Commit Graph

1367 Commits

Author SHA1 Message Date
Janos Tolgyesi
15687a28d5
Use correct tokenizer for Bedrock/Anthropic LLMs (#11561)
**Description**

This PR implements the usage of the correct tokenizer in Bedrock LLMs,
if using anthropic models.

**Issue:** #11560

**Dependencies:** optional dependency on `anthropic` python library.

**Twitter handle:** jtolgyesi


---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-12 08:41:52 -07:00
kYLe
467b082c34
Modify Anyscale integration to work with Anyscale Endpoint (#11569)
**Description:** Modify Anyscale integration to work with [Anyscale
Endpoint](https://docs.endpoints.anyscale.com/)
and it supports invoke, async invoke, stream and async invoke features

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-12 08:41:25 -07:00
plpycoin
51193309ea
Update readthedocs.py (#11110)
Only parse .html files
.svg .png favicon.ico will crash processing phase

---------

Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
2023-10-12 11:32:06 -04:00
Nuno Campos
ca9de26f2b
Add callback function to RunnablePassthrough (#11564)
<!-- 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.
 -->
2023-10-12 15:10:16 +01:00
Nuno Campos
7f4734c0dd
Add deploy command to repos generated by cli template (#11711)
<!-- 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.
 -->
2023-10-12 15:09:21 +01:00
Nuno Campos
1c0857b53e
Fix default impl of aparse_result (#11702)
Should delegate to parse_result, not to aparse, as parse_result is a
method that some output parsers override

<!-- 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.
 -->
2023-10-12 14:13:59 +01:00
nuric
44da27c07b
Add SemaDB VST wrapper (#11484)
- **Description**: Adding vectorstore wrapper for
[SemaDB](https://rapidapi.com/semafind-semadb/api/semadb).
- **Issue**: None
- **Dependencies**: None
- **Twitter handle**: semafind

Checks performed:
- [x] `make format`
- [x] `make lint`
- [x] `make test`
- [x] `make spell_check`
- [x] `make docs_build`

Documentation added:

- SemaDB vectorstore wrapper tutorial
2023-10-11 19:09:38 -07:00
hsuyuming
0b743f005b
Feature/enhance huggingfacepipeline to handle different return type (#11394)
**Description:** Avoid huggingfacepipeline to truncate the response if
user setup return_full_text as False within huggingface pipeline.

**Dependencies:** : None
**Tag maintainer:**   Maybe @sam-h-bean ?

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-11 19:09:03 -07:00
Leonid Kuligin
2aba9ab47e
Retriever based on GCP DocAI Warehouse (#11400)
- **Description:** implements a retriever on top of DocAI Warehouse (to
interact with existing enterprise documents)
  https://cloud.google.com/document-ai-warehouse?hl=en
  - **Issue:** new functionality
 
@baskaryan

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-11 19:08:53 -07:00
Erick Friis
a477ddda45
Langsmith in readme update (#11497) 2023-10-11 18:43:52 -07:00
Leonid Kuligin
9e81ab47be
Added a better error description if processor name is wrong. (#11488)
Replace this entire comment with:
  - **Description:** added a better error description for this error
  - **Issue:** #11407 
  
  @baskaryan
2023-10-11 18:43:40 -07:00
Robert Yi
e75766b759
fix: incorrect arguments in clickhouse docstring (#11693)
fix docstring for clickhouse
2023-10-11 21:41:21 -04:00
Eugene Yurtsev
17b5090c18
Add type to Agent actions (#11682)
Add `type` to agent actions.
2023-10-11 21:33:24 -04:00
April
c14a8df2ee
wrap confluence attachment processing with a try-except block (#11503)
Prevents document loading from erroring out when an attachment is not
found at the url.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-11 18:13:42 -07:00
eajechiloae
4ba2c8ba75
Fix ClearML callback (#11472)
Handle different field names in dicts/dataframes, fixing the ClearML
callback.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-11 17:09:02 -07:00
Lawrence Wu
93bb19f69a
Fix chains/loading.py error messages (#11688)
- **Description:** make the error messages consistent in
chains/loading.py
  - **Dependencies:** None
2023-10-11 17:05:42 -07:00
Harrison Chase
18ebce2032
fix tool async (#11689) 2023-10-11 16:40:23 -07:00
sudranga
9beb03e771
11474 (#11519)
No relevant documents may be found for a given question. In some use
cases, we could directly respond with a fixed message instead of doing
an LLM call with an empty context. This PR exposes this as an option:
response_if_no_docs_found.

