Commit Graph

379 Commits

Author SHA1 Message Date
Harrison Chase
40f6e60e68
Harrison/stripe (#3762)
Co-authored-by: Ismail Pelaseyed <homanp@gmail.com>
2023-04-28 20:03:21 -07:00
Rafal Wojdyla
160bfae93f
Add DocstoreFn - lookup doc via arbitrary function (#3760)
This **partially** addresses
https://github.com/hwchase17/langchain/issues/1524, but it's also useful
for some of our use cases.

This `DocstoreFn` allows to lookup a document given a function that
accepts the `search` string without the need to implement a custom
`Docstore`.

This could be useful when:
* you don't want to implement a `Docstore` just to provide a custom
`search`
 * it's expensive to construct an `InMemoryDocstore`/dict
 * you retrieve documents from remote sources
 * you just want to reuse existing objects
2023-04-28 19:50:32 -07:00
Zander Chase
5042bd40d3
Add Shell Tool (#3335)
Create an official bash shell tool to replace the dynamically generated one
2023-04-28 11:10:43 -07:00
Zander Chase
334c162f16
Add Other File Utilities (#3209)
Add other File Utilities, include
- List Directory
- Search for file
- Move
- Copy
- Remove file

Bundle as toolkit
Add a notebook that connects to the Chat Agent, which somewhat supports
multi-arg input tools
Update original read/write files to return the original dir paths and
better handle unsupported file paths.
Add unit tests
2023-04-28 10:53:37 -07:00
Zander Chase
da7b51455c
Dynamic tool -> single purpose (#3697)
I think the logic of
https://github.com/hwchase17/langchain/pull/3684#pullrequestreview-1405358565
is too confusing.

I prefer this alternative because:
- All `Tool()` implementations by default will be treated the same as
before. No breaking changes.
- Less reliance on pydantic magic
- The decorator (which only is typed as returning a callable) can infer
schema and generate a structured tool
- Either way, the recommended way to create a custom tool is through
inheriting from the base tool
2023-04-28 09:38:41 -07:00
Zander Chase
4654c58f72
Add validation on agent instantiation for multi-input tools (#3681)
Tradeoffs here:
- No lint-time checking for compatibility
- Differs from JS package
- The signature inference, etc. in the base tool isn't simple
- The `args_schema` is optional 

Pros:
- Forwards compatibility retained
- Doesn't break backwards compatibility
- User doesn't have to think about which class to subclass (single base
tool or dynamic `Tool` interface regardless of input)
-  No need to change the load_tools, etc. interfaces

Co-authored-by: Hasan Patel <mangafield@gmail.com>
2023-04-27 15:36:11 -07:00
Davis Chase
b807a114e4
Add query parsing unit tests (#3672) 2023-04-27 13:42:12 -07:00
Eugene Yurtsev
708787dddb
Blob: Add validator and use future annotations (#3650)
Minor changes to the Blob schema.

---------

Co-authored-by: Zander Chase <130414180+vowelparrot@users.noreply.github.com>
2023-04-27 14:33:59 -04:00
Eugene Yurtsev
c5a4b4fea1
Suppress duckdb warning in unit tests explicitly (#3653)
This catches the warning raised when using duckdb, asserts that it's as expected.

The goal is to resolve all existing warnings to make unit-testing much stricter.
2023-04-27 14:29:41 -04:00
Eugene Yurtsev
e6c8cce050
Add unit-test to catch changes to required deps (#3662)
This adds a unit test that can catch changes to required dependencies
2023-04-27 13:04:17 -04:00
Eugene Yurtsev
055f58960a
Fix pytest collection warning (#3651)
Fixes a pytest collection warning because the test class starts with the
prefix "Test"
2023-04-27 09:51:43 -07:00
plutopulp
6d6fd1b9e1
Add PipelineAI LLM integration (#3644)
Add PipelineAI LLM integration
2023-04-27 08:22:26 -07:00
Harrison Chase
a35bbbfa9e
Harrison/lancedb (#3634)
Co-authored-by: Minh Le <minhle@canva.com>
2023-04-27 08:14:36 -07:00
Eugene Yurtsev
5d02010763
Introduce Blob and Blob Loader interface (#3603)
This PR introduces a Blob data type and a Blob loader interface.

