Commit Graph

6868 Commits

Author SHA1 Message Date
shroominic
e6f0cee896
community: Async Ollama + ChatOllama (#15169)
**Description:**
Adding async methods to booth OllamaLLM and ChatOllama to enable async
streaming and async .on_llm_new_token callbacks.

**Issue:**
ChatOllama is not working in combination with an AsyncCallbackManager
because the .on_llm_new_token method is not awaited.
2023-12-26 12:08:04 -08:00
KallieLev
3154c9bc9f
docs: Update dependencies installation cell in steam toolkit (#15148)
**Description:** `decouple` is not the correct package, it's
`python-decouple`, and the notebook cell doesn't compile.

<!-- Thank you for contributing to LangChain!

Please title your PR "<package>: <description>", where <package> is
whichever of langchain, community, core, experimental, etc. is being
modified.

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,
- **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` from the root
of the package you've modified to check this locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc: https://python.langchain.com/docs/contributing/

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/docs/integrations` directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->
2023-12-26 12:07:03 -08:00
Harrison Chase
33e024ad10
[core] print ascii (#15179) 2023-12-26 11:43:14 -08:00
Phill Zarfos
35896faab7
community: correct spelling mistakes of "Suffle" and "reporoducibility" (#15172)
- **Description:** Correct spelling mistakes of "Suffle" and
"reporoducibility" in `DirectoryLoader` class
  - **Issue:** N/A
  - **Dependencies:** N/A
  - **Twitter handle:** N/A
2023-12-26 11:22:59 -08:00
chyroc
3a3f880e5a
Patch: improve ollama 404 api error message, fix #15147 (#15156)
Make this issue more clearly exposed to developers
2023-12-26 11:07:39 -08:00
Bastiaan Quast
e52a734818
Oxford comma, consistent with format elsewhere (#15167)
This document uses Oxford comma (A, B, and C), in this list the comma
was missing before "and".

This PR corrects that.

<!-- Thank you for contributing to LangChain!

Please title your PR "<package>: <description>", where <package> is
whichever of langchain, community, core, experimental, etc. is being
modified.

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,
- **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` from the root
of the package you've modified to check this locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc: https://python.langchain.com/docs/contributing/

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/docs/integrations` directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->
2023-12-26 11:07:09 -08:00
Shorthills AI
f59d0d3b20
Corrected an grammatical mistake (#15163)
Co-authored-by: Vishal <141389263+VishalYadavShorthillsAI@users.noreply.github.com>
Co-authored-by: Sanskar Tanwar <142409040+SanskarTanwarShorthillsAI@users.noreply.github.com>
Co-authored-by: UpneetShorthillsAI <144228282+UpneetShorthillsAI@users.noreply.github.com>
Co-authored-by: HarshGuptaShorthillsAI <144897987+HarshGuptaShorthillsAI@users.noreply.github.com>
Co-authored-by: AdityaKalraShorthillsAI <143726711+AdityaKalraShorthillsAI@users.noreply.github.com>
Co-authored-by: SakshiShorthillsAI <144228183+SakshiShorthillsAI@users.noreply.github.com>
Co-authored-by: AashiGuptaShorthillsAI <144897730+AashiGuptaShorthillsAI@users.noreply.github.com>
Co-authored-by: ShamshadAhmedShorthillsAI <144897733+ShamshadAhmedShorthillsAI@users.noreply.github.com>
2023-12-26 11:06:53 -08:00
Harrison Chase
83232d7e94
add multitenancy (#15176) 2023-12-26 09:08:32 -08:00
Nuno Campos
a2d3042823
Improve graph repr for runnable passthrough and itemgetter (#15083)
<!-- Thank you for contributing to LangChain!

Please title your PR "<package>: <description>", where <package> is
whichever of langchain, community, core, experimental, etc. is being
modified.

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,
- **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` from the root
of the package you've modified to check this locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc: https://python.langchain.com/docs/contributing/

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/docs/integrations` directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->
2023-12-22 16:05:48 -08:00
Nuno Campos
0d0901ea18
Nc/dec22/runnable graph lambda (#15078)
<!-- Thank you for contributing to LangChain!

Please title your PR "<package>: <description>", where <package> is
whichever of langchain, community, core, experimental, etc. is being
modified.

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,
- **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` from the root
of the package you've modified to check this locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc: https://python.langchain.com/docs/contributing/

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/docs/integrations` directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->
2023-12-22 14:36:46 -08:00
Ivan
59d4b80a92
[community]: Elasticsearch chat history encoding (#15055)
- Added ensure_ascii property to ElasticsearchChatMessageHistory

<!-- Thank you for contributing to LangChain!

