Commit Graph

3877 Commits

Author SHA1 Message Date
SlapDrone
961a0e200f
Implement AgentExecutorIterator (#6929)
- Description: Implements a `.iter()` method for the `AgentExecutor`
class. This allows hooking into and intercepting intermediate agent
steps.
  - Issue: #6925 
  - Dependencies: None
  - Tag maintainer: @vowelparrot @agola11 
  - Twitter handle: @SlapDron3 @lacicocodes

---------

Co-authored-by: Lacico <Lacicocodes@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-23 18:00:22 -07:00
Harrison Chase
77bf75c236
bump experimental to 002 (#8150) 2023-07-23 09:22:39 -07:00
Harrison Chase
e46126eac6
add llamaapi (#8140) 2023-07-23 09:16:16 -07:00
Harrison Chase
f0eb5db670
Harrison/agent intro (#8138)
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-22 22:14:59 -07:00
Harrison Chase
cbf2fc8af8
prompt ergonomics (#7799) 2023-07-22 14:19:17 -07:00
Samuel Berthe
d81d6e874f
doc(sqldatabasechain): use views when jsonb column description is not available (#8133)
I think the PR diff is self explaining ;)

@baskaryan
2023-07-22 11:30:04 -07:00
Harrison Chase
506b21bfc2
Update MIGRATE.md 2023-07-22 09:11:43 -07:00
Harrison Chase
9854d9e5cb cr 2023-07-22 09:07:26 -07:00
Harrison Chase
9f3073d418
bump versions (#8129) 2023-07-22 08:46:37 -07:00
Harrison Chase
86946a47a8
Harrison/add back in experimental (#8128) 2023-07-22 08:27:29 -07:00
Karthik Raja A
8b08687fc4
MultiOn client toolkit (#8110)
Addition of MultiOn Client Agent Toolkit
Dependencies: multion pip package
This PR consists of the following:
- MultiOn utility,tools and integration with agent
- sample jupyter notebook.
Request @hwchase17 , @hinthornw

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-07-22 08:19:01 -07:00
Harrison Chase
aa0e69bc98
Harrison/official pre release (#8106) 2023-07-21 18:44:32 -07:00
Philip Kiely - Baseten
95bcf68802
add kwargs support for Baseten models (#8091)
This bugfix PR adds kwargs support to Baseten model invocations so that
e.g. the following script works properly:

```python
chatgpt_chain = LLMChain(
    llm=Baseten(model="MODEL_ID"),
    prompt=prompt,
    verbose=False,
    memory=ConversationBufferWindowMemory(k=2),
    llm_kwargs={"max_length": 4096}
)
```
2023-07-21 13:56:27 -07:00
Harrison Chase
8dcabd9205
bump releases rc0 (#8097) 2023-07-21 13:54:57 -07:00
Bagatur
58f65fcf12
use top nav docs (#8090) 2023-07-21 13:52:03 -07:00
Harrison Chase
0faba034b1
add experimental release action (#8096) 2023-07-21 13:38:35 -07:00
Harrison Chase
d353d668e4
remove CVEs (#8092)
This PR aims to move all code with CVEs into `langchain.experimental`.
Note that we are NOT yet removing from the core `langchain` package - we
will give people a week to migrate here.

See MIGRATE.md for how to migrate

Zero changes to functionality

Vulnerabilities this addresses:

PALChain:
- https://security.snyk.io/vuln/SNYK-PYTHON-LANGCHAIN-5752409
- https://security.snyk.io/vuln/SNYK-PYTHON-LANGCHAIN-5759265

