Commit Graph

1684 Commits

Author SHA1 Message Date
Roma
2b4e9a3efa
Add unit test for _merge_splits function (#3513)
This commit adds a new unit test for the _merge_splits function in the
text splitter. The new test verifies that the function merges text into
chunks of the correct size and overlap, using a specified separator. The
test passes on the current implementation of the function.
2023-04-25 10:02:59 -07:00
Sami Liedes
61da2bb742
Pandas agent: Pass forward callback manager (#3518)
The Pandas agent fails to pass callback_manager forward, making it
impossible to use custom callbacks with it. Fix that.

Co-authored-by: Sami Liedes <sami.liedes@rocket-science.ch>
2023-04-25 09:58:56 -07:00
mbchang
a08e9a3109
Docs: fix naming typo (#3532) 2023-04-25 09:58:25 -07:00
Harrison Chase
dc2188b36d
bump version to 149 (#3530) 2023-04-25 08:43:59 -07:00
mbchang
831ca61481
docs: two_player_dnd docs (#3528) 2023-04-25 08:24:53 -07:00
yakigac
f338d6251c
Add a test for cosmos db memory (#3525)
Test for #3434 @eavanvalkenburg 
Initially, I was unaware and had submitted a pull request #3450 for the
same purpose, but I have now repurposed the one I used for that. And it
worked.
2023-04-25 08:10:02 -07:00
leo-gan
6b28cbe058
improved arxiv (#3495)
Improved `arxiv/tool.py` by adding more specific information to the
`description`. It would help with selecting `arxiv` tool between other
tools.
Improved `arxiv.ipynb` with more useful descriptions.
2023-04-25 08:09:17 -07:00
mbchang
29f321046e
doc: add two player D&D game (#3476)
In this notebook, we show how we can use concepts from
[CAMEL](https://www.camel-ai.org/) to simulate a role-playing game with
a protagonist and a dungeon master. To simulate this game, we create a
`TwoAgentSimulator` class that coordinates the dialogue between the two
agents.
2023-04-25 08:07:18 -07:00
Harrison Chase
0fc0aa62f2
Harrison/blockchain docloader (#3491)
Co-authored-by: Jon Saginaw <saginawj@users.noreply.github.com>
2023-04-25 08:07:06 -07:00
Harrison Chase
bee59b4689
Updated missing refactor in docs "return_map_steps" (#2956) (#3469)
Minor rename in the documentation that was overlooked when refactoring.

---------

Co-authored-by: Ehmad Zubair <ehmad@cogentlabs.co>
2023-04-24 22:28:47 -07:00
Harrison Chase
707741de58
Harrison/prediction guard (#3490)
Co-authored-by: Daniel Whitenack <whitenack.daniel@gmail.com>
2023-04-24 22:27:22 -07:00
Harrison Chase
7257f9e015
Harrison/tfidf parameters (#3481)
Co-authored-by: pao <go5kuramubon@gmail.com>
Co-authored-by: KyoHattori <kyo.hattori@abejainc.com>
2023-04-24 22:19:58 -07:00
Harrison Chase
eda69b13f3
openai embeddings (#3488) 2023-04-24 22:19:47 -07:00
Harrison Chase
d3ce47414d
Harrison/chroma update (#3489)
Co-authored-by: vyeevani <30946190+vyeevani@users.noreply.github.com>
Co-authored-by: Vineeth Yeevani <vineeth.yeevani@gmail.com>
2023-04-24 22:19:36 -07:00
Sami Liedes
c8b70e1c6a
langchain-server: Do not expose postgresql port to host (#3431)
Apart from being unnecessary, postgresql is run on its default port,
which means that the langchain-server will fail to start if there is
already a postgresql server running on the host. This is obviously less
than ideal.

(Yeah, I don't understand why "expose" is the syntax that does not
expose the ports to the host...)

Tested by running langchain-server and trying out debugging on a host
that already has postgresql bound to the port 5432.

Co-authored-by: Sami Liedes <sami.liedes@rocket-science.ch>
2023-04-24 22:19:23 -07:00
Harrison Chase
7084d69ea7
Harrison/verbose conv ret (#3492)
Co-authored-by: makretch <max.kretchmer@gmail.com>
2023-04-24 22:16:07 -07:00
Harrison Chase
36a039d017
Harrison/prompt prefix (#3496)
Co-authored-by: Ian <ArGregoryIan@gmail.com>
2023-04-24 22:15:44 -07:00
Harrison Chase
408a0183cd
Harrison/weaviate (#3494)
Co-authored-by: Nick Rubell <nick@rubell.com>
2023-04-24 22:15:32 -07:00
Eduard van Valkenburg
ba7a5ac9d7
Azure CosmosDB memory (#3434)
Still needs docs, otherwise works.
2023-04-24 22:15:12 -07:00
Lucas Vieira
e6c1c32aff
Support GCS Objects with / in GCS Loaders (#3356)
So, this is basically fixing the same things as #1517 but for GCS.