Please title your PR "<package>: <description>", where <package> is
whichever of langchain, community, core, experimental, etc. is being
modified.

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,
- **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` from the root
of the package you've modified to check this locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc: https://python.langchain.com/docs/contributing/

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/docs/integrations` directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->

---------

Co-authored-by: Ivan Chetverikov <ivan.chetverikov@raftds.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-12-22 13:21:34 -08:00
Corey Brown
9e492620d4
Don't reassign chunk_type (#14923)
**Description**: The parameter chunk_type was being hard coded to
"extractive_answers", so that when "snippet" was being passed, it was
being ignored. This change simply doesn't do that.
2023-12-22 13:20:53 -08:00
Takuya Igei
6da2246215
Add support Vertex AI Gemini uses a public image URL (#14949)
## What

Since `langchain_google_genai.ChatGoogleGenerativeAI` supported A public
image URL, we add to support it in `langchain.chat_models.ChatVertexAI`
as well.

### Example

```py
from langchain.chat_models.vertexai import ChatVertexAI
from langchain_core.messages import HumanMessage

llm = ChatVertexAI(model_name="gemini-pro-vision")
image_message = {
    "type": "image_url",
    "image_url": {
        "url": "https://python.langchain.com/assets/images/cell-18-output-1-0c7fb8b94ff032d51bfe1880d8370104.png",
    },
}
text_message = {
    "type": "text",
    "text": "What is shown in this image?",
}
message = HumanMessage(content=[text_message, image_message])

output = llm([message])
print(output.content)
```

## Refs

-
https://python.langchain.com/docs/integrations/llms/google_vertex_ai_palm
-
https://python.langchain.com/docs/integrations/chat/google_generative_ai
2023-12-22 13:19:09 -08:00
Archan Ghosh
affa3e755a
Update arxiv.py with get_summaries_as_docs inside of Arxivloader (#14953)
Added the call function get_summaries_as_docs inside of Arxivloader

- **Description:** Added a function that returns the documents from
get_summaries_as_docs, as the call signature is present in the parent
file but never used from Arxivloader, this can be used from Arxivloader
itself just like .load() as both the signatures are same.
- **Issue:** Reduces time to load papers as no pdf is processed only
metadata is pulled from Arxiv allowing users for faster load times on
bulk loads. Users can then choose one or more paper and use ID directly
with .load() to load pdf thereby loading all the contents of the paper.
2023-12-22 13:14:22 -08:00
Sypherd
d4f45b1421
core(minor): Allow explicit types for ChatMessageHistory adds (#14967)
<!-- 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://python.langchain.com/docs/contributing/

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.
 -->
## Description
Changes the behavior of `add_user_message` and `add_ai_message` to allow
for messages of those types to be passed in. Currently, if you want to
use the `add_user_message` or `add_ai_message` methods, you have to pass
in a string. For `add_message` on `ChatMessageHistory`, however, you
have to pass a `BaseMessage`. This behavior seems a bit inconsistent.
Personally, I'd love to be able to be explicit that I want to
`add_user_message` and pass in a `HumanMessage` without having to grab
the `content` attribute. This PR allows `add_user_message` to accept
`HumanMessage`s or `str`s and `add_ai_message` to accept `AIMessage`s or
`str`s to add that functionality and ensure backwards compatibility.

## Issue
* None

## Dependencies
* None

## Tag maintainer
@hinthornw
@baskaryan 

## Note
`make test` results in `make: *** No rule to make target 'test'.  Stop.`
2023-12-22 13:12:01 -08:00
ccurme
f2782f4c86
community: add args_schema to GmailSendMessage (#14973)
- **Description:** `tools.gmail.send_message` implements a
`SendMessageSchema` that is not used anywhere. `GmailSendMessage` also
does not have an `args_schema` attribute (this led to issues when
invoking the tool with an OpenAI functions agent, at least for me). Here
we add the missing attribute and a minimal test for the tool.
  - **Issue:** N/A
  - **Dependencies:** N/A
  - **Twitter handle:** N/A

---------

Co-authored-by: Chester Curme <chestercurme@microsoft.com>
2023-12-22 13:07:44 -08:00
Satin Wuker
e7ad834a21
docs/docs/get_started: fixing typos in quickstart.mdx (#15025)
Fixing typos: it's -> its
Fixing grammatical mistakes:
* having to worry -> worrying
* convert -> converts
* few main types -> a few main types

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-12-22 12:55:44 -08:00
Sid Sarasvati
0e3da6d8d2
Update youtube_transcript.ipynb (#15015)
add_video_info should be false in the first example

<!-- Thank you for contributing to LangChain!