SQLDatabaseChain
- https://security.snyk.io/vuln/SNYK-PYTHON-LANGCHAIN-5759268

`load_prompt` (Python files only)
- https://security.snyk.io/vuln/SNYK-PYTHON-LANGCHAIN-5725807
2023-07-21 13:32:39 -07:00
Bagatur
08c658d3f8
fix api ref (#8083) 2023-07-21 12:37:21 -07:00
Harrison Chase
344cbd9c90
update contributor guide (#8088) 2023-07-21 12:01:05 -07:00
Harrison Chase
17c06ee456 cr 2023-07-21 10:48:00 -07:00
Harrison Chase
da04760de1
Harrison/move experimental (#8084) 2023-07-21 10:36:28 -07:00
Harrison Chase
f35db9f43e
(WIP) set up experimental (#7959) 2023-07-21 09:20:24 -07:00
c-bata
623b321e75
Fix allowed_search_types in VectorStoreRetriever (#8064)
Unexpectedly changed at
6792a3557d

<!-- 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
 -->

I guess `allowed_search_types` is unexpectedly changed in
6792a3557d,
so that we cannot specify `similarity_score_threshold` here.

```python
class VectorStoreRetriever(BaseRetriever):
    ...
    allowed_search_types: ClassVar[Collection[str]] = (
        "similarity",
        "similarityatscore_threshold",
        "mmr",
    )

    @root_validator()
    def validate_search_type(cls, values: Dict) -> Dict:
        """Validate search type."""
        search_type = values["search_type"]
        if search_type not in cls.allowed_search_types:
            raise ValueError(...)
        if search_type == "similarity_score_threshold":
            ... # UNREACHABLE CODE
```

VectorStores Maintainers: @rlancemartin @eyurtsev
2023-07-21 08:39:36 -07:00
Bagatur
95e369b38d
bump 239 (#8077) 2023-07-21 07:31:14 -07:00
William FH
c38965fcba
Add embedding and vectorstore provider info as tags (#8027)
Example:
https://smith.langchain.com/public/bcd3714d-abba-4790-81c8-9b5718535867/r


The vectorstore implementations aren't super standardized yet, so just
adding an optional embeddings property to pass in.
2023-07-20 22:40:01 -07:00
Mohammad Mohtashim
355b7d8b86
Getting SQL cmd directly from SQLDatabase Chain. (#7940)
- Description: Get SQL Cmd directly generated by SQL-Database Chain
without executing it in the DB engine.
- Issue: #4853 
- Tag maintainer: @hinthornw,@baskaryan

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-07-20 22:36:55 -07:00
Lance Martin
5a084e1b20
Async HTML loader and HTML2Text transformer (#8036)
New HTML loader that asynchronously loader a list of urls. 
 
New transformer using [HTML2Text](https://github.com/Alir3z4/html2text/)
for HTML to clean, easy-to-read plain ASCII text (valid Markdown).
2023-07-20 22:30:59 -07:00
Wey Gu
cf60cff1ef
feat: Add with_history option for chatglm (#8048)
In certain 0-shot scenarios, the existing stateful language model can
unintentionally send/accumulate the .history.

This commit adds the "with_history" option to chatglm, allowing users to
control the behavior of .history and prevent unintended accumulation.

Possible reviewers @hwchase17 @baskaryan @mlot

Refer to discussion over this thread:
https://twitter.com/wey_gu/status/1681996149543276545?s=20
2023-07-20 22:25:37 -07:00
Harrison Chase
1f3b987860
Harrison/GitHub toolkit (#8047)
Co-authored-by: Trevor Dobbertin <trevordobbertin@gmail.com>
2023-07-20 22:24:55 -07:00
Leonid Ganeline
ae8bc9e830
Refactored sql_database (#7945)
The `sql_database.py` is unnecessarily placed in the root code folder.
A similar code is usually placed in the `utilities/`.
As a byproduct of this placement, the sql_database is [placed on the top
level of classes in the API
Reference](https://api.python.langchain.com/en/latest/api_reference.html#module-langchain.sql_database)
which is confusing and not correct.


