Commit Graph

4834 Commits

Author SHA1 Message Date
Bagatur
ce08f436db
Expose loads and dumps in load namespace 2023-09-28 09:34:48 -04:00
Nuno Campos
cfa2203c62
Add input/output schemas to runnables (#11063)
This adds `input_schema` and `output_schema` properties to all
runnables, which are Pydantic models for the input and output types
respectively. These are inferred from the structure of the Runnable as
much as possible, the only manual typing needed is
- optionally add type hints to lambdas (which get translated to
input/output schemas)
- optionally add type hint to RunnablePassthrough

These schemas can then be used to create JSON Schema descriptions of
input and output types, see the tests

- [x] Ensure no InputType and OutputType in our classes use abstract
base classes (replace with union of subclasses)
- [x] Implement in BaseChain and LLMChain
- [x] Implement in RunnableBranch
- [x] Implement in RunnableBinding, RunnableMap, RunnablePassthrough,
RunnableEach, RunnableRouter
- [x] Implement in LLM, Prompt, Chat Model, Output Parser, Retriever
- [x] Implement in RunnableLambda from function signature
- [x] Implement in Tool

<!-- 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/hwchase17/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.
 -->
2023-09-28 11:05:15 +01:00
Eugene Yurtsev
b05bb9e136
LangServe (#11046)
Adds LangServe package

* Integrate Runnables with Fast API creating Server and a RemoteRunnable
client
* Support multiple runnables for a given server
* Support sync/async/batch/abatch/stream/astream/astream_log on the
client side (using async implementations on server)
* Adds validation using annotations (relying on pydantic under the hood)
-- this still has some rough edges -- e.g., open api docs do NOT
generate correctly at the moment
* Uses pydantic v1 namespace

Known issues: type translation code doesn't handle a lot of types (e.g.,
TypedDicts)

---------

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
2023-09-28 10:52:44 +01:00
Nuno Campos
77ce9ed6f1
Support using async callback handlers with sync callback manager (#10945)
The current behaviour just calls the handler without awaiting the
coroutine, which results in exceptions/warnings, and obviously doesn't
actually execute whatever the callback handler does

<!-- 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/hwchase17/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.
 -->
2023-09-28 10:39:01 +01:00
Bagatur
48a04aed75
bump 304 (#11147) 2023-09-27 19:24:09 -07:00
Jonathan Evans
23065f54c0
Added prompt wrapping for Claude with Bedrock (#11090)
- **Description:** Prompt wrapping requirements have been implemented on
the service side of AWS Bedrock for the Anthropic Claude models to
provide parity between Anthropic's offering and Bedrock's offering. This
overnight change broke most existing implementations of Claude, Bedrock
and Langchain. This PR just steals the the Anthropic LLM implementation
to enforce alias/role wrapping and implements it in the existing
mechanism for building the request body. This has also been tested to
fix the chat_model implementation as well. Happy to answer any further
questions or make changes where necessary to get things patched and up
to PyPi ASAP, TY.
- **Issue:** No issue opened at the moment, though will update when
these roll in.
  - **Dependencies:** None

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-09-27 19:20:07 -07:00
xiaoyu
b87cc8b31e
add 3 property types in metadata for notiondb loader (#8509)
### Description: 
NotionDB supports a number of common property types. I have found three
common types that are not included in notiondb loader. When programs
loaded them with notiondb, which will cause some metadata information
not to be passed to langchain. Therefore, I added three common types:
- date
- created_time
- last_edit_time.

### Issue: 
no
### Dependencies: 
No dependencies added :)
### Tag maintainer: 
@rlancemartin, @eyurtsev
### Twitter handle: 
@BJTUTC
2023-09-27 17:38:05 -07:00
Harrison Chase
258d67b0ac
Revert "improve the performance of base.py" (#11143)
Reverts langchain-ai/langchain#8610

this is actually an oversight - this merges all dfs into one df. we DO
NOT want to do this - the idea is we work and manipulate multiple dfs
2023-09-27 17:37:29 -07:00
Mohamad Zamini
9306394078
improve the performance of base.py (#8610)
This removes the use of the intermediate df list and directly
concatenates the dataframes if path is a list of strings. The pd.concat
function combines the dataframes efficiently, making it faster and more
memory-efficient compared to appending dataframes to a list.