Please title your PR "<package>: <description>", where <package> is
whichever of langchain, community, core, experimental, etc. is being
modified.

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,
- **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` from the root
of the package you've modified to check this locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc: https://python.langchain.com/docs/contributing/

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/docs/integrations` directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->
2023-12-22 12:47:05 -08:00
Philip Kiely - Baseten
6342da333a
community: refactor Baseten integration with new API endpoints & docs (#15017)
- **Description:** In response to user feedback, this PR refactors the
Baseten integration with updated model endpoints, as well as updates
relevant documentation. This PR has been tested by end users in
production and works as expected.
  - **Issue:** N/A
- **Dependencies:** This PR actually removes the dependency on the
`baseten` package!
  - **Twitter handle:** https://twitter.com/basetenco
2023-12-22 12:46:24 -08:00
Blane Honeycutt
3fc1b3553b
Community: Adds ability to pass a Config to the boto3 client used by Bedrock (#15029)
# Description  
This PR adds the ability to pass a `botocore.config.Config` instance to
the boto3 client instantiated by the Bedrock LLM.

Currently, the Bedrock LLM doesn't support a way to pass a Config, which
means that some settings (e.g., timeouts and retry configuration)
require instantiating a new boto3 client with a Config and then
replacing the LLM's client:

```python
llm = Bedrock(
        region_name='us-west-2',
        model_id="anthropic.claude-v2",
        model_kwargs={'max_tokens_to_sample': 4096, 'temperature': 0},
)

llm.client = boto_client('bedrock-runtime', region_name='us-west-2', config=Config({'read_timeout': 300}))
```

# Issue
N/A

# Dependencies
N/A
2023-12-22 12:42:56 -08:00
Grzegorz Sajko
dc71fcfabf
corrected outdated link (#15053)
<!-- Thank you for contributing to LangChain!

Please title your PR "<package>: <description>", where <package> is
whichever of langchain, community, core, experimental, etc. is being
modified.

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,
- **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` from the root
of the package you've modified to check this locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc: https://python.langchain.com/docs/contributing/

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/docs/integrations` directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->
2023-12-22 12:39:38 -08:00
chyroc
0e149bbb4c
Improve: remove extra spaces in get_from_env error (#15064) 2023-12-22 11:50:03 -08:00
Ran
c3f8733aef
fix: correct spelling mistakes of "seperate, intialise, pre-defined" (#14647)
fix spellings

**seperate -> separate**: found more occurrences, see
https://github.com/langchain-ai/langchain/pull/14602
**initialise -> intialize**: the latter is more common in the repo
**pre-defined > predefined**: adding a comma after a prefix is a
delicate matter, but this is a generally accepted word

also, another word that appears in the repo is "fs" (stands for
filesystem), e.g., in `libs/core/langchain_core/prompts/loading.py`
` """Unified method for loading a prompt from LangChainHub or local
fs."""`
Isn't "filesystem" better?
2023-12-22 11:49:35 -08:00
chyroc
86d27fd684
Fix: fix partners name typo in tests (#15066)
<!-- Thank you for contributing to LangChain!

Please title your PR "<package>: <description>", where <package> is
whichever of langchain, community, core, experimental, etc. is being
modified.

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,
- **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` from the root
of the package you've modified to check this locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc: https://python.langchain.com/docs/contributing/

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/docs/integrations` directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Ran <rccalman@gmail.com>
2023-12-22 11:48:39 -08:00
Harrison Chase
2e159931ac
add defaults for tavily (#15075) 2023-12-22 11:48:26 -08:00
chyroc
4440ec5ab3
Refactor: use SecretStr for minimax embeddings (#15067) 2023-12-22 11:43:23 -08:00
chyroc
aa19ca9723
Refactor: use SecretStr for jina embeddings (#15068)
<!-- Thank you for contributing to LangChain!

Please title your PR "<package>: <description>", where <package> is
whichever of langchain, community, core, experimental, etc. is being
modified.