- moved the `sql_database.py` from the root code folder to the
`utilities/`

@baskaryan

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-07-20 22:17:55 -07:00
William FH
dc9d6cadab
Dedup methods (#8049) 2023-07-20 22:13:22 -07:00
Harrison Chase
f99f497b2c
Harrison/predibase (#8046)
Co-authored-by: Abhay Malik <32989166+Abhay-765@users.noreply.github.com>
2023-07-20 19:26:50 -07:00
Jacob Lee
56c6ab1715
Fix bad docs sidebar header (#7966)
Quick fix for:

<img width="283" alt="Screenshot 2023-07-19 at 2 49 44 PM"
src="https://github.com/hwchase17/langchain/assets/6952323/91e4868c-b75e-413d-9f8f-d34762abf164">

CC @baskaryan
2023-07-20 19:06:57 -07:00
Wian Stipp
ebc5ff2948
HuggingFaceTextGenInference bug fix: Multiple values for keyword argument (#8044)
Fixed the bug causing: `TypeError: generate() got multiple values for
keyword argument 'stop_sequences'`

```python
res = await self.async_client.generate(
                prompt,
                **self._default_params,
                stop_sequences=stop,
                **kwargs,
            )
```
The above throws an error because stop_sequences is in also in the
self._default_params.
---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-20 19:05:08 -07:00
Kacper Łukawski
ed6a5532ac
Implement async support in Qdrant local mode (#8001)
I've extended the support of async API to local Qdrant mode. It is faked
but allows prototyping without spinning a container. The tests are
improved to test the in-memory case as well.

@baskaryan @rlancemartin @eyurtsev @agola11
2023-07-20 19:04:33 -07:00
Bagatur
7717c24fc4
fix redis cache chat model (#8041)
Redis cache currently stores model outputs as strings. Chat generations
have Messages which contain more information than just a string. Until
Redis cache supports fully storing messages, cache should not interact
with chat generations.
2023-07-20 19:00:05 -07:00
Taqi Jaffri
973593c5c7
Added streaming support to Replicate (#8045)
Streaming support is useful if you are doing long-running completions or
need interactivity e.g. for chat... adding it to replicate, using a
similar pattern to other LLMs that support streaming.

Housekeeping: I ran `make format` and `make lint`, no issues reported in
the files I touched.

I did update the replicate integration test but ran into some issues,
specifically:

1. The original test was failing for me due to the model argument not
being specified... perhaps this test is not regularly run? I fixed it by
adding a call to the lightweight hello world model which should not be
burdensome for replicate infra.
2. I couldn't get the `make integration_tests` command to pass... a lot
of failures in other integration tests due to missing dependencies...
however I did make sure the particluar test file I updated does pass, by
running `poetry run pytest
tests/integration_tests/llms/test_replicate.py`

Finally, I am @tjaffri https://twitter.com/tjaffri for feature
announcement tweets... or if you could please tag @docugami
https://twitter.com/docugami we would really appreciate that :-)

Tagging model maintainers @hwchase17  @baskaryan 

Thank for all the awesome work you folks are doing.

---------

Co-authored-by: Taqi Jaffri <tjaffri@docugami.com>
2023-07-20 18:59:54 -07:00
Piyush Jain
31b7ddc12c
Neptune graph and openCypher QA Chain (#8035)
## Description
This PR adds a graph class and an openCypher QA chain to work with the
Amazon Neptune database.

## Dependencies
`requests` which is included in the LangChain dependencies.

## Maintainers for Review
@krlawrence
@baskaryan

### Twitter handle
pjain7
2023-07-20 18:56:47 -07:00
Leonid Ganeline
995220b797
Refactored math_utils (#7961)
`math_utils.py` is in the root code folder. This creates the
`langchain.math_utils: Math Utils` group on the API Reference navigation
ToC, on the same level with `Chains` and `Agents` which is not correct.