<!-- Thank you for contributing to LangChain!

Replace this 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 you're PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.

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.

Maintainer responsibilities:
  - General / Misc / if you don't know who to tag: @baskaryan
  - DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev
  - Models / Prompts: @hwchase17, @baskaryan
  - Memory: @hwchase17
  - Agents / Tools / Toolkits: @hinthornw
  - Tracing / Callbacks: @agola11
  - Async: @agola11

If no one reviews your PR within a few days, feel free to @-mention the
same people again.

See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
 -->

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-09-27 17:36:03 -07:00
Mincoolee
05b75f3f13
feat: add support for arxiv identifier in ArxivAPIWrapper() (#9318)
- Description: this PR adds the support for arxiv identifier of the
ArxivAPIWrapper. I modified the `run()` and `load()` functions in
`arxiv.py`, using regex to recognize if the query is in the form of
arxiv identifier (see
[https://info.arxiv.org/help/find/index.html](https://info.arxiv.org/help/find/index.html)).
If so, it will directly search the paper corresponding to the arxiv
identifier. I also modified and added tests in `test_arxiv.py`.
  - Issue: #9047 
  - Dependencies: N/A
  - Tag maintainer: N/A

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-09-27 17:35:16 -07:00
William FH
d3c2ca5656
Enhanced pairwise error (#11131) 2023-09-27 16:04:43 -07:00
Taqi Jaffri
b7e9db5e73
Stop sequences in fireworks, plus notebook updates (#11136)
The new Fireworks and FireworksChat implementations are awesome! Added
in this PR https://github.com/langchain-ai/langchain/pull/11117 thank
you @ZixinYang

However, I think stop words were not plumbed correctly. I've made some
simple changes to do that, and also updated the notebook to be a bit
clearer with what's needed to use both new models.


---------

Co-authored-by: Taqi Jaffri <tjaffri@docugami.com>
2023-09-27 16:01:05 -07:00
William FH
33da8bd711
Add Exact match and Regex Match Evaluators (#11132) 2023-09-27 14:18:07 -07:00
Harrison Chase
e355606b11
add more import checks (#11033) 2023-09-27 11:17:12 -07:00
Dan Bolser
efb7c459a2
Update base.py (#10843)
Fixing a typo in the example code in the docstring...

You have to start somewhere though right?

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-09-27 11:15:58 -07:00
Jeremy Naccache
c59a5bae48
Fix intermediate steps example in docs : replaced json.dumps with Langchain's dumps() (#10593)
The intermediate steps example in docs has an example on how to retrieve
and display the intermediate steps.
But the intermediate steps object is of type AgentAction which cannot be
passed to json.dumps (it raises an error).
I replaced it with Langchain's dumps function (from langchain.load.dump
import dumps) which is the preferred way to do so.
2023-09-27 11:00:29 -07:00
tanujtiwari-at
a79f595543
Support extra tools argument for pandas agent toolkit (#11040)
**Description** 

We support adding new tools in some toolkits already like the [SQLAgent
toolkit](https://github.com/langchain-ai/langchain/blob/master/libs/langchain/langchain/agents/agent_toolkits/sql/base.py#L27).

Related
[SO](https://stackoverflow.com/questions/76583163/are-langchain-toolkits-able-to-be-modified-can-we-add-tools-to-a-pandas-datafra)
thread
This replicates the same functionality here, so users can add custom
bespoke tools.
2023-09-27 10:57:04 -07:00
Aashish Saini
c4471d1877
Fixing some spelling mistakes (#10881)
@baskaryan

