Commit Graph

3495 Commits

Author SHA1 Message Date
Alex Sherstinsky
db652de496 community: Support both Predibase SDK-v1 and SDK-v2 in Predibase-LangChain integration (#20859) 2024-04-25 17:39:42 -07:00
Erick Friis
c697b094c4 docs, multiple: de-beta with_structured_output (#20850) 2024-04-25 17:39:42 -07:00
aditya thomas
ced09e8628 docs: update openai llm documentation (#20827)
**Description:** Bring OpenAI LLM page to the LCEL era
**Issue:** See discussion #20810
**Dependencies:** None
2024-04-25 17:39:42 -07:00
Pavlo Paliychuk
397e495294 docs: Update Zep Messaging, add links to Zep Cloud Docs (#20848)
Thank you for contributing to LangChain!

- [x] **PR title**: docs: Update Zep Messaging, add links to Zep Cloud
Docs

- [x] **PR message**: 
- **Description:** This PR updates Zep messaging in the docs + links to
Langchain Zep Cloud examples in our documentation
    - **Twitter handle:** @paulpaliychuk51


- [x] **Add tests and docs**: 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.


- [x] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/

Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.

If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.
2024-04-25 17:39:42 -07:00
Bagatur
0a57ae0dae docs: contributing note (#20843) 2024-04-25 17:39:42 -07:00
ccurme
d64189009e langchain: deprecate LLMChain, RetrievalQA, and ConversationalRetrievalChain (#20751) 2024-04-25 17:39:42 -07:00
Stefano Ottolenghi
aeafdb8647 docs: Fix typo to render list (#20774)
This _should_ fix the currently broken list in the [Neo4jVector
page](https://python.langchain.com/docs/integrations/vectorstores/neo4jvector/).

![Screenshot from 2024-04-23
08-40-37](https://github.com/langchain-ai/langchain/assets/114478074/ab5ad622-879e-4764-93db-5f502eae479b)
2024-04-25 17:39:41 -07:00
Oleksandr Yaremchuk
d7d881c7b1 experimental[minor]: upgrade the prompt injection model (#20783)
- **Description:** In January, Laiyer.ai became part of ProtectAI, which
means the model became owned by ProtectAI. In addition to that,
yesterday, we released a new version of the model addressing issues the
Langchain's community and others mentioned to us about false-positives.
The new model has a better accuracy compared to the previous version,
and we thought the Langchain community would benefit from using the
[latest version of the
model](https://huggingface.co/protectai/deberta-v3-base-prompt-injection-v2).
- **Issue:** N/A
- **Dependencies:** N/A
- **Twitter handle:** @alex_yaremchuk
2024-04-25 17:39:41 -07:00
Chen94yue
94d9c2f431 Update custom_retriever.ipynb (#20776)
Fixed an error in the sample code to ensure that the code can run
directly.

Thank you for contributing to LangChain!

- [ ] **PR title**: "package: description"
- Where "package" is whichever of langchain, community, core,
experimental, etc. is being modified. Use "docs: ..." for purely docs
changes, "templates: ..." for template changes, "infra: ..." for CI
changes.
  - Example: "community: add foobar LLM"


- [ ] **PR message**: ***Delete this entire checklist*** and replace
with
    - **Description:** a description of the change
    - **Issue:** the issue # it fixes, if applicable
    - **Dependencies:** any dependencies required for this change
- **Twitter handle:** if your PR gets announced, and you'd like a
mention, we'll gladly shout you out!


- [ ] **Add tests and docs**: 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.


- [ ] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/

Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.

If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.
2024-04-25 17:39:41 -07:00
Bagatur
f9b4ece439 docs: update examples in api ref (#20768) 2024-04-25 17:39:41 -07:00
Bagatur
df5b598928 docs: fix api ref link autogeneration (#20766) 2024-04-25 17:39:41 -07:00
monke111
a78848e887 Update google_drive.ipynb (#20731)
langchain_community.document_loaders depricated 
new langchain_google_community

Thank you for contributing to LangChain!