This is the first of a sequence of PRs that follows this proposal: 

https://github.com/hwchase17/langchain/pull/2833

The primary goals of these abstraction are:

* Decouple content loading from content parsing code.
* Help duplicated content loading code from document loaders.
* Make lazy loading a default for langchain.
2023-04-27 09:45:25 -04:00
Harrison Chase
ab749fa1bb
Harrison/opensearch logic (#3631)
Co-authored-by: engineer-matsuo <95115586+engineer-matsuo@users.noreply.github.com>
2023-04-26 22:08:03 -07:00
Ehsan M. Kermani
4a246e2fd6
Allow clearing cache and fix gptcache (#3493)
This PR

* Adds `clear` method for `BaseCache` and implements it for various
caches
* Adds the default `init_func=None` and fixes gptcache integtest
* Since right now integtest is not running in CI, I've verified the
changes by running `docs/modules/models/llms/examples/llm_caching.ipynb`
(until proper e2e integtest is done in CI)
2023-04-26 22:03:50 -07:00
cs0lar
440c98e24b
Fix/issue 2695 (#3608)
## Background
fixes #2695  

## Changes
The `add_text` method uses the internal embedding function if one was
passes to the `Weaviate` constructor.
NOTE: the latest merge on the `Weaviate` class made the specification of
a `weaviate_api_key` mandatory which might not be desirable for all
users and connection methods (for example weaviate also support Embedded
Weaviate which I am happy to add support to here if people think it's
desirable). I wrapped the fetching of the api key into a try catch in
order to allow the `weaviate_api_key` to be unspecified. Do let me know
if this is unsatisfactory.

## Test Plan
added test for `add_texts` method.
2023-04-26 21:45:03 -07:00
leo-gan
36c59e0c25
Arxiv document loader (#3627)
It makes sense to use `arxiv` as another source of the documents for
downloading.
- Added the `arxiv` document_loader, based on the
`utilities/arxiv.py:ArxivAPIWrapper`
- added tests
- added an example notebook
- sorted `__all__` in `__init__.py` (otherwise it is hard to find a
class in the very long list)
2023-04-26 21:04:56 -07:00
Zander Chase
443a893ffd
Align names of search tools (#3620)
Tools for Bing, DDG and Google weren't consistent even though the
underlying implementations were.
All three services now have the same tools and implementations to easily
switch and experiment when building chains.
2023-04-26 16:21:34 -07:00
Maciej Bryński
aa345a4bb7
Add get_text_separator parameter to BSHTMLLoader (#3551)
By default get_text doesn't separate content of different HTML tag.
Adding option for specifying separator helps with document splitting.
2023-04-26 16:10:16 -07:00
Zander Chase
ee670c448e
Persistent Bash Shell (#3580)
Clean up linting and make more idiomatic by using an output parser

---------

Co-authored-by: FergusFettes <fergusfettes@gmail.com>
2023-04-26 15:20:28 -07:00
Davis Chase
d18b0caf0e
Add Anthropic default request timeout (#3540)
thanks @hitflame!

---------

Co-authored-by: Wenqiang Zhao <hitzhaowenqiang@sina.com>
Co-authored-by: delta@com <delta@com>
2023-04-25 11:40:41 -07:00
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
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
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
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
408a0183cd
Harrison/weaviate (#3494)
Co-authored-by: Nick Rubell <nick@rubell.com>
2023-04-24 22:15:32 -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
Davis Chase
b2564a6391
fix #3884 (#3475)
fixes mar bug #3384
2023-04-24 19:54:15 -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
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
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
Davit Buniatyan
2c0023393b
Deep Lake mini upgrades (#3375)
Improvements
* set default num_workers for ingestion to 0
* upgraded notebooks for avoiding dataset creation ambiguity
* added `force_delete_dataset_by_path`
* bumped deeplake to 3.3.0
* creds arg passing to deeplake object that would allow custom S3

Notes
* please double check if poetry is not messed up (thanks!)

Asks
* Would be great to create a shared slack channel for quick questions

---------

Co-authored-by: Davit Buniatyan <d@activeloop.ai>
2023-04-23 21:23:54 -07:00
Zander Chase
20f530e9c5
Add Sentence Transformers Embeddings (#3409)
Add embeddings based on the sentence transformers library.
Add a notebook and integration tests.