### Problem
When loading GCS Objects with `/` in the object key (eg.
folder/some-document.txt) using `GCSFileLoader`, the objects are
downloaded into a temporary directory and saved as a file.

This errors out when the parent directory does not exist within the
temporary directory.

### What this pr does
Creates parent directories based on object key.

This also works with deeply nested keys:
folder/subfolder/some-document.txt
2023-04-24 22:05:44 -07:00
Mindaugas Sharskus
a4d85f7fd5
[Fix #3365]: Changed regex to cover new line before action serious (#3367)
Fix for: [Changed regex to cover new line before action
serious.](https://github.com/hwchase17/langchain/issues/3365)
---

This PR fixes the issue where `ValueError: Could not parse LLM output:`
was thrown on seems to be valid input.

Changed regex to cover new lines before action serious (after the
keywords "Action:" and "Action Input:").

regex101: https://regex101.com/r/CXl1kB/1

---------

Co-authored-by: msarskus <msarskus@cisco.com>
2023-04-24 22:05:31 -07:00
Maxwell Mullin
696f840426
GuessedAtParserWarning from RTD document loader documentation example (#3397)
Addresses #3396 by adding 

`features='html.parser'` in example
2023-04-24 21:54:39 -07:00
engkheng
06f6c49e61
Improve llm_chain.ipynb and getting_started.ipynb for chains docs (#3380)
My attempt at improving the `Chain`'s `Getting Started` docs and
`LLMChain` docs. Might need some proof-reading as English is not my
first language.

In LLM examples, I replaced the example use case when a simpler one
(shorter LLM output) to reduce cognitive load.
2023-04-24 21:49:55 -07:00
Zander Chase
b89c258bc5
Add retry logic for ChromaDB (#3372)
Rewrite of #3368

Mainly an issue for when people are just getting started, but still nice
to not throw an error if the number of docs is < k.

Add a little decorator utility to block mutually exclusive keyword
arguments
2023-04-24 21:48:29 -07:00
tkarper
6b49be9951
Add Databutton to list of Deployment options (#3364) 2023-04-24 21:45:38 -07:00
jrhe
980cc41709
Adds progress bar using tqdm to directory_loader (#3349)
Approach copied from `WebBaseLoader`. Assumes the user doesn't have
`tqdm` installed.
2023-04-24 21:42:42 -07:00
killpanda
344e3508b1
bug_fixes: use md5 instead of uuid id generation (#3442)
At present, the method of generating `point` in qdrant is to use random
`uuid`. The problem with this approach is that even documents with the
same content will be inserted repeatedly instead of updated. Using `md5`
as the `ID` of `point` to insert text can achieve true `update or
insert`.

Co-authored-by: mayue <mayue05@qiyi.com>
2023-04-24 21:39:51 -07:00
Jon Luo
b765805964
Support SQLAlchemy 2.0 (#3310)
With https://github.com/executablebooks/jupyter-cache/pull/93 merged and
`MyST-NB` updated, we can now support SQLAlchemy 2. Closes #1766
2023-04-24 21:10:56 -07:00
engkheng
7c2c73af5f
Update Getting Started page of Prompt Templates (#3298)
Updated `Getting Started` page of `Prompt Templates` to showcase more
features provided by the class. Might need some proof reading because
apparently English is not my first language.
2023-04-24 21:10:22 -07:00
Hasan Patel
a14d1c02f8
Updated Readme.md (#3477)
Corrected some minor grammar issues, changed infra to infrastructure for
more clarity. Improved readability
2023-04-24 20:11:29 -07:00
Davis Chase
b2564a6391
fix #3884 (#3475)
fixes mar bug #3384
2023-04-24 19:54:15 -07:00
Prakhar Agarwal
53b14de636
pass list of strings to embed method in tf_hub (#3284)
This fixes the below mentioned issue. Instead of simply passing the text
to `tensorflow_hub`, we convert it to a list and then pass it.
https://github.com/hwchase17/langchain/issues/3282

Co-authored-by: Prakhar Agarwal <i.prakhar-agarwal@devrev.ai>
2023-04-24 19:51:53 -07:00
Beau Horenberger
2b9f1cea4e
add LoRA loading for the LlamaCpp LLM (#3363)
First PR, let me know if this needs anything like unit tests,
reformatting, etc. Seemed pretty straightforward to implement. Only
hitch was that mmap needs to be disabled when loading LoRAs or else you
segfault.
2023-04-24 18:31:14 -07:00
Ehsan M. Kermani
5d0674fb46
Use a consistent poetry version everywhere (#3250)
Fixes the discrepancy of poetry version in Dockerfile and the GAs
2023-04-24 18:19:51 -07:00
Felipe Lopes
8c56e92566
feat: add private weaviate api_key support on from_texts (#3139)
This PR adds support for providing a Weaviate API Key to the VectorStore
methods `from_documents` and `from_texts`. With this addition, users can
authenticate to Weaviate and make requests to private Weaviate servers
when using these methods.

