Commit Graph

8268 Commits

Author SHA1 Message Date
aditya thomas
b43a9d5808
docs: adding voyageai to the list of partner packages (#19376)
**Description:** Adding VoyageAI to the list of partners
**Issue:** A standalone langchain-voyageai package has been added
**Dependencies:** None
2024-03-22 17:08:15 -07:00
Zeeland
2549df00cd
docs: fix error bilibili url (#19375)
Thank you for contributing to LangChain!

bilibili-api-python use https://github.com/Nemo2011/bilibili-api repo.
Change to the correct address.

- [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.
2024-03-22 17:06:17 -07:00
aditya thomas
375ab7bf59
docs: update module imports for fireworks documentation (#19377)
**Description:** Update module imports for Fireworks documentation
**Issue:** Module imports not present or in incorrect location
**Dependencies:** None
2024-03-22 17:05:27 -07:00
aditya thomas
0cc0467267
docs: update import paths and move to lcel for llama.cpp examples (#19391)
**Description:** Update import paths and move to lcel for llama.cpp
examples
**Issue:** Update import paths to reflect package refactoring and move
chains to LCEL in examples
**Dependencies:** None

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
2024-03-23 00:04:12 +00:00
fengjial
3b52ee05d1
community[patch]: fix bugs in baiduvectordb as vectorstore (#19380)
fix small bugs in vectorstore/baiduvectordb
2024-03-22 17:03:59 -07:00
Cailin Wang
5402aef32e
docs: Add partition parameter to DashVector (#19385)
**Description**: Add `partition` parameter to DashVector
dashvector.ipynb
**Related PR**: https://github.com/langchain-ai/langchain/pull/19023
**Twitter handle**: @CailinWang_

---------

Co-authored-by: root <root@Bluedot-AI>
2024-03-22 17:00:29 -07:00
aditya thomas
515aab3312
community[patch]: invoke callback prior to yielding token (openai) (#19389)
**Description:** Invoke callback prior to yielding token for BaseOpenAI
& OpenAIChat
**Issue:** [Callback for on_llm_new_token should be invoked before the
token is yielded by the model
#16913](https://github.com/langchain-ai/langchain/issues/16913)
**Dependencies:** None
2024-03-22 16:45:55 -07:00
aditya thomas
49e932cd24
community[patch]: invoke callback prior to yielding token (fireworks) (#19388)
**Description:** Invoke callback prior to yielding token for Fireworks
**Issue:** [Callback for on_llm_new_token should be invoked before the
token is yielded by the model
#16913](https://github.com/langchain-ai/langchain/issues/16913)
**Dependencies:** None
2024-03-22 16:44:06 -07:00
aditya thomas
16ef88a87d
docs: moving FireworksEmbeddings documentation to docs folder (#19398)
**Description:** Moving FireworksEmbeddings documentation to the
location docs/integration/text_embedding/ from langchain_fireworks/docs/
**Issue:** FireworksEmbeddings documentation was not in the correct
location
**Dependencies:** None

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-03-22 23:24:22 +00:00
Leonid Ganeline
06190063e7
infra: makefile api_docs_clean fix (#19405)
Fixed a Makefile command that cleans up the api_docs
2024-03-22 15:45:55 -07:00
Christophe Bornet
1b813fe6fe
langchain[patch]: Add async methods to VectorStoreRetrieverMemory (#19408) 2024-03-22 15:44:24 -07:00
Tarun Jain
ef6d3d66d6
community[patch]: docarray requires hnsw installation (#19416)
I have a small dataset, and I tried to use docarray:
``DocArrayHnswSearch ``. But when I execute, it returns:

```bash
    raise ImportError(
ImportError: Could not import docarray python package. Please install it with `pip install "langchain[docarray]"`.
```

Instead of docarray it needs to be 

```bash
docarray[hnswlib]
```

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
2024-03-22 22:39:07 +00:00
German Swan
d4dc98a9f9
community[patch]: RecursiveUrlLoader: add base_url option (#19421)
RecursiveUrlLoader does not currently provide an option to set
`base_url` other than the `url`, though it uses a function with such an
option.
For example, this causes it unable to parse the
`https://python.langchain.com/docs`, as it returns the 404 page, and
`https://python.langchain.com/docs/get_started/introduction` has no
child routes to parse.
`base_url` allows setting the `https://python.langchain.com/docs` to
filter by, while the starting URL is anything inside, that contains
relevant links to continue crawling.
I understand that for this case, the docusaurus loader could be used,
but it's a common issue with many websites.