Co-authored-by: khimaros <me@khimaros.com>
2023-04-23 18:25:20 -07:00
Luke Harris
b4de839ed8
Several confluence loader improvements (#3300)
This PR addresses several improvements:

- Previously it was not possible to load spaces of more than 100 pages.
The `limit` was being used both as an overall page limit *and* as a per
request pagination limit. This, in combination with the fact that
atlassian seem to use a server-side hard limit of 100 when page content
is expanded, meant it wasn't possible to download >100 pages. Now
`limit` is used *only* as a per-request pagination limit and `max_pages`
is introduced as the way to limit the total number of pages returned by
the paginator.
- Document metadata now includes `source` (the source url), making it
compatible with `RetrievalQAWithSourcesChain`.
 - It is now possible to include inline and footer comments.
- It is now possible to pass `verify_ssl=False` and other parameters to
the confluence object for use cases that require it.
2023-04-23 15:06:10 -07:00
Harrison Chase
a6664be79c
Harrison/myscale (#3352)
Co-authored-by: Fangrui Liu <fangruil@moqi.ai>
Co-authored-by: 刘 方瑞 <fangrui.liu@outlook.com>
Co-authored-by: Fangrui.Liu <fangrui.liu@ubc.ca>
2023-04-22 09:17:38 -07:00
Filip Haltmayer
215dcc2d26
Refactor Milvus/Zilliz (#3047)
Refactoring milvus/zilliz to clean up and have a more consistent
experience.

Signed-off-by: Filip Haltmayer <filip.haltmayer@zilliz.com>
2023-04-22 08:26:19 -07:00
Richy Wang
88a8f59aa7
Add a full PostgresSQL syntax database 'AnalyticDB' as vector store. (#3135)
Hi there!
I'm excited to open this PR to add support for using a fully Postgres
syntax compatible database 'AnalyticDB' as a vector.
As AnalyticDB has been proved can be used with AutoGPT,
ChatGPT-Retrieve-Plugin, and LLama-Index, I think it is also good for
you.
AnalyticDB is a distributed Alibaba Cloud-Native vector database. It
works better when data comes to large scale. The PR includes:

- [x]  A new memory: AnalyticDBVector
- [x]  A suite of integration tests verifies the AnalyticDB integration

I have read your [contributing
guidelines](72b7d76d79/.github/CONTRIBUTING.md).
And I have passed the tests below
- [x]  make format
- [x]  make lint
- [x]  make coverage
- [x]  make test
2023-04-22 08:25:41 -07:00
Zander Chase
05a8aa5447
Fix linting on master (#3327) 2023-04-21 15:49:46 -07:00
Varun Srinivas
d2f922f525
Change in method name for creating an issue on JIRA (#3307)
The awesome JIRA tool created by @zywilliamli calls the `create_issue()`
method to create issues, however, the actual method is `issue_create()`.

Details in the Documentation here:
https://atlassian-python-api.readthedocs.io/jira.html#manage-issues
2023-04-21 13:01:33 -07:00
Paul Garner
aa9d5707e0
Add PythonLoader which auto-detects encoding of Python files (#3311)
This PR contributes a `PythonLoader`, which inherits from
`TextLoader` but detects and sets the encoding automatically.
2023-04-21 10:47:57 -07:00
Davis Chase
2fd24d31a4
Cleanup integration test dir (#3308) 2023-04-21 09:44:09 -07:00
Naveen Tatikonda
bb6c459f7a
OpenSearch: Add Support for Lucene Filter (#3201)
### Description
Add Support for Lucene Filter. When you specify a Lucene filter for a
k-NN search, the Lucene algorithm decides whether to perform an exact
k-NN search with pre-filtering or an approximate search with modified
post-filtering. This filter is supported only for approximate search
with the indexes that are created using `lucene` engine.