- [ ] **PR title**: "package: description"
- Where "package" is whichever of langchain, community, core,
experimental, etc. is being modified. Use "docs: ..." for purely docs
changes, "templates: ..." for template changes, "infra: ..." for CI
changes.
  - Example: "community: add foobar LLM"


- [ ] **PR message**: ***Delete this entire checklist*** and replace
with
    - **Description:** a description of the change
    - **Issue:** the issue # it fixes, if applicable
    - **Dependencies:** any dependencies required for this change
- **Twitter handle:** if your PR gets announced, and you'd like a
mention, we'll gladly shout you out!


- [ ] **Add tests and docs**: 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.


- [ ] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/

Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.

If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.
2024-04-25 17:39:41 -07:00
Katarina Supe
0a486ecce2 docs: update Memgraph docs (#20736)
- **Description:** Memgraph Platform is being run differently now so I
updated this (I am DX engineer from Memgraph).
2024-04-25 17:39:41 -07:00
Bagatur
4308bd0e33 docs: install partner pkgs vercel (#20761) 2024-04-25 17:39:41 -07:00
Bagatur
13205a594e docs: automatically add api ref links (#20755)
![Screenshot 2024-04-22 at 1 51 13
PM](https://github.com/langchain-ai/langchain/assets/22008038/b8b09fec-3800-4b97-bd26-5571b8308f4a)
2024-04-25 17:39:41 -07:00
ccurme
a66ee9fba1 patch: deprecate (a)get_relevant_documents (#20477)
- `.get_relevant_documents(query)` -> `.invoke(query)`
- `.get_relevant_documents(query=query)` -> `.invoke(query)`
- `.get_relevant_documents(query, callbacks=callbacks)` ->
`.invoke(query, config={"callbacks": callbacks})`
- `.get_relevant_documents(query, **kwargs)` -> `.invoke(query,
**kwargs)`

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2024-04-25 17:39:41 -07:00
A Noor
c550cd13c8 docs: Fixed grammar mistake (#20697)
Description: Changed "You are" to "You are a". Grammar issue.
Dependencies: None

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
2024-04-25 17:39:41 -07:00
Leonid Kuligin
723bbda3db docs: on google-genai vs google-vertexai (#20713)
Thank you for contributing to LangChain!

- [ ] **PR title**: "docs: added a description of differences
langchain_google_genai vs langchain_google_vertexai"


- [ ]
- **Description:** added a description of differences
langchain_google_genai vs langchain_google_vertexai
2024-04-25 17:39:41 -07:00
shumway743
916f9588ed community[minor]: add graph store implementation for apache age (#20582)
**Description:** implemented GraphStore class for Apache Age graph db

**Dependencies:** depends on psycopg2

Unit and integration tests included. Formatting and linting have been
run.

---------

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-04-25 17:39:41 -07:00
Erick Friis
1784c94e53 docs: aws listing (#20674) 2024-04-25 17:39:40 -07:00
Mateusz Szewczyk
d48f859198 ibm: Add support for Embedding Models (#20647)
---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2024-04-25 17:39:40 -07:00
Tomaz Bratanic
1e9ba3e95a Update neo4j vector documentation (#20455)
Co-authored-by: Chester Curme <chester.curme@gmail.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
2024-04-25 17:39:40 -07:00
Saurabh Chalke
e06982db3a docs: Remove Duplicate --quiet Flag in Installation Command in LangSmith Docs (#20121)
**Description:** This pull request removes a duplicated `--quiet` flag
in the pip install command found in the LangSmith Walkthrough section of
the documentation.

**Issue:** N/A

**Dependencies:** None
2024-04-25 17:39:40 -07:00
Aditya
61d132855c Updated Tutorials for Vertex Vector Search (#20376)
Thank you for contributing to LangChain!

- [ ] **PR title**: "package: docs"


- [ ] **PR message**: 
    - **Description:** Updated Tutorials for Vertex Vector Search
    - **Issue:** NA
    - **Dependencies:** NA
- **Twitter handle:** if your PR gets announced, and you'd like a
mention, we'll gladly shout you out!