---------

Co-authored-by: AashutoshPathakShorthillsAI <142410372+AashutoshPathakShorthillsAI@users.noreply.github.com>
Co-authored-by: Aayush <142384656+AayushShorthillsAI@users.noreply.github.com>
Co-authored-by: Aashish Saini <141953346+AashishSainiShorthillsAI@users.noreply.github.com>
Co-authored-by: ManpreetShorthillsAI <142380984+ManpreetShorthillsAI@users.noreply.github.com>
Co-authored-by: AryamanJaiswalShorthillsAI <142397527+AryamanJaiswalShorthillsAI@users.noreply.github.com>
Co-authored-by: Adarsh Shrivastav <142413097+AdarshKumarShorthillsAI@users.noreply.github.com>
Co-authored-by: Vishal <141389263+VishalYadavShorthillsAI@users.noreply.github.com>
Co-authored-by: ChetnaGuptaShorthillsAI <142381084+ChetnaGuptaShorthillsAI@users.noreply.github.com>
Co-authored-by: PankajKumarShorthillsAI <142473460+PankajKumarShorthillsAI@users.noreply.github.com>
Co-authored-by: AbhishekYadavShorthillsAI <142393903+AbhishekYadavShorthillsAI@users.noreply.github.com>
Co-authored-by: AmitSinghShorthillsAI <142410046+AmitSinghShorthillsAI@users.noreply.github.com>
Co-authored-by: Md Nazish Arman <142379599+MdNazishArmanShorthillsAI@users.noreply.github.com>
Co-authored-by: KamalSharmaShorthillsAI <142474019+KamalSharmaShorthillsAI@users.noreply.github.com>
Co-authored-by: Lakshya <lakshyagupta87@yahoo.com>
Co-authored-by: AnujMauryaShorthillsAI <142393269+AnujMauryaShorthillsAI@users.noreply.github.com>
Co-authored-by: Saransh Sharma <142397365+SaranshSharmaShorthillsAI@users.noreply.github.com>
Co-authored-by: GhayurHamzaShorthillsAI <136243850+GhayurHamzaShorthillsAI@users.noreply.github.com>
Co-authored-by: Puneet Dhiman <142409038+PuneetDhimanShorthillsAI@users.noreply.github.com>
Co-authored-by: Riya Rana <142411643+RiyaRanaShorthillsAI@users.noreply.github.com>
Co-authored-by: Akshay Tripathi <142379735+AkshayTripathiShorthillsAI@users.noreply.github.com>
2023-09-27 10:56:51 -07:00
Bagatur
410ac8129d
bump 303 (#11120) 2023-09-27 08:30:33 -07:00
Bagatur
8e4dbae428
Add fireworks chat model (#11117) 2023-09-27 08:22:12 -07:00
Bagatur
657581dbdf Fix ChatFireworks typing 2023-09-27 08:15:40 -07:00
Bagatur
12aad659dd add ChatFireworks to chat_models 2023-09-27 08:11:26 -07:00
Bagatur
872ebdaf90 remove FireworksChat from llms 2023-09-27 08:10:41 -07:00
Bagatur
9451240941 Fix fireworks chat linting issues 2023-09-27 08:09:33 -07:00
Harrison Chase
6b4928ad96
fix-lcel-notebooks (#11111)
fix some missing imports/naming
2023-09-27 06:36:11 -07:00
Tomáš Dvořák
865a21938c
speed up enforce_stop_tokens helper function (#10984)
**Description:**

As long as `enforce_stop_tokens` returns a first occurrence, we can
speed up the execution by setting the optional `maxsplit` parameter to
1.

Tag maintainer:
@agola11
@hwchase17

<!-- 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/hwchase17/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.
 -->

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-09-27 05:29:29 -07:00
Austin Walker
bb41252dab
fix: bump min_unstructured_version for UnstructuredAPIFileLoader (#11025)
**Description:** New metadata fields were added to
`unstructured==0.10.15`, and our hosted api has been updated to reflect
this. When users call `partition_via_api` with an older version of the
library, they'll hit a parsing error related to the new fields.
2023-09-27 05:28:06 -07:00
William FH
75b3893daf
Fix runnable branch callbacks (#11091)
We aren't calling on_chain_end here unless we use the default option
2023-09-27 11:38:56 +01:00
Bagatur
6c5251feb0 poetry 2023-09-26 20:12:49 -07:00
Bagatur
5310184f96 poetry 2023-09-26 20:12:29 -07:00
Cynthia Yang
6dd44ff1c0
Refactor Fireworks and add ChatFireworks (#3) (#10597)
Description 
* Refactor Fireworks within Langchain LLMs.
* Remove FireworksChat within Langchain LLMs.
* Add ChatFireworks (which uses chat completion api) to Langchain chat
models.
* Users have to install `fireworks-ai` and register an api key to use
the api.