---------

Co-authored-by: Sudharsan Rangarajan <sudranga@nile-global.com>
2023-10-11 16:30:15 -07:00
Joaquin Menendez
ef99b06362
feature: add metadata information into the embedding file before uplo… (#11553)
Replace this entire comment with:
- **Description:** In this modified version of the function, if the
metadatas parameter is not None, the function includes the corresponding
metadata in the JSON object for each text. This allows the metadata to
be stored alongside the text's embedding in the vector store.
  - 
  - **Issue:** #10924
  - **Dependencies:** None
  - **Tag maintainer:** @hwchase17
@agola11
  - **Twitter handle:** @MelliJoaco

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-11 16:05:13 -07:00
Marcin Wątroba
51a3a86022
#11655 Add SQLAlchemyMd5Cache implementation (#11660)
- **Description:** Add SQLAlchemyMd5Cache implementation, 
  - **Issue:** the issue # #11655,
  - **Dependencies:** no deps,
  - **Tag maintainer:** @markowanga

---------

Co-authored-by: Marcin Wątroba <marcin.watroba@pwr.edu.pl>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-11 15:28:09 -07:00
Suresh Kumar Ponnusamy
70f7558db2
langchain-experimental: Add allow_list support in experimental/data_anonymizer (#11597)
- **Description:** Add allow_list support in langchain experimental
data-anonymizer package
  - **Issue:** no
  - **Dependencies:** no
  - **Tag maintainer:** @hwchase17
  - **Twitter handle:**
2023-10-11 14:50:41 -07:00
wemysschen
2363c02cf3
Bos loader (#11525)
**Description:**
Add  BaiduCloud BOS document loader.

---------

Co-authored-by: chenweixu01 <chenweixu01@baidu.com>
Co-authored-by: root <root@icoding-cwx.bcc-szzj.baidu.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-11 14:43:48 -07:00
Kwanghoon Choi
fbb82608cd
Fixed a bug in reporting Python code validation (#11522)
- **Description:** fixed a bug in pal-chain when it reports Python
    code validation errors. When node.func does not have any ids, the
    original code tried to print node.func.id in raising ValueError.
- **Issue:** n/a,
- **Dependencies:** no dependencies,
- **Tag maintainer:** @hazzel-cn, @eyurtsev
- **Twitter handle:** @lazyswamp

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-11 14:34:28 -07:00
Harrison Chase
9f39c23a13
add input type for convo retrieval chain (#11679) 2023-10-11 17:13:48 -04:00
zhaozhiming
d5e762d328
fix: Change the docs of JSONAgentOutputParser (#11594)
I am merely making some minor adjustments to the function documentation.
I hope to provide a small assistance to LangChain.
- **Description:** Change the docs of JSONAgentOutputParser. It will be
`JSON` better,
  - **Issue:** no,
  - **Dependencies:** no,
  - **Tag maintainer:** @hwchase17,
  - **Twitter handle:** Not worth mentioning.
2023-10-11 14:05:53 -07:00
Vinay Kakade
dd0cd98861
Add support for ChatOpenAI models in Infino callback handler (#11608)
**Description:** This PR adds support for ChatOpenAI models in the
Infino callback handler. In particular, this PR implements
`on_chat_model_start` callback, so that ChatOpenAI models are supported.
With this change, Infino callback handler can be used to track latency,
errors, and prompt tokens for ChatOpenAI models too (in addition to the
support for OpenAI and other non-chat models it has today). The existing
example notebook is updated to show how to use this integration as well.
cc/ @naman-modi @savannahar68

**Issue:** https://github.com/langchain-ai/langchain/issues/11607 

**Dependencies:** None

**Tag maintainer:** @hwchase17 

**Twitter handle:** [@vkakade](https://twitter.com/vkakade)
2023-10-11 14:00:54 -07:00
Israel Ekpo
d0603c86b6
Add Support for Azure Cosmos DB MongoDB vCore Vector Store #11627 (#11632)
This PR adds support for the Azure Cosmos DB MongoDB vCore Vector Store

https://learn.microsoft.com/en-us/azure/cosmos-db/mongodb/vcore/

https://learn.microsoft.com/en-us/azure/cosmos-db/mongodb/vcore/vector-search

Summary:
- **Description:** added vector store integration for Azure Cosmos DB
MongoDB vCore Vector Store,
  - **Issue:** the issue # it fixes #11627,
  - **Dependencies:** pymongo dependency,
  - **Tag maintainer:** @hwchase17,
  - **Twitter handle:** @izzyacademy