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,
- **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` from the root
of the package you've modified to check this locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc: https://python.langchain.com/docs/contributing/

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/docs/integrations` directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->
2023-12-22 11:42:29 -08:00
Leonid Ganeline
f9230e005b
book reference (#15072)
Added a  reference to to a new book about `LangChain`.
2023-12-22 11:41:23 -08:00
Nuno Campos
7d5800ee51
Add Runnable.get_graph() to get a graph representation of a Runnable (#15040)
It can be drawn in ascii with Runnable.get_graph().draw()
2023-12-22 11:40:45 -08:00
Eugene Yurtsev
aad3d8bd47
langchain(patch): Restrict paths in LocalFileStore cache (#15065)
This PR restricts the paths that can be resolve using the local file system cache so that all paths must be contained within the root path.
2023-12-22 11:20:17 -05:00
Michael Goin
501cc8311d
community[patch]: Fix generation_config not setting properly for DeepSparse (#15036)
- **Description:** Tiny but important bugfix to use a more stable
interface for specifying generation_config parameters for DeepSparse LLM
2023-12-22 01:39:22 -05:00
QIAN Zifei
2460f977c5
community[minor]: Azure DocumentIntelligenceLoader/Parser support update with latest SDK (#14389)
- **Description:**
Add DocumentIntelligenceLoader & DocumentIntelligenceParser
implementation using the latest Azure Document Intelligence SDK with
markdown support.
The core logic resides in DocumentIntelligenceParser and
DocumentIntelligenceLoader is a mere wrapper of the parser.
The parser will takes api_endpoint and api_key and creates
DocumentIntelligenceClient for the user. 4 parsing modes are supported:
1. Markdown (default)
2. Single
3. Page 
4. Object

UT and notebook are also updated accordingly.

- **Dependencies:** Azure Document Intelligence SDK:
azure-ai-documentintelligence
[azure-sdk-for-python/sdk/documentintelligence/azure-ai-documentintelligence
at 7c42462ac662522a6fd21b17d2a20f4cd40d0356 · Azure/azure-sdk-for-python
(github.com)](https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2FAzure%2Fazure-sdk-for-python%2Ftree%2F7c42462ac662522a6fd21b17d2a20f4cd40d0356%2Fsdk%2Fdocumentintelligence%2Fazure-ai-documentintelligence&data=05%7C01%7CZifei.Qian%40microsoft.com%7C298225aa3e31468a863108dbf07374ff%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C638368150928704292%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=oE0Sl4HERnMKdbkV9KgBV46Z2xytcQAShdTWf7ZNl%2Bs%3D&reserved=0).

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2023-12-21 16:40:27 -08:00
Ran
129a929d69
infra: Fix test filesystem paths incompatible with windows (#14388)
- **Description:** This PR fixes test failures on Windows caused by path
handling differences and unescaped special characters in regex. The
failing tests are:
```
FAILED tests/unit_tests/storage/test_filesystem.py::test_yield_keys - AssertionError: assert ['key1', 'subdir\\key2'] == ['key1', 'subdir/key2']
FAILED tests/unit_tests/test_imports.py::test_importable_all - ModuleNotFoundError: No module named 'langchain_community.langchain_community\\adapters'
FAILED tests/unit_tests/tools/file_management/test_utils.py::test_get_validated_relative_path_errs_on_absolute - re.error: incomplete escape \U at position 53
FAILED tests/unit_tests/tools/file_management/test_utils.py::test_get_validated_relative_path_errs_on_parent_dir - re.error: incomplete escape \U at position 69
FAILED tests/unit_tests/tools/file_management/test_utils.py::test_get_validated_relative_path_errs_for_symlink_outside_root - re.error: incomplete escape \U at position 64
```

- **Issue:** fixes
https://github.com/langchain-ai/langchain/issues/11775 (partially)
- **Dependencies:** none
2023-12-21 13:45:42 -08:00
Nuno Campos
71076cceaf
Move json and xml parsers to core (#15026)
<!-- Thank you for contributing to LangChain!

Please title your PR "<package>: <description>", where <package> is
whichever of langchain, community, core, experimental, etc. is being
modified.

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,
- **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` from the root
of the package you've modified to check this locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc: https://python.langchain.com/docs/contributing/

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/docs/integrations` directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->
2023-12-21 12:36:56 -08:00
Nuno Campos
d5533b7081
Add option to make messages placeholder optional (#15031)
<!-- Thank you for contributing to LangChain!

Please title your PR "<package>: <description>", where <package> is
whichever of langchain, community, core, experimental, etc. is being
modified.

