Commit Graph

4873 Commits

Author SHA1 Message Date
Erick Friis
1de1182a9f docs: discourage unconfirmed partner packages (#24099) 2024-07-11 00:34:37 +00:00
ccurme
975b6129f6 core[patch]: support conversion of runnables to tools (#23992)
Open to other thoughts on UX.

string input:
```python
as_tool = retriever.as_tool()
as_tool.invoke("cat")  # [Document(...), ...]
```

typed dict input:
```python
class Args(TypedDict):
    key: int

def f(x: Args) -> str:
    return str(x["key"] * 2)

as_tool = RunnableLambda(f).as_tool(
    name="my tool",
    description="description",  # name, description are inferred if not supplied
)
as_tool.invoke({"key": 3})  # "6"
```

for untyped dict input, allow specification of parameters + types
```python
def g(x: Dict[str, Any]) -> str:
    return str(x["key"] * 2)

as_tool = RunnableLambda(g).as_tool(arg_types={"key": int})
result = as_tool.invoke({"key": 3})  # "6"
```

Passing the `arg_types` is slightly awkward but necessary to ensure tool
calls populate parameters correctly:
```python
from typing import Any, Dict

from langchain_core.runnables import RunnableLambda
from langchain_openai import ChatOpenAI


def f(x: Dict[str, Any]) -> str:
    return str(x["key"] * 2)

runnable = RunnableLambda(f)
as_tool = runnable.as_tool(arg_types={"key": int})

llm = ChatOpenAI().bind_tools([as_tool])

result = llm.invoke("Use the tool on 3.")
tool_call = result.tool_calls[0]
args = tool_call["args"]
assert args == {"key": 3}

as_tool.run(args)
```

Contrived (?) example with langgraph agent as a tool:
```python
from typing import List, Literal
from typing_extensions import TypedDict

from langchain_openai import ChatOpenAI
from langgraph.prebuilt import create_react_agent


llm = ChatOpenAI(temperature=0)


def magic_function(input: int) -> int:
    """Applies a magic function to an input."""
    return input + 2


agent_1 = create_react_agent(llm, [magic_function])


class Message(TypedDict):
    role: Literal["human"]
    content: str

agent_tool = agent_1.as_tool(
    arg_types={"messages": List[Message]},
    name="Jeeves",
    description="Ask Jeeves.",
)

agent_2 = create_react_agent(llm, [agent_tool])
```

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2024-07-10 19:29:59 -04:00
Jacob Lee
b63a48b7d3 docs[patch]: Fix typos, add prereq sections (#24095) 2024-07-10 23:15:37 +00:00
Erick Friis
141943a7e1 infra: docs ignore step in script (#24090) 2024-07-10 15:18:00 -07:00
jongwony
14dd89a1ee docs: add itemgetter in how_to/dynamic_chain (#23951)
Hello! I am honored to be able to contribute to the LangChain project
for the first time.

- **Description:** Using `RunnablePassthrough` logic without providing
`chat_history` key will result in nested keys in `question`, so I submit
a pull request to resolve this issue.

I am attaching a LangSmith screenshot below.

This is the result of the current version of the document.

<img width="1112" alt="image"
src="https://github.com/langchain-ai/langchain/assets/12846075/f0597089-c375-472f-b2bf-793baaecd836">

without `chat_history`:

<img width="1112" alt="image"
src="https://github.com/langchain-ai/langchain/assets/12846075/5c0e3ae7-3afe-417c-9132-770387f0fff2">


- **Lint and test**: 

<img width="777" alt="image"
src="https://github.com/langchain-ai/langchain/assets/12846075/575d2545-3aed-4338-9779-1a0b17365418">
2024-07-10 17:17:51 +00:00
ccurme
9c6efadec3 community[patch]: propagate cost information to OpenAI callback (#23996)
This is enabled following
https://github.com/langchain-ai/langchain/pull/22716.
2024-07-10 14:50:35 +00:00
Dismas Banda
91b37b2d81 docs: fix spelling mistake in concepts.mdx: Fouth -> Fourth (#24067)
**Description:** 
Corrected the spelling for fourth.

**Twitter handle:** @dismasbanda
2024-07-10 14:35:54 +00:00
Jacob Lee
66265aaac4 docs[patch]: Update GPT4All docs (#24044)
CC @efriis
2024-07-10 02:39:42 +00:00
Jacob Lee
8dac0fb3f1 docs[patch]: Remove deprecated Airbyte loaders from listings (#23927)
CC @efriis
2024-07-10 02:21:25 +00:00
Ethan Yang
13855ef0c3 [HuggingFace Pipeline] add streaming support (#23852) 2024-07-09 17:02:00 -04:00
Bhadresh Savani
5d78b34a6f [Docs] typo Update in azureopenai.ipynb (#23945)
Update documentation for a typo.
2024-07-08 17:48:33 -04:00
Bagatur
1e957c0c23 docs: rm discord (#23985) 2024-07-08 14:27:58 -07:00
Mustafa Abdul-Kader
f152d6ed3d docs(llamacpp): fix copy paste error (#23983) 2024-07-08 20:06:04 +00:00
JonasDeitmersATACAMA
4d6f28cdde Update annoy.ipynb (#23970)
mmemory in the description -> memory (corrected spelling mistake)

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, ccurme, vbarda, hwchase17.
2024-07-08 12:52:05 +00:00
Zheng Robert Jia
bf8d4716a7 Update concepts.mdx (#23955)
Added link to list of built-in tools.

