choose a base ref
...
head repository: langchain-ai/langchain
Failed to load repositories. Confirm that selected head ref is valid, then try again.
Loading
compare: v0.0.308
Choose a head ref
  • 12 commits
  • 26 files changed
  • 11 contributors

Commits on Oct 4, 2023

  1. GitHubIssuesLoader Custom API URL Support (#11378) 

    - **Description:** Adds support for custom API URL in the
GitHubIssuesLoader. This allows it to be used with Github enterprise
instances.
    @daniel-butler-irl
    daniel-butler-irl authored Oct 4, 2023
    Configuration menu
    Copy the full SHA
    939bcec View commit details
    Browse the repository at this point in the history

  2. Fixed import typo (#11278) 

    Fixed small import typo in react_docstore documentation

---------

Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
    @MattiaSangermano @eyurtsev
    MattiaSangermano and eyurtsev authored Oct 4, 2023
    Configuration menu
    Copy the full SHA
    cdf5259 View commit details
    Browse the repository at this point in the history

  3. Trigger Docker release workflow after new langchain release is made. (#… 

    …11290)

We want to publish a new Docker image after a new langchain Python
package version is published.
    @obi1kenobi
    obi1kenobi authored Oct 4, 2023
    Configuration menu
    Copy the full SHA
    37f2f71 View commit details
    Browse the repository at this point in the history

  4. Feat bedrock cohere support (#11230) 

    **Description:**
Added support for Cohere command model via Bedrock.
With this change it is now possible to use the `cohere.command-text-v14`
model via Bedrock API.

About Streaming: Cohere model outputs 2 additional chunks at the end of
the text being generated via streaming: a chunk containing the text
`<EOS_TOKEN>`, and a chunk indicating the end of the stream. In this
implementation I chose to ignore both chunks. An alternative solution
could be to replace `<EOS_TOKEN>` with `\n`

Tests: manually tested that the new model work with both
`llm.generate()` and `llm.stream()`.
Tested with `temperature`, `p` and `stop` parameters.

**Issue:** #11181 

**Dependencies:** No new dependencies

**Tag maintainer:** @baskaryan 

**Twitter handle:** mangelino

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
    @massi-ang @hwchase17
    massi-ang and hwchase17 authored Oct 4, 2023
    Configuration menu
    Copy the full SHA
    2f83350 View commit details
    Browse the repository at this point in the history

  5. Add explanations to GoogleDriveLoader how to avoid errors (#11335) 

    - **Description:** add a paragraph to the GoogleDriveLoader doc on how
to bypass errors on authentication.

For some reason, specifying credential path via `credentials_path`
constructor parameter when creating `GoogleDriveLoader` makes it so that
the oAuth screen is never showing up when first using GoogleDriveLoader.
Instead, the `RefreshError: ('invalid_grant: Bad Request', {'error':
'invalid_grant', 'error_description': 'Bad Request'})` error happens.
Setting it via `os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = ...`
solves the problem. Also, `token_path` constructor parameter is
mandatory, otherwise another error happens when trying to `load()` for
the first time.

These errors are tricky and time-consuming to figure out, so I believe
it's good to mention them in the docs.

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
    @anatoliykmetyuk
    anatoliykmetyuk and Erick Friis authored Oct 4, 2023
    Configuration menu
    Copy the full SHA
    34a6410 View commit details
    Browse the repository at this point in the history

  6. Anthropic system message fix (#11301) 

    Removes human prompt prefix before system message for anthropic models

Bedrock anthropic api enforces that Human and Assistant messages must be
interleaved (cannot have same type twice in a row). We currently treat
System Messages as human messages when converting messages -> string
prompt. Our validation when using Bedrock/BedrockChat raises an error
when this happens. For ChatAnthropic we don't validate this so no error
is raised, but perhaps the behavior is still suboptimal
    @baskaryan
    baskaryan authored Oct 4, 2023
    Configuration menu
    Copy the full SHA
    b499de2 View commit details
    Browse the repository at this point in the history

  7. Use an enum for configurable_alternatives to make the generated json … 

    …schema nicer (#11350)
    @nfcampos
    nfcampos authored Oct 4, 2023
    Configuration menu
    Copy the full SHA
    b0893c7 View commit details
    Browse the repository at this point in the history

  8. Revert "Rm additional file check for scheduled tests (#11192)" (#11297) 

    This reverts commit ff90bb5.

Requires #11296 to merge first.
    @obi1kenobi
    obi1kenobi authored Oct 4, 2023
    Configuration menu
    Copy the full SHA
    88c5349 View commit details
    Browse the repository at this point in the history

  9. add default async (#11141)

    @baskaryan
    baskaryan authored Oct 4, 2023
    Configuration menu
    Copy the full SHA
    106608b View commit details
    Browse the repository at this point in the history

  10. Add _type to json functions output parser (#11381) 

    <!-- Thank you for contributing to LangChain!

Replace this entire comment with:
  - **Description:** a description of the change, 
  - **Issue:** the issue # it fixes (if applicable),
  - **Dependencies:** any dependencies required for this change,
- **Tag maintainer:** for a quicker response, tag the relevant
maintainer (see below),
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!

Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc:

https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md

If you're adding a new integration, please include:
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in `docs/extras`
directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->
    @nfcampos
    nfcampos authored Oct 4, 2023
    Configuration menu
    Copy the full SHA
    0d80226 View commit details
    Browse the repository at this point in the history

  11. a better error description when GCP project is not set (#11377) 

    - **Description:** a little bit better error description
  - **Issue:** #10879
    @lkuligin
    lkuligin authored Oct 4, 2023
    Configuration menu
    Copy the full SHA
    4f4e0f3 View commit details
    Browse the repository at this point in the history

  12. bump 308 (#11383)

    @baskaryan
    baskaryan authored Oct 4, 2023
    Configuration menu
    Copy the full SHA
    dd514c2 View commit details
    Browse the repository at this point in the history
Loading