Refactoring:
- created the `utils/` folder
- moved `math_utils.py` to `utils/math.py`
- moved `utils.py` to `utils/utils.py`
- split `utils.py` into `utils.py, env.py, strings.py`
- added module description

@baskaryan
2023-07-20 18:55:43 -07:00
Paolo Picello
5137f40dd6
Update mongodb_atlas.py docstrings (#8033)
Hi all, I just added the "index_name" parameter to the docstrings for
mongodb_atlas.py (it is missing in the [public doc
page](https://api.python.langchain.com/en/latest/vectorstores/langchain.vectorstores.mongodb_atlas.MongoDBAtlasVectorSearch.html#langchain-vectorstores-mongodb-atlas-mongodbatlasvectorsearch).

Thanks
2023-07-20 17:35:07 -07:00
felixocker
9226fda58b
fix: create schema description from URIs and str w/out rdflib warnings (#8025)
- Description: fix to avoid rdflib warnings when concatenating URIs and
strings to create the text snippet for the knowledge graph's schema.
@marioscrock pointed this out in a comment related to #7165
- Issue: None, but the problem was mentioned as a comment in #7165
- Dependencies: None
- Tag maintainer: Related to memory -> @hwchase17, maybe @baskaryan as
it is a fix
2023-07-20 15:55:19 -07:00
Emory Petermann
7239d57a53
Update Golden integration documentation (#8030)
fixes some typos and cleans up onboarding for golden, thank you!

@hinthornw
2023-07-20 15:53:44 -07:00
Jonathon Belotti
021bb9be84
Update Modal.com integration docs (#8014)
Hey, I'm a Modal Labs engineer and I'm making this docs update after
getting a user question in [our beta Slack
space](https://join.slack.com/t/modalbetatesters/shared_invite/zt-1xl9gbob8-1QDgUY7_PRPg6dQ49hqEeQ)
about the Langchain integration docs.

🔗 [Modal beta-testers link to docs discussion
thread](https://modalbetatesters.slack.com/archives/C031Z7DBQFL/p1689777700594819?thread_ts=1689775859.855849&cid=C031Z7DBQFL)
2023-07-20 15:53:06 -07:00
Jeffrey Wang
62d0475c29
Add Metaphor new field and reformat docs (#8022)
This PR reformats our python notebook example and also adds a new field
we have.

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2023-07-20 15:50:54 -07:00
William FH
e2a99bd169
Different error strings (#8010) 2023-07-20 09:58:25 -07:00
Bagatur
ec4f93b629
bump 238 (#8012) 2023-07-20 09:21:15 -07:00
vrushankportkey
5f10d2ea1d
Add Portkey LLMOps integration (#7877)
Integrating Portkey, which adds production features like caching,
tracing, tagging, retries, etc. to langchain apps.

  - Dependencies: None
  - Twitter handle: https://twitter.com/portkeyai
  - test_portkey.py added for tests
  - example notebook added in new utilities folder in modules
  
 Also fixed a bug with OpenAIEmbeddings where headers weren't passing.

cc @baskaryan

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-20 09:08:44 -07:00
Boris Nieuwenhuis
095937ad52
Add google place ID to google places tool response (#7789)
- Description: this change will add the google place ID of the found
location to the response of the GooglePlacesTool
  - Issue: Not applicable
  - Dependencies: no dependencies
  - Tag maintainer: @hinthornw
  - Twitter handle: Not applicable
2023-07-20 09:04:31 -07:00
Bagatur
7c24a6b9d1
Bagatur/apify (#8008)
<!-- 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: Jiří Moravčík <jiri.moravcik@gmail.com>
Co-authored-by: Jan Čurn <jan.curn@gmail.com>
2023-07-20 08:36:01 -07:00
Aiden Le
1d7414a371
Feature: Add openai_api_model attribute to Doctran models (#7868)
- Description: Added the ability to define the open AI model.
- Issue: Currently the Doctran instance uses gpt-4 by default, this does
not work if the user has no access to gpt -4.
  - rlancemartin, @eyurtsev, @baskaryan

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-20 07:27:56 -07:00