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, ccurme, vbarda, hwchase17.
2024-07-08 08:47:51 -04:00
Zheng Robert Jia
4ec5fdda8d Update index.mdx (#23956)
Added reference to built-in tools list.
2024-07-08 08:47:28 -04:00
ccurme
ee579c77c1 docs: chain migration guide (#23844)
Co-authored-by: jacoblee93 <jacoblee93@gmail.com>
2024-07-05 16:37:34 -07:00
Rajendra Kadam
8b84457b17 community[minor]: Support PGVector in PebbloRetrievalQA (#23874)
- **Description:** Support PGVector in PebbloRetrievalQA
  - Identity and Semantic Enforcement support for PGVector
  - Refactor Vectorstore validation and name check
  - Clear the overridden identity and semantic enforcement filters
- **Issue:** NA
- **Dependencies:** NA
- **Tests**: NA(already added)
-  **Docs**: Updated
- **Twitter handle:** [@Raj__725](https://twitter.com/Raj__725)
2024-07-05 16:02:25 -04:00
Leonid Ganeline
fcd018be47 docs: langgraph link fix (#23848)
Link for the LangGraph doc is instead the LG repo link.
Fixed the link
2024-07-05 15:50:45 -04:00
Robbie Cronin
0990ab146c community: update import in chatbot tutorial to use InMemoryChatMessageHistory (#23903)
Summary of change:

- Replace ChatMessageHistory with InMemoryChatMessageHistory

Fixes #23892

---------

Co-authored-by: Eugene Yurtsev <eugene@langchain.dev>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
2024-07-05 15:48:11 -04:00
Mateusz Szewczyk
902b57d107 IBM: Added WatsonxChat passing params to invoke method (#23758)
Thank you for contributing to LangChain!

- [x] **PR title**: "IBM: Added WatsonxChat to chat models preview,
update passing params to invoke method"


- [x] **PR message**: 
- **Description:** Added WatsonxChat passing params to invoke method,
added integration tests
    - **Dependencies:** `ibm_watsonx_ai`


- [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/

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2024-07-05 18:07:50 +00:00
ccurme
25de47878b langchain[patch]: deprecate AnalyzeDocumentChain (#23769) 2024-07-05 14:00:23 -04:00
Klaudia Lemiec
a2082bc1f8 docs: Arxiv docs update (#23871)
- [X] **PR title**
- [X] **PR message**: ***Delete this entire checklist*** and replace
with
    - **Description:** Update of docstrings and docpages
- **Issue:**
[22866](https://github.com/langchain-ai/langchain/issues/22866)

- [X] **Add tests and docs**

- [X] **Lint and test**
2024-07-05 11:43:51 -04:00
jonathan | ヨナタン
d311f22182 Langchain: fixed a typo in the imports (#23864)
Description: Fixed a typo during the imports for the
GoogleDriveSearchTool
    
Issue: It's only for the docs, but it bothered me so i decided to fix it
quickly :D
2024-07-05 15:42:50 +00:00
Arun Sasidharan
db6512aa35 docs: fix typo in llm_chain.ipynb (#23907)
- Fix typo in the tutorial step
- Add some context on `text`
2024-07-05 15:41:46 +00:00
André Quintino
99b1467b63 community: add support for 'cloud' parameter in JiraAPIWrapper (#23057)
- **Description:** Enhance JiraAPIWrapper to accept the 'cloud'
parameter through an environment variable. This update allows more
flexibility in configuring the environment for the Jira API.
 - **Twitter handle:** Andre_Q_Pereira

---------

Co-authored-by: André Quintino <andre.quintino@tui.com>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Co-authored-by: Chester Curme <chester.curme@gmail.com>
2024-07-05 15:11:10 +00:00
volodymyr-memsql
a4eb6d0fb1 community: add SingleStoreDB semantic cache (#23218)
This PR adds a `SingleStoreDBSemanticCache` class that implements a
cache based on SingleStoreDB vector store, integration tests, and a
notebook example.