OpenSearch Documentation -
https://opensearch.org/docs/latest/search-plugins/knn/filter-search-knn/#lucene-k-nn-filter-implementation

Signed-off-by: Naveen Tatikonda <navtat@amazon.com>
2023-04-20 20:42:53 -07:00
Davis Chase
46542dc774
Contextual compression retriever (#2915)
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-04-20 17:01:14 -07:00
Gabriel Altay
34fb56b633
fix copy/pasta typos wikipedia->arxiv (#3222)
just updates a few module level docstrings from Wikipedia -> Arxiv
2023-04-20 07:15:41 -07:00
Harrison Chase
d2520a5f1e
Harrison/ddg (#3206)
Co-authored-by: itai <itai.marks@gmail.com>
Co-authored-by: Itai Marks <itaim@users.noreply.github.com>
Co-authored-by: Tianyi Pan <60060750+tipani86@users.noreply.github.com>
Co-authored-by: Tianyi Pan <tianyi.pan@clobotics.com>
Co-authored-by: Adilzhan Ismailov <13088690+aismlv@users.noreply.github.com>
Co-authored-by: Justin Flick <Justinjayflick@gmail.com>
Co-authored-by: Justin Flick <jflick@homesite.com>
2023-04-19 21:32:26 -07:00
Harrison Chase
9a0356d276
Harrison/file chat history (#3198)
Co-authored-by: Young Lee <joybro201@gmail.com>
2023-04-19 21:05:20 -07:00
Harrison Chase
9181cd9b22
Harrison/playwright selector (#3185)
Co-authored-by: zhyuri <4649294+zhyuri@users.noreply.github.com>
2023-04-19 16:54:15 -07:00
Harrison Chase
68cd37175e
Harrison/arxiv tool (#3186)
Co-authored-by: leo-gan <leo.gan.57@gmail.com>
2023-04-19 16:53:34 -07:00
Zander Chase
4adfd790f0
Update File Management Tools to Include Root Directory (#3112)
- Permit the specification of a `root_dir` to the read/write file tools
to specify a working directory
- Add validation for attempts to read/write outside the directory (e.g.,
through `../../` or symlinks or `/abs/path`'s that don't lie in the
correct path)
- Add some tests for all


One question is whether we should make a default root directory for
these? tradeoffs either way
2023-04-19 16:46:10 -07:00
engkheng
dbbc340f25
Validate input_variables when using jinja2 templates (#3140)
`langchain.prompts.PromptTemplate` and
`langchain.prompts.FewShotPromptTemplate` do not validate
`input_variables` when initialized as `jinja2` template.

```python
# Using langchain v0.0.144
template = """"\
Your variable: {{ foo }}
{% if bar %}
You just set bar boolean variable to true
{% endif %}
"""

# Missing variable, should raise ValueError
prompt_template = PromptTemplate(template=template, 
                                 input_variables=["bar"], 
                                 template_format="jinja2", 
                                 validate_template=True)

# Extra variable, should raise ValueError
prompt_template = PromptTemplate(template=template, 
                                 input_variables=["bar", "foo", "extra", "thing"], 
                                 template_format="jinja2", 
                                 validate_template=True)
```
2023-04-19 16:18:32 -07:00
Zander Chase
90ef705ced
Update Tool Input (#3103)
- Remove dynamic model creation in the `args()` property. _Only infer
for the decorator (and add an argument to NOT infer if someone wishes to
only pass as a string)_
- Update the validation example to make it less likely to be
misinterpreted as a "safe" way to run a repl


There is one example of "Multi-argument tools" in the custom_tools.ipynb
from yesterday, but we could add more. The output parsing for the base
MRKL agent hasn't been adapted to handle structured args at this point
in time

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-04-18 18:18:33 -07:00
Harrison Chase
aad0a498ac
Harrison/output error (#3094)
Co-authored-by: yummydum <sumita@nowcast.co.jp>
2023-04-18 08:59:56 -07:00
Harrison Chase
db968284f8
tools refactor (#2961)
Co-authored-by: vowelparrot <130414180+vowelparrot@users.noreply.github.com>
2023-04-17 21:35:29 -07:00
engkheng
19febc77d6
Support inference of input_variables from jinja2 template (#3013)
`langchain.prompts.PromptTemplate` is unable to infer `input_variables`
from jinja2 template.

```python
# Using langchain v0.0.141
template_string = """\
Hello world
Your variable: {{ var }}
{# This will not get rendered #}

{% if verbose %}
Congrats! You just turned on verbose mode and got extra messages!
{% endif %}
"""

template = PromptTemplate.from_template(template_string, template_format="jinja2")
print(template.input_variables) # Output ['# This will not get rendered #', '% endif %', '% if verbose %']
```