## Motivation
Currently, LangChain's VectorStore methods do not provide a way to
authenticate to Weaviate. This limits the functionality of the library
and makes it more difficult for users to take advantage of Weaviate's
features.

This PR addresses this issue by adding support for providing a Weaviate
API Key as extra parameter used in the `from_texts` method.

## Contributing Guidelines
I have read the [contributing
guidelines](72b7d76d79/.github/CONTRIBUTING.md)
and the PR code passes the following tests:

- [x] make format
- [x] make lint
- [x] make coverage
- [x] make test
2023-04-24 17:55:34 -07:00
Zzz233
239dc10852
ES similarity_search_with_score() and metadata filter (#3046)
Add similarity_search_with_score() to ElasticVectorSearch, add metadata
filter to both similarity_search() and similarity_search_with_score()
2023-04-24 17:20:08 -07:00
Zander Chase
416f3bdf11
Vwp/alpaca streaming (#3468)
Co-authored-by: Luke Stanley <306671+lukestanley@users.noreply.github.com>
2023-04-24 16:27:51 -07:00
Cao Hoang
26035dfa59
remove default usage of openai model in SQLDatabaseToolkit (#2884)
#2866

This toolkit used openai LLM as the default, which could incurr unwanted
cost.
2023-04-24 16:27:38 -07:00
Harrison Chase
675d86aa11
show how to use memory in convo chain (#3463) 2023-04-24 13:29:51 -07:00
leo-gan
d5086d4760
added integration links to the ecosystem.rst (#3453)
Now it is hard to search for the integration points between
data_loaders, retrievers, tools, etc.
I've placed links to all groups of providers and integrations on the
`ecosystem` page.
So, it is easy to navigate between all integrations from a single
location.
2023-04-24 12:17:44 -07:00
Davis Chase
2cbd41145c
Bugfix: Not all combine docs chains takes kwargs prompt (#3462)
Generalize ConversationalRetrievalChain.from_llm kwargs

---------

Co-authored-by: shubham.suneja <shubham.suneja>
2023-04-24 12:13:06 -07:00
cs0lar
3033c6b964
fixes #1214 (#3003)
### Background

Continuing to implement all the interface methods defined by the
`VectorStore` class. This PR pertains to implementation of the
`max_marginal_relevance_search_by_vector` method.

### Changes

- a `max_marginal_relevance_search_by_vector` method implementation has
been added in `weaviate.py`
- tests have been added to the the new method
- vcr cassettes have been added for the weaviate tests

### Test Plan

Added tests for the `max_marginal_relevance_search_by_vector`
implementation

### Change Safety

- [x] I have added tests to cover my changes
2023-04-24 11:50:55 -07:00
Harrison Chase
434d8c4c0e Merge branch 'master' of github.com:hwchase17/langchain 2023-04-24 11:30:14 -07:00
Harrison Chase
bdb5f2f9fb update notebook 2023-04-24 11:30:06 -07:00
Zander Chase
d06d47bc92
LM Requests Wrapper (#3457)
Co-authored-by: jnmarti <88381891+jnmarti@users.noreply.github.com>
2023-04-24 11:12:47 -07:00
Harrison Chase
b64c86a25f
bump version to 148 (#3458) 2023-04-24 11:08:32 -07:00
mbchang
82845e3821
add meta-prompt to autonomous agents use cases (#3254)
An implementation of
[meta-prompt](https://noahgoodman.substack.com/p/meta-prompt-a-simple-self-improving),
where the agent modifies its own instructions across episodes with a
user.

![figure](https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F468217b9-96d9-47c0-a08b-dbf6b21b9f49_492x384.png)
2023-04-24 10:48:38 -07:00
yunfeilu92
77235bbe43
propogate kwargs to cls in OpenSearchVectorSearch (#3416)
kwargs shoud be passed into cls so that opensearch client can be
properly initlized in __init__(). Otherwise logic like below will not
work. as auth will not be passed into __init__

```python
docsearch = OpenSearchVectorSearch.from_documents(docs, embeddings, opensearch_url="http://localhost:9200")

query = "What did the president say about Ketanji Brown Jackson"
docs = docsearch.similarity_search(query)
```

Co-authored-by: EC2 Default User <ec2-user@ip-172-31-28-97.ec2.internal>
2023-04-24 10:43:41 -07:00
Eduard van Valkenburg
46c9636012
small constructor change and updated notebook (#3426)
small change in the pydantic definitions, same api. 

updated notebook with right constructure and added few shot example
2023-04-24 10:42:38 -07:00
Zander Chase
49122a96e7
Structured Tool Bugfixes (#3324)
- Proactively raise error if a tool subclasses BaseTool, defines its
own schema, but fails to add the type-hints
- fix the auto-inferred schema of the decorator to strip the
unneeded virtual kwargs from the schema dict

Helps avoid silent instances of #3297
2023-04-24 09:58:29 -07:00