Additionally, this PR contains minor changes to SingleStoreDB vector
store:
 - change add texts/documents methods to return a list of inserted ids
 - implement delete(ids) method to delete documents by list of ids
 - added drop() method to drop a correspondent database table
- updated integration tests to use and check functionality implemented
above


CC: @baskaryan, @hwchase17

---------

Co-authored-by: Volodymyr Tkachuk <vtkachuk-ua@singlestore.com>
2024-07-05 09:26:06 -04:00
eliasecchig
efb48566d0 docs: add Vertex Feature Store, edit BigQuery Vector Search (#23709)
Add Vertex Feature Store, edit BigQuery Vector Search docs

---------

Co-authored-by: Chester Curme <chester.curme@gmail.com>
2024-07-05 12:12:21 +00:00
Yuki Watanabe
0e916d0d55 community: Overhaul MLflow Integration documentation (#23067) 2024-07-03 22:52:17 -04:00
Mu Xian Ming
c06c666ce5 docs: fix docs/tutorials/llm_chain.ipynb (#23807)
to correctly display the link

Co-authored-by: Mu Xianming <mu.xianming@lmwn.com>
2024-07-03 15:38:31 -04:00
Vadym Barda
d206df8d3d docs: improve structure in the agent migration to langgraph guide (#23817) 2024-07-03 12:25:11 -07:00
Bagatur
8842a0d986 docs: fireworks nit (#23822) 2024-07-03 15:36:27 +00:00
Bagatur
e787249af1 docs: fireworks standard page (#23816) 2024-07-03 14:33:05 +00:00
Jacob Lee
27aa4d38bf docs[patch]: Update structured output docs to have more discussion (#23786)
CC @agola11 @ccurme
2024-07-02 16:53:31 -07:00
William W Wang
76e7e4e9e6 Update docs: LangChain agent memory (#23673)
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"


**Description:** Update docs content on agent memory

If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
2024-07-02 17:06:32 -04:00
Bagatur
27ce58f86e docs: google genai standard page (#23766)
Part of #22296
2024-07-02 13:54:34 -04:00
Karim Lalani
acc8fb3ead docs[patch]: Update OllamaFunctions docs to match chat model integration template (#23179)
Added Tool Calling Agent Example with langgraph to OllamaFunctions
documentation
2024-07-02 10:05:44 -07:00
Bagatur
79c07a8ade docs: standardize bedrock page (#23738)
Part of #22296
2024-07-02 12:03:36 -04:00
Teja Hara
a77a263e24 Added langchain-community installation (#23741)
PR title: Docs enhancement

- Description: Adding installation instructions for integrations
requiring langchain-community package since 0.2
- Issue: https://github.com/langchain-ai/langchain/issues/22005

---------

Co-authored-by: ccurme <chester.curme@gmail.com>
2024-07-02 11:03:07 -04:00
Khelan Modi
4457e64e13 Update azure_cosmos_db for mongodb documentation (#23740)
added pre-filtering documentation

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"


- [x] **PR message**: 
    - **Description:** added filter vector search 
    - **Issue:** N/A
    - **Dependencies:** N/A
    - **Twitter handle:**: n/a


- [x] **Add tests and docs**: If you're adding a new integration, please
include - No need for tests, just a simple doc update
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, ccurme, vbarda, hwchase17.
2024-07-02 12:53:05 +00:00
mattthomps1
cc55823486 docs: updated PPLX model (#23723)
Description: updated pplx docs to reference a currently [supported
model](https://docs.perplexity.ai/docs/model-cards). pplx-70b-online
->llama-3-sonar-small-32k-online

---------

Co-authored-by: Chester Curme <chester.curme@gmail.com>
2024-07-02 08:48:49 -04:00
Bagatur
aa165539f6 docs: standardize cohere page (#23739)
Part of #22296
2024-07-01 19:34:13 -04:00
Jacob Lee
7791d92711 community[patch]: Fix requests alias for load_tools (#23734)
CC @baskaryan
2024-07-01 15:02:14 -07:00
Jacob Lee
f4b2e553e7 docs[patch]: Update Unstructured loader notebooks and install instructions (#23726)
CC @baskaryan @MthwRobinson
2024-07-01 13:36:48 -07:00
Jacob Lee
d2c7379f1c 👥 Update LangChain people data (#23697)
👥 Update LangChain people data

---------

Co-authored-by: github-actions <github-actions@github.com>
2024-07-01 17:42:55 +00:00
Francesco Kruk
7538f3df58 Update jina embedding notebook to show multimodal capability more clearly (#23702)
After merging the [PR #22594 to include Jina AI multimodal capabilities
in the Langchain
documentation](https://github.com/langchain-ai/langchain/pull/22594), we
updated the notebook to showcase the difference between text and
multimodal capabilities more clearly.
2024-07-01 09:13:19 -04:00
Sourav Biswal
b60df8bb4f Update chatbot.ipynb (#23688)
DOC: missing parenthesis #23687

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"


- [x] **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!


- [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, ccurme, vbarda, hwchase17.
2024-07-01 13:00:34 +00:00
Mateusz Szewczyk
a78ccb993c ibm: Add support for Chat Models (#22979) 2024-06-29 01:59:25 -07:00
Jacob Lee
16c59118eb docs[patch]: Adds short tracing how-tos and conceptual guide (#23657)
CC @agola11
2024-06-28 18:28:49 -07:00
Jacob Lee
c0bb26e85b docs[patch]: Typo fix (#23652) 2024-06-28 17:27:44 -07:00