@lkuligin for review

---------

Co-authored-by: adityarane@google.com <adityarane@google.com>
Co-authored-by: Leonid Kuligin <lkuligin@yandex.ru>
Co-authored-by: Chester Curme <chester.curme@gmail.com>
2024-04-25 17:39:40 -07:00
Boris Djurdjevic
31afca6706 docs: Fix minor typo in data_connection/document_loaders/custom (#20648)
**Description:**
Minor documentation typo fix in
`data_connection/document_loaders/custom`: `thta's` -> `that's`
2024-04-25 17:39:40 -07:00
Leonid Ganeline
e93bb33cfa docs: integrations/retrievers cleanup (#20357)
Fixed format inconsistencies; added descriptions, links.
2024-04-25 17:39:40 -07:00
Leonid Ganeline
6ab64f23b2 docs: providers alibaba update (#20560)
Added missed integrations to the Alibaba Cloud provider page
2024-04-25 17:39:40 -07:00
Leonid Ganeline
cba348461c docs: imports update (#20625)
Updated imports in docs

Co-authored-by: Erick Friis <erick@langchain.dev>
2024-04-25 17:39:40 -07:00
Ethan Yang
c649273474 docs: Update openvino example documents links (#20638) 2024-04-25 17:39:40 -07:00
Sivaudha
202a07297b langchain[minor]: Databricks vector search self query integration (#20627)
- Enable self querying feature for databricks vector search

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
2024-04-25 17:39:40 -07:00
Charlie Holtz
faaaeab8a8 community: update Replicate to work with official models (#20633)
Description: you don't need to pass a version for Replicate official
models. That was broken on LangChain until now!

You can now run: 

```
llm = Replicate(
    model="meta/meta-llama-3-8b-instruct",
    model_kwargs={"temperature": 0.75, "max_length": 500, "top_p": 1},
)
prompt = """
User: Answer the following yes/no question by reasoning step by step. Can a dog drive a car?
Assistant:
"""
llm(prompt)
```

I've updated the replicate.ipynb to reflect that.

twitter: @charliebholtz

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2024-04-25 17:39:40 -07:00
Lance Martin
ef6628c75c community[patch]: Fix Ollama for LLaMA3 (#20624)
We see verbose generations w/ LLaMA3 and Ollama - 

https://smith.langchain.com/public/88c4cd21-3d57-4229-96fe-53443398ca99/r

--- 

Fix here implies that when stop was being set to an empty list, the
stream had no conditions under which to stop, which could lead to
excessive or unintended output.

Test LLaMA2 - 

https://smith.langchain.com/public/57dfc64a-591b-46fa-a1cd-8783acaefea2/r

Test LLaMA3 - 

https://smith.langchain.com/public/76ff5f47-ac89-4772-a7d2-5caa907d3fd6/r

https://smith.langchain.com/public/a31d2fad-9094-4c93-949a-964b27630ccb/r

Test Mistral -

https://smith.langchain.com/public/a4fe7114-c308-4317-b9fd-6c86d31f1c5b/r

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2024-04-25 17:39:40 -07:00
Erick Friis
19057204df infra: fix doc imports ci (#20629) 2024-04-25 17:39:40 -07:00
naaive
1e131c1fcb docs: Update body_func to hybrid_query in ElasticsearchRetriever (#20498) 2024-04-25 17:39:40 -07:00
Eugene Yurtsev
2f42e0e1b5 docs: Remove example vsdx data (#20620)
VSDX data contains EMF files. Some of these apparently can contain
exploits with some Adobe tools.

This is likely a false positive from antivirus software, but we
can remove it nonetheless.
2024-04-25 17:39:40 -07:00
Dhruv Chawla
ee297206ff docs: Update uptrain.ipynb to show outputs (#20551)
Hey @eyurtsev, I noticed that the notebook isn't displaying the outputs
properly. I've gone ahead and rerun the cells to ensure that readers can
easily understand the functionality without having to run the code
themselves.
2024-04-25 17:39:40 -07:00
Leonid Ganeline
a718223a80 docs: import update (#20610)
Updated imports
2024-04-25 17:39:40 -07:00
Ethan Yang
0c4e5f1599 community: Add save_model function for openvino reranker and embedding (#19896) 2024-04-25 17:39:40 -07:00
zR
aaec583b35 update zhipuai notebook (#20595)
fix timeout issue
fix zhipuai usecase notebookbook

Thank you for contributing to LangChain!