---------

Co-authored-by: Israel Ekpo <israel.ekpo@gmail.com>
Co-authored-by: Israel Ekpo <44282278+izzyacademy@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-11 13:56:46 -07:00
Erick Friis
28ee6a7c12
Track ChatFireworks time to first_token (#11672) 2023-10-11 13:37:03 -07:00
Eugene Yurtsev
539941281d
Fix output types for BaseChatModel (#11670)
* Should use non chunked messages for Invoke/Batch
* After this PR, stream output type is not represented, do we want to
use the union?

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2023-10-11 16:02:03 -04:00
Eugene Yurtsev
99adcdb1c9
Add dedicated type attribute to be used solely for serialization purposes (#11585)
Adds standard `type` field for all messages that will be
serialized/validated by pydantic.

* The presence of `type` makes it easier for developers consuming
schemas to write client code to serialize/deserialize.
* In LangServe `type` will be used for both validation and will appear
in the generated openapi specs
2023-10-11 15:06:42 -04:00
eryk-dsai
06d5971be9
Fix issue #10985 - Skip model.to(device) if it is instantiated with bitsandbytes config (#11009)
Preventing error caused by attempting to move the model that was already
loaded on the GPU using the Accelerate module to the same or another
device. It is not possible to load model with Accelerate/PEFT to CPU for
now

Addresses:
[#10985](https://github.com/langchain-ai/langchain/issues/10985)
2023-10-11 09:28:27 -07:00
Nuno Campos
64969bc8ae
Add patch_config(configurable=) arg, make with_config(configurable=) merge it with existing (#11662)
<!-- 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.
 -->
2023-10-11 14:45:31 +01:00
Harrison Chase
ce0019b646
make utils conditional (#11646) 2023-10-11 06:11:32 +01:00
Harrison Chase
8f06085b24
make tools conditional (#11647) 2023-10-11 06:11:05 +01:00
Bassem Yacoube
5451b724fc
Adds support for llama2 and fixes MPT-7b url (#11465)
- **Description:** This is an update to OctoAI LLM provider that adds
support for llama2 endpoints hosted on OctoAI and updates MPT-7b url
with the current one.
@baskaryan
Thanks!

---------

Co-authored-by: ML Wiz <bassemgeorgi@gmail.com>
2023-10-10 20:34:35 -07:00
Todd Kerpelman
0bff399af1
Make metadata from the url_selenium loader match that of the web_base loader (#11617)
**Description:** I noticed the metadata returned by the url_selenium
loader was missing several values included by the web_base loader. (The
former returned `{source: ...}`, the latter returned `{source: ...,
title: ..., description: ..., language: ...}`.) This change fixes it so
both loaders return all 4 key value pairs.

Files have been properly formatted and all tests are passing. Note,
however, that I am not much of a python expert, so that whole "Adding
the imports inside the code so that tests pass" thing seems weird to me.
Please LMK if I did anything wrong.
2023-10-10 20:32:45 -07:00
Tarun Thotakura
c9d4d53545
Fixed the assignment of custom_llm_provider argument (#11628)
- **Description:** Assigning the custom_llm_provider to the default
params function so that it will be passed to the litellm
- **Issue:** Even though the custom_llm_provider argument is being
defined it's not being assigned anywhere in the code and hence its not
being passed to litellm, therefore any litellm call which uses the
custom_llm_provider as required parameter is being failed. This
parameter is mainly used by litellm when we are doing inference via
Custom API server.
https://docs.litellm.ai/docs/providers/custom_openai_proxy
  - **Dependencies:** No dependencies are required