---------

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-03-22 15:34:31 -07:00
Erick Friis
e71daa7a03
openai[patch]: add test coverage to output (#19462) 2024-03-22 15:33:10 -07:00
igeni
4babefcb2f
cli[patch]: Modified regular expression (#19449)
- **Description:** Modified regular expression to add support for
unicode chars and simplify pattern

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
2024-03-22 15:24:08 -07:00
Ray Bell
7d36ee38b7
docs: point to titantic dataset on web (#19455)
Updated `pd.read_csv("titantic.csv")` to
`pd.read_csv("https://raw.githubusercontent.com/pandas-dev/pandas/main/doc/data/titanic.csv")`
i.e. it will read it
https://raw.githubusercontent.com/pandas-dev/pandas/main/doc/data/titanic.csv
and allow anyone to run the code.

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
2024-03-22 22:22:41 +00:00
Ray Bell
f959fad56e
docs: use invoke instead of run (#19457)
Updated the deprecated run with invoke

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
2024-03-22 15:08:26 -07:00
Bagatur
d93d49bc43
openai[patch]: tool use integration test (#19460) 2024-03-22 14:49:54 -07:00
Erick Friis
a99e644913
openai[patch]: integration test structured output (#19459) 2024-03-22 21:43:24 +00:00
Erick Friis
ac57123f40
openai[patch]: release 0.1.1 (#19458) 2024-03-22 21:36:21 +00:00
Luca Dorigo
47cfbe7522
openai[patch]: [URGENT REGRESSION FIX] Don't fail if tool message already doesn't contain name (#19435)
- [ ] **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.

---------

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-03-22 14:33:50 -07:00
aditya thomas
bc028294d0
docs: delete mistralai embeddings doc from incorrect location (#19432)
**Description:** Delete MistralAIEmbeddings usage document from folder
partners/mistralai/docs
**Issue:** The document is present in the folder docs/docs
**Dependencies:** None
2024-03-22 14:02:59 -07:00
Erick Friis
11e37943ed
mistralai[patch]: fix core version (#19454) 2024-03-22 20:48:13 +00:00
Erick Friis
3b093160c4
mistralai[patch]: release 0.1.0rc1 (#19453) 2024-03-22 20:34:36 +00:00
aditya thomas
4856a87261
community[patch]: invoke callback prior to yielding token (llama.cpp) (#19392)
**Description:** Invoke callback prior to yielding token for llama.cpp
**Issue:** [Callback for on_llm_new_token should be invoked before the
token is yielded by the model
#16913](https://github.com/langchain-ai/langchain/issues/16913)
**Dependencies:** None
2024-03-22 16:17:56 -04:00
ccurme
c4599444ee
mistralai: update tool calling (#19451)
```python
from langchain.agents import tool
from langchain_mistralai import ChatMistralAI


llm = ChatMistralAI(model="mistral-large-latest", temperature=0)

@tool
def get_word_length(word: str) -> int:
    """Returns the length of a word."""
    return len(word)


tools = [get_word_length]
llm_with_tools = llm.bind_tools(tools)

llm_with_tools.invoke("how long is the word chrysanthemum")
```
currently raises
```
AttributeError: 'dict' object has no attribute 'model_dump'
```

Same with `.with_structured_output`
```python
from langchain_mistralai import ChatMistralAI
from langchain_core.pydantic_v1 import BaseModel

class AnswerWithJustification(BaseModel):
    """An answer to the user question along with justification for the answer."""
    answer: str
    justification: str

llm = ChatMistralAI(model="mistral-large-latest", temperature=0)
structured_llm = llm.with_structured_output(AnswerWithJustification)

structured_llm.invoke("What weighs more a pound of bricks or a pound of feathers")
```

This appears to fix.
2024-03-22 16:03:48 -04:00
Erick Friis
cceaca3e4f
cookbook[patch]: add strip of quotes (#19452) 2024-03-22 19:10:39 +00:00
ccurme
8a2528c34a
[langchain] fix OpenAIAssistantRunnable.create_assistant (#19081)
- **Description:** OpenAI assistants support some pre-built tools (e.g.,
`"retrieval"` and `"code_interpreter"`) and expect these as `{"type":
"code_interpreter"}`. This may have been upset by
https://github.com/langchain-ai/langchain/pull/18935
- **Issue:** https://github.com/langchain-ai/langchain/issues/19057
2024-03-22 13:23:19 -04:00
Harrison Chase
b40c80007f
core[minor]: Add utility code to create tool examples (#18602)
Co-authored-by: Chester Curme <chester.curme@gmail.com>
2024-03-22 13:17:40 -04:00
Erick Friis
53ac1ebbbc
mistralai[minor]: 0.1.0rc0, remove mistral sdk (#19420) 2024-03-22 01:24:58 +00:00
William FH
e980c14d6a
core[patch]: allow "placeholder" type in from_messages tuples (#19152)
Co-authored-by: Erick Friis <erick@langchain.dev>
2024-03-21 22:09:24 +00:00
billytrend-cohere
f6bcd42421
community[patch]: Replace positional argument with text=text for cohere>=5 compatibility (#19407)
- **Description:** Replace positional argument with text=text for
cohere>=5 compatibility
2024-03-21 10:42:51 -07:00
enfeng
b20c2640da
anthropic[patch]: update base_url of anthropic (#18634)
A small change ~