- [ ] **PR title**: "package: description"
- Where "package" is whichever of langchain, community, core,
experimental, etc. is being modified. Use "docs: ..." for purely docs
changes, "templates: ..." for template changes, "infra: ..." for CI
changes.
  - Example: "community: add foobar LLM"


- [ ] **PR message**: ***Delete this entire checklist*** and replace
with
    - **Description:** a description of the change
    - **Issue:** the issue # it fixes, if applicable
    - **Dependencies:** any dependencies required for this change
- **Twitter handle:** if your PR gets announced, and you'd like a
mention, we'll gladly shout you out!


- [ ] **Add tests and docs**: 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.


- [ ] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/

Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.

If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.
2024-04-25 17:39:40 -07:00
Justsosostar
7b933cb15f fix typo in langchain/docs/docs/intergrations/tools/nuclia.ipynb (#20591)
Thank you for contributing to LangChain!

- [x] **PR title**: "package: description"
- Where "package" is whichever of langchain, community, core,
experimental, etc. is being modified. Use "docs: ..." for purely docs
changes, "templates: ..." for template changes, "infra: ..." for CI
changes.
  - Example: "community: add foobar LLM"


- [ ] **PR message**: ***Delete this entire checklist*** and replace
with
    - **Description:** a description of the change
    - **Issue:** the issue # it fixes, if applicable
    - **Dependencies:** any dependencies required for this change
- **Twitter handle:** if your PR gets announced, and you'd like a
mention, we'll gladly shout you out!


- [ ] **Add tests and docs**: 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.


- [ ] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/

Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.

If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.
2024-04-25 17:39:40 -07:00
aditya thomas
b4cc71b5fc docs[callbacks]: update to the FileCallbackHandler documentation (#20496)
**Description:** Update to the `FileCallbackHandler` documentation
**Issue:** #20493 
**Dependencies:** None
2024-04-25 17:39:40 -07:00
Erick Friis
cb95413158 docs: nits (#20577) 2024-04-25 17:39:40 -07:00
Erick Friis
2091e9d2b1 docs: aws docs updates (#20571) 2024-04-25 17:39:40 -07:00
Erick Friis
e4a91e9454 upstage: init package (#20574)
Co-authored-by: Sean Cho <sean@upstage.ai>
Co-authored-by: JuHyung-Son <sonju0427@gmail.com>
2024-04-25 17:39:40 -07:00
Jacob Lee
62c8553839 Lock low level dep to fix Vercel docs build (#20573)
@baskaryan @efriis 

TODO: Figure out why our lockfile isn't being respected here
2024-04-25 17:39:39 -07:00
Guangdong Liu
6856205c17 docs: Get rid of ZeroShotAgent and use create_react_agent instead (#20154)
- **Issue:** close #20122
 - @baskaryan, @eyurtsev.
2024-04-25 17:39:39 -07:00
Guangdong Liu
48f28f9d00 docs: Get rid of ZeroShotAgent and use create_react_agent instead (#20155)
- **Issue:** #20122
- @baskaryan,@eyurtsev
2024-04-25 17:39:39 -07:00
Sevin F. Varoglu
789e1d9b24 community[minor]: add ChatOctoAI (#20059)
This PR adds ChatOctoAI, a chat model integration for OctoAI.
2024-04-25 17:39:39 -07:00
Bagatur
ac958c78a5 docs: add structred output to feat table (#20539) 2024-04-25 17:39:39 -07:00
pjb157
5040c1fddb community[minor]: Unify Titan Takeoff Integrations and Adding Embedding Support (#18775)
**Community: Unify Titan Takeoff Integrations and Adding Embedding
Support**

 **Description:** 
Titan Takeoff no longer reflects this either of the integrations in the
community folder. The two integrations (TitanTakeoffPro and
TitanTakeoff) where causing confusion with clients, so have moved code
into one place and created an alias for backwards compatibility. Added
Takeoff Client python package to do the bulk of the work with the
requests, this is because this package is actively updated with new
versions of Takeoff. So this integration will be far more robust and
will not degrade as badly over time.

**Issue:**
Fixes bugs in the old Titan integrations and unified the code with added
unit test converge to avoid future problems.

**Dependencies:**
Added optional dependency takeoff-client, all imports still work without
dependency including the Titan Takeoff classes but just will fail on
initialisation if not pip installed takeoff-client

**Twitter**
@MeryemArik9

Thanks all :)

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
2024-04-25 17:39:39 -07:00