@krrishdholakia , @baskaryan

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-10 20:29:24 -07:00
Leonid Ganeline
db67ccb0bb
docstrings cleanup (#11640)
Added missed docstrings. Some reformatting.
2023-10-10 19:56:47 -07:00
Yang, Bo
3a82bd7bdb
Use raise from statement so that users can find detailed error message (#11461)
- **Description:** Use `raise from` statement so that users can find
detailed error message
  - **Tag maintainer:** @baskaryan, @eyurtsev, @hwchase17
2023-10-10 17:25:23 -07:00
Nuno Campos
9a0ed75a95
Add configurable fields with options (#11601)
<!-- 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.
 -->
2023-10-10 22:17:22 +01:00
Bagatur
7232e082de
bump 312 (#11621) 2023-10-10 12:34:49 -07:00
Eugene Yurtsev
58220cda72
Remove LLM Bash and related bash utilities (#11619)
Deprecate LLMBash and related bash utilities
2023-10-10 14:54:09 -04:00
Shubham Kushwaha
49de862076
Arcee.ai LLM & Retriever integration (#11579)
- **Description:** This PR introduces a new LLM and Retriever API to
https://arcee.ai for the python client
  - **Issue:** implements the integrations as requested in #11578 ,
  - **Dependencies:** no dependencies are required,
  - **Tag maintainer:** @hwchase17
  - **Twitter handle:** shwooobham 


** `make format`, `make lint` and `make test` runs locally.**
```shell
=========== 1245 passed, 277 skipped, 20 warnings in 16.26s ===========
./scripts/check_pydantic.sh .
./scripts/check_imports.sh
poetry run ruff .
[ "." = "" ] || poetry run black . --check
All done!  🍰 
1818 files would be left unchanged.
[ "." = "" ] || poetry run mypy .
Success: no issues found in 1815 source files
[ "." = "" ] || poetry run black .
All done!  🍰 
1818 files left unchanged.
[ "." = "" ] || poetry run ruff --select I --fix .
poetry run codespell --toml pyproject.toml
poetry run codespell --toml pyproject.toml -w
```


**Contributions**
1. Arcee (langchain/llms), ArceeRetriever (langchain/retrievers),
ArceeWrapper (langchain/utilities)
2. docs for Arcee (llms/arcee.py) and
ArceeRetriever(retrievers/arcee.py)
3.

cc: @jacobsolawetz @ben-epstein

---------

Co-authored-by: Shubham <shubham@sORo.local>
2023-10-10 10:20:45 -07:00
Eugene Yurtsev
b56ca0c2a4
Deprecate LLMSymbolicMath from langchain core (#11615)
Deprecate LLMSymbolicMath from langchain core package.
2023-10-10 12:33:51 -04:00
Eugene Yurtsev
c9bce5bbfb
Add version to langchain_experimental (#11613)
Add version to langchain experimental
2023-10-10 11:17:41 -04:00
Predrag Gruevski
22abeb9f6c
Disable loading jinja2 PromptTemplate from file. (#10252)
jinja2 templates are not sandboxed and are at risk for arbitrary code
execution. To mitigate this risk:
- We no longer support loading jinja2-formatted prompt template files.
- `PromptTemplate` with jinja2 may still be constructed manually, but
the class carries a security warning reminding the user to not pass
untrusted input into it.

Resolves #4394.
2023-10-10 11:15:42 -04:00
Nuno Campos
c7c03d4709
Fix mutation bugs in callback manager configure (#11603)
<!-- 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.
 -->
2023-10-10 14:50:18 +01:00
cccs-eric
e2a9072b80
Fix CohereRerank configuration (#11583)
**Description:** CohereRerank is missing `cohere_api_key` as a field and
since extras are forbidden, it is not possible to pass-in the key. The
only way is to use an env variable named `COHERE_API_KEY`.

For example, if trying to create a compressor like this:
```python
cohere_api_key = "......Cohere api key......"
compressor = CohereRerank(cohere_api_key=cohere_api_key)
```
you will get the following error:
```
  File "/langchain/.venv/lib/python3.10/site-packages/pydantic/v1/main.py", line 341, in __init__
    raise validation_error
pydantic.v1.error_wrappers.ValidationError: 1 validation error for CohereRerank
cohere_api_key
  extra fields not permitted (type=value_error.extra)
```
2023-10-09 23:26:34 -07:00
Anar
55fef4b64b
implemented add files method in LLMRails (#11518)
This PR provides add files method with LLMRails. Implemented here are:

docs/extras/integrations/vectorstores/llm-rails.ipynb

---------

Co-authored-by: Anar Aliyev <aaliyev@mgmt.cloudnet.services>
2023-10-09 16:29:43 -07:00
Stephen Hankinson
316dddc7cd
fix wording of query_sql_database_tool_description (#11530)
- **Description:** Fixes minor typo for the
query_sql_database_tool_description in the db toolkit
  - **Issue:** N/A
  - **Dependencies:** N/A
  - **Tag maintainer:** @nfcampos 
  - **Twitter handle:** N/A
2023-10-09 15:32:45 -07:00