- [ ] **update base_url**: "package: langchain_anthropic"

---------

Co-authored-by: yangenfeng <yangenfeng@xiaoniangao.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2024-03-20 21:04:55 -07:00
Erick Friis
a9cda536ad
openai[patch]: fix core min version (#19366) 2024-03-20 15:38:29 -07:00
Erick Friis
0b20c098df
openai[patch]: fix name param (#19365) 2024-03-20 22:22:09 +00:00
Erick Friis
f6c8700326
openai[patch]: release 0.1.0, message id and name support (#19363) 2024-03-20 15:11:39 -07:00
Bagatur
3fa711dce0
experimental[patch]: Release 0.0.55 (#19353) 2024-03-20 13:06:39 -07:00
Erick Friis
2bcd760c46
robocorp[patch]: run integration tests on release (#19358) 2024-03-20 19:31:12 +00:00
Erick Friis
a031c183ae
robocorp[patch]: release 0.0.4 (#19357) 2024-03-20 12:28:41 -07:00
Bagatur
d95ea3550e
langchain[patch]: Release 0.1.13 (#19351) 2024-03-20 18:25:12 +00:00
Bagatur
b58b38769d
community[patch]: Release 0.0.29 (#19350) 2024-03-20 18:09:48 +00:00
Bagatur
5d220975fc
core[patch]: Release 0.1.33 (#19348) 2024-03-20 17:28:56 +00:00
Eugene Yurtsev
aa9ccca775
langchain[patch]: Add tests for indexing (#19342)
This PR adds tests for the indexing API
2024-03-20 13:00:22 -04:00
William FH
68298cdc82
[Feat] Accept non-dict if only 1 prompt input variable (#19156)
For prompt templates with only 1 variable (common in e.g.,
MessageGraph), it's convenient to wrap the incoming object in the
variable before formatting.


The downside of this, of course, would be that some number of
invocations will successfully format when the user may have intended to
format it properly before
2024-03-20 09:59:32 -07:00
mackong
d9396bdec1
langchain[patch]: add stop for various non-openai agents (#19333)
* Description: add stop for various non-openai agents.
* Issue: N/A
* Dependencies: N/A

---------

Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
2024-03-20 11:34:10 -04:00
Yudhajit Sinha
7d216ad1e1
community[patch]: Invoke callback prior to yielding token (titan_takeoff_pro) (#18624)
## PR title
community[patch]: Invoke callback prior to yielding token

## PR message
- Description: Invoke callback prior to yielding token in _stream_
method in llms/titan_takeoff_pro.
- Issue: #16913 
- Dependencies: None
2024-03-20 07:58:18 -07:00
Yudhajit Sinha
455a74486b
community[patch]: Invoke callback prior to yielding token (sparkllm) (#18625)
## PR title
community[patch]: Invoke callback prior to yielding token

## PR message
- Description: Invoke callback prior to yielding token in _stream_
method in llms/sparkllm.
- Issue: #16913 
- Dependencies: None
2024-03-20 07:57:53 -07:00
Yudhajit Sinha
5ac1860484
community[patch]: Invoke callback prior to yielding token (replicate) (#18626)
## PR title
community[patch]: Invoke callback prior to yielding token

## PR message
- Description: Invoke callback prior to yielding token in _stream_
method in llms/replicate.
- Issue: #16913 
- Dependencies: None
2024-03-20 07:57:27 -07:00
Yudhajit Sinha
9525e392de
community[patch]: Invoke callback prior to yielding token (pai_eas_endpoint) (#18627)
## PR title
community[patch]: Invoke callback prior to yielding token

## PR message
- Description: Invoke callback prior to yielding token in _stream_
method in llms/pai_eas_endpoint.
- Issue: #16913 
- Dependencies: None
2024-03-20 07:56:58 -07:00
Yudhajit Sinha
140f06e59a
community[patch]: Invoke callback prior to yielding token (openai) (#18628)
## PR title
community[patch]: Invoke callback prior to yielding token

## PR message
- Description: Invoke callback prior to yielding token in _stream_
method in llms/openai.
- Issue: #16913 
- Dependencies: None
2024-03-20 07:56:30 -07:00