---------

Co-authored-by: engkheng <ongengkheng929@example.com>
2023-04-17 20:31:03 -07:00
Nuno Campos
dac32c59e5
Nc/combining output parser (#3014)
Co-authored-by: vowelparrot <130414180+vowelparrot@users.noreply.github.com>
2023-04-17 20:29:53 -07:00
Davis Chase
19c85aa990
Factor out doc formatting and add validation (#3026)
@cnhhoang850 slightly more generic fix for #2944, works for whatever the
expected metadata keys are not just `source`
2023-04-17 20:28:01 -07:00
Naveen Tatikonda
3453b7457c
OpenSearch: Add Support for Boolean Filter with ANN search (#3038)
### Description
Add Support for Boolean Filter with ANN search
Documentation -
https://opensearch.org/docs/latest/search-plugins/knn/filter-search-knn/#boolean-filter-with-ann-search

### Issues Resolved
https://github.com/hwchase17/langchain/issues/2924

Signed-off-by: Naveen Tatikonda <navtat@amazon.com>
2023-04-17 20:26:26 -07:00
Harrison Chase
afd3e70ae5
Harrison/confluent loader (#2994)
Co-authored-by: Justin Flick <Justinjayflick@gmail.com>
2023-04-17 20:23:45 -07:00
vowelparrot
99c0382209
Generative Characters (#2859)
Add a time-weighted memory retriever and a notebook that approximates a
Generative Agent from https://arxiv.org/pdf/2304.03442.pdf


The "daily plan" components are removed for now since they are less
useful without a virtual world, but the memory is an interesting
component to build off.

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-04-16 21:41:00 -07:00
Jan Backes
a9310a3e8b
Add Annoy as VectorStore (#2939)
Adds Annoy (https://github.com/spotify/annoy) as vector Store. 

RESOLVES hwchase17/langchain#2842

discord ref:
https://discord.com/channels/1038097195422978059/1051632794427723827/1096089994168377354

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: vowelparrot <130414180+vowelparrot@users.noreply.github.com>
2023-04-16 13:44:04 -07:00
Harrison Chase
e12e00df12
use output parsers in agents (#2987) 2023-04-16 13:15:21 -07:00
cs0lar
8b9e02da9d
Fix/issue 1213 (#2932)
### Background

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

### Changes

- a `max_marginal_relevance_search` 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` implementation

### Change Safety

- [x] I have added tests to cover my changes
2023-04-16 13:11:30 -07:00
vowelparrot
5ca7ce77cd
Remove pythonrepl from LLM-MathChain (#2943)
Use numexpr evaluate instead of the python REPL to avoid malicious code
injection.

Tested against the (limited) math dataset and got the same score as
before.

For more permissive tools (like the REPL tool itself), other approaches
ought to be provided (some combination of Sanitizer + Restricted python
+ unprivileged-docker + ...), but for a calculator tool, only
mathematical expressions should be permitted.

See https://github.com/hwchase17/langchain/issues/814
2023-04-16 08:50:32 -07:00
vowelparrot
4ffc58e07b
Add similarity_search_with_normalized_similarities (#2916)
Add a method that exposes a similarity search with corresponding
normalized similarity scores. Implement only for FAISS now.

### Motivation:

Some memory definitions combine `relevance` with other scores, like
recency , importance, etc.

While many (but not all) of the `VectorStore`'s expose a
`similarity_search_with_score` method, they don't all interpret the
units of that score (depends on the distance metric and whether or not
the the embeddings are normalized).

This PR proposes a `similarity_search_with_normalized_similarities`
method that lets consumers of the vector store not have to worry about
the metric and embedding scale.

*Most providers default to euclidean distance, with Pinecone being one
exception (defaults to cosine _similarity_).*

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-04-15 21:06:08 -07:00
dev2049
36aa7f30e4
Move PythonRepl -> langchain.utilities (#2917) 2023-04-15 10:50:25 -07:00
Davit Buniatyan
b3a5b51728
[minor] Deep Lake auth improvements in docs, kwargs pass, faster tests (#2927)
Minor cosmetic changes 
- Activeloop environment cred authentication in notebooks with
`getpass.getpass` (instead of CLI which not always works)
- much faster tests with Deep Lake pytest mode on 
- Deep Lake kwargs pass