Issue - Not applicable
Dependencies - None
Tag maintainer - @rlancemartin @baskaryan
2023-09-26 20:11:55 -07:00
Bagatur
5514ebe859
Don't type chains in output_parsers (#11092)
Can't use TYPE_CHECKING style imports for pydantic params because it will try to instantiate the typed object by default.
2023-09-26 17:49:35 -07:00
CG80499
64385c4eae
Make pairwise comparison chain more like LLM as a judge (#11013)
<!-- Thank you for contributing to LangChain!

Replace this entire comment with:
  - **Description:**: Adds LLM as a judge as an eval chain
  - **Tag maintainer:** @hwchase17 

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/hwchase17/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.
 -->

---------

Co-authored-by: William FH <13333726+hinthornw@users.noreply.github.com>
2023-09-26 13:19:04 -07:00
Joseph McElroy
175ef0a55d
[ElasticsearchStore] Enable custom Bulk Args (#11065)
This enables bulk args like `chunk_size` to be passed down from the
ingest methods (from_text, from_documents) to be passed down to the bulk
API.

This helps alleviate issues where bulk importing a large amount of
documents into Elasticsearch was resulting in a timeout.

Contribution Shoutout
- @elastic

- [x] Updated Integration tests

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-09-26 12:53:50 -07:00
Eugene Yurtsev
d19fd0cfae
LogEntry/LogStream use str instead of uuid for id (#11080)
Cast the UUID to a string
2023-09-26 20:38:51 +01:00
Bagatur
d85339b9f2
extract sublinks exclude by abs path (#11079) 2023-09-26 12:26:27 -07:00
Bagatur
7ee8b2d1bf
exclude dirs in async recursive loading (#11077) 2023-09-26 09:59:04 -07:00
Leonid Ganeline
21199cc7b4
📖 docs: fixed integrations/document loaders toc (#9281)
Fixed navbar:
- renamed several files, so ToC is sorted correctly
- made ToC items consistent: formatted several Titles
- added several links
- reformatted several docs to a consistent format
- renamed several files (removed `_example` suffix)
- added renamed files to the `docs/docs_skeleton/vercel.json`
2023-09-26 09:47:37 -07:00
Bagatur
0ea384d575
fix multiple chains lcel how to (#11074) 2023-09-26 08:39:02 -07:00
Bagatur
12fb393a43
bump 302 (#11070) 2023-09-26 08:13:01 -07:00
Bagatur
097ecef06b
refactor web base loader (#11057) 2023-09-26 08:11:31 -07:00
Bagatur
487611521d
fix root import (#11072) 2023-09-26 08:11:16 -07:00
Bagatur
a2f7246f0e
skip excluded sublinks before recursion (#11036) 2023-09-26 02:24:54 -07:00
William FH
9c5eca92e4
Update notebook deps (#11053) 2023-09-25 22:41:29 -07:00
William FH
448426a6ac
Add collab link (#11052) 2023-09-25 22:35:25 -07:00
William FH
4aec587979
Update LangSmith Walkthrough (#11043) 2023-09-25 22:32:56 -07:00
Harrison Chase
bea78b3271
make warnings more modular (#11047) 2023-09-25 20:46:43 -07:00
Harrison Chase
c87e9fb2ce
conditional imports (#11017) 2023-09-25 15:46:32 -07:00
Tomaz Bratanic
0625ab7a9e
Filtering graph schema for Cypher generation (#10577)
Sometimes you don't want the LLM to be aware of the whole graph schema,
and want it to ignore parts of the graph when it is constructing Cypher
statements.
2023-09-25 14:14:15 -07:00
Palau
89ef440c14
Kay retriever (#10657)
- **Description**: Adding retrievers for [kay.ai](https://kay.ai) and
SEC filings powered by Kay and Cybersyn. Kay provides context as a
service: it's an API built for RAG.
- **Issue**: N/A
- **Dependencies**: Just added a dep to the
[kay](https://pypi.org/project/kay/) package
- **Tag maintainer**: @baskaryan @hwchase17 Discussed in slack
- **Twtter handle:** [@vishalrohra_](https://twitter.com/vishalrohra_)

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-09-25 13:10:13 -07:00