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,
- **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` from the root
of the package you've modified to check this locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc: https://python.langchain.com/docs/contributing/

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/docs/integrations` directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->
2023-12-21 12:36:37 -08:00
Bagatur
40f42b8947
community[patch]: Release 0.0.6 (#15023) 2023-12-21 14:37:44 -05:00
Bagatur
7eb1100925
core[patch]: Release 0.1.3 (#15022) 2023-12-21 14:35:15 -05:00
Nuno Campos
63e512b680
Implement streaming for all list output parsers (#14981)
<!-- Thank you for contributing to LangChain!

Please title your PR "<package>: <description>", where <package> is
whichever of langchain, community, core, experimental, etc. is being
modified.

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,
- **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` from the root
of the package you've modified to check this locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc: https://python.langchain.com/docs/contributing/

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/docs/integrations` directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->
2023-12-21 11:30:35 -08:00
Nuno Campos
b471166df7
Implement streaming for xml output parser (#14984)
<!-- Thank you for contributing to LangChain!

Please title your PR "<package>: <description>", where <package> is
whichever of langchain, community, core, experimental, etc. is being
modified.

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,
- **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` from the root
of the package you've modified to check this locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc: https://python.langchain.com/docs/contributing/

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/docs/integrations` directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->
2023-12-21 11:30:18 -08:00
Erick Friis
94bc3967a1
infra: api docs build order (#15018) 2023-12-21 11:05:02 -08:00
Jacob Lee
1b01ee0e3c
community[minor]: add hf chat wrapper (#14736)
Builds on #14040 with community refactor merged and notebook updated.

Note that with this refactor, models will be imported from
`langchain_community.chat_models.huggingface` rather than the main
`langchain` repo.

---------

Signed-off-by: harupy <17039389+harupy@users.noreply.github.com>
Signed-off-by: ugm2 <unaigaraymaestre@gmail.com>
Signed-off-by: Yuchen Liang <yuchenl3@andrew.cmu.edu>
Co-authored-by: Andrew Reed <andrew.reed.r@gmail.com>
Co-authored-by: Andrew Reed <areed1242@gmail.com>
Co-authored-by: A-Roucher <aymeric.roucher@gmail.com>
Co-authored-by: Aymeric Roucher <69208727+A-Roucher@users.noreply.github.com>
2023-12-21 12:28:30 -05:00
Leonid Kuligin
b99274c9d8
community[patch]: changed default for VertexAIEmbeddings (#14614)
Replace this entire comment with:
- **Description:** @kurtisvg has raised a point that it's a good idea to
have a fixed version for embeddings (since otherwise a user might run a
query with one version vs a vectorstore where another version was used).
In order to avoid breaking changes, I'd suggest to give users a warning,
and make a `model_name` a required argument in 1.5 months.
2023-12-21 12:15:19 -05:00
Yannick Müller
138bc49759
docs: fixed wrong link in documentation (#14999)
See #14998
2023-12-21 12:06:43 -05:00
Karim Lalani
228ddabc3b
community: fix for surrealdb client 0.3.2 update + store and retrieve metadata (#14997)
Surrealdb client changes from 0.3.1 to 0.3.2 broke the surrealdb vectore
integration.
This PR updates the code to work with the updated client. The change is
backwards compatible with previous versions of surrealdb client.
Also expanded the vector store implementation to store and retrieve
metadata that's included with the document object.
2023-12-21 12:04:57 -05:00
Ikko Eltociear Ashimine
c7be59c122
docs: Update templates README.md (#15013)
Mulitple -> Multiple
2023-12-21 12:04:05 -05:00
Lance Martin
535db72607
Update Ollama multi-modal multi-vector template README.md (#14995) 2023-12-20 20:07:38 -08:00
Lance Martin
94586ec242
Update Ollama multi-modal template README.md (#14994) 2023-12-20 20:07:27 -08:00
Lance Martin
1db7450bc2
Update Gemini template README.md (#14993) 2023-12-20 20:07:20 -08:00
Lance Martin
8996d1a65d
Update multi-modal multi-vector template README.md (#14992) 2023-12-20 20:07:12 -08:00
Lance Martin
448b4d3522
Update multi-modal template README.md (#14991)
<!-- Thank you for contributing to LangChain!

Please title your PR "<package>: <description>", where <package> is
whichever of langchain, community, core, experimental, etc. is being
modified.

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,
- **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` from the root
of the package you've modified to check this locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc: https://python.langchain.com/docs/contributing/

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/docs/integrations` directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->
2023-12-20 20:06:52 -08:00