Notes
- I put pytest environment creds inside `vectorstores/conftest.py`, but
feel free to suggest a better location. For context, if I put in
`test_deeplake.py`, `ruff` doesn't let me to set them before import
deeplake

---------

Co-authored-by: Davit Buniatyan <d@activeloop.ai>
2023-04-15 10:49:16 -07:00
Ankush Gola
ec59e9d886
Fix ChatAnthropic stop_sequences error (#2919) (#2920)
Note to self: Always run integration tests, even on "that last minute
change you thought would be safe" :)

---------

Co-authored-by: Mike Lambert <mike.lambert@anthropic.com>
2023-04-14 17:22:01 -07:00
Mike Lambert
392f1b3218
Add Anthropic ChatModel to langchain (#2293)
* Adds an Anthropic ChatModel
* Factors out common code in our LLMModel and ChatModel
* Supports streaming llm-tokens to the callbacks on a delta basis (until
a future V2 API does that for us)
* Some fixes
2023-04-14 15:09:07 -07:00
Harrison Chase
1e9378d0a8
Harrison/weaviate fixes (#2872)
Co-authored-by: cs0lar <cristiano.solarino@gmail.com>
Co-authored-by: cs0lar <cristiano.solarino@brightminded.com>
2023-04-13 22:37:34 -07:00
Harrison Chase
705596b46a
Harrison/fix create sql agent (#2870)
Co-authored-by: Timothé Pearce <timothe.pearce@gmail.com>
2023-04-13 22:07:58 -07:00
sergerdn
04c458a270
feat: improve pinecone tests (#2806)
Improve the integration tests for Pinecone by adding an `.env.example`
file for local testing. Additionally, add some dev dependencies
specifically for integration tests.

This change also helps me understand how Pinecone deals with certain
things, see related issues
https://github.com/hwchase17/langchain/issues/2484
https://github.com/hwchase17/langchain/issues/2816
2023-04-13 21:49:31 -07:00
vowelparrot
bf0887c486
Add Slack Directory Loader (#2841)
Fixes linting issue from #2835 

Adds a loader for Slack Exports which can be a very valuable source of
knowledge to use for internal QA bots and other use cases.

```py
# Export data from your Slack Workspace first.
from langchain.document_loaders import SLackDirectoryLoader

SLACK_WORKSPACE_URL = "https://awesome.slack.com"

loader = ("Slack_Exports", SLACK_WORKSPACE_URL)
docs = loader.load()
```
2023-04-13 21:31:59 -07:00
Tim Asp
be4fb24b32
OpenAI LLM: update modelname_to_contextsize with new models (#2843)
Token counts pulled from https://openai.com/pricing
2023-04-13 11:13:34 -07:00
KullTC
802363eb6a
Remove print statement from test (#2809)
Remove unnecessary print statement.
2023-04-13 09:31:48 -07:00
KullTC
64596b23b9
Return output of PythonAstREPLTool when falling back to exec() (#2780)
When the code ran by the PythonAstREPLTool contains multiple statements
it will fallback to exec() instead of using eval(). With this change, it
will also return the output of the code in the same way the
PythonREPLTool will.
2023-04-12 21:22:46 -07:00
Harrison Chase
e49f1e628c
Harrison/gpt cache (#2744)
Co-authored-by: SimFG <bang.fu@zilliz.com>
2023-04-12 14:16:58 -07:00
Joshua Snyder
59d054308c
Add type inference for output parsers (#2769)
Currently, the output type of a number of OutputParser's `parse` methods
is `Any` when it can in fact be inferred.

This PR makes BaseOutputParser use a generic type and fixes the output
types of the following parsers:
- `PydanticOutputParser`
- `OutputFixingParser`
- `RetryOutputParser`
- `RetryWithErrorOutputParser`

The output of the `StructuredOutputParser` is corrected from `BaseModel`
to `Any` since there are no type guarantees provided by the parser.

Fixes issue #2715
2023-04-12 09:12:20 -07:00
Johnny Lee
0ab364404e
add continue to fix 'continue_on_failure' parameter for URL doc loader (#2735)
Currently, the function still fails if `continue_on_failure` is set to
True, because `elements` is not set.

---------

Co-authored-by: leecjohnny <johnny-lee1255@users.noreply.github.com>
2023-04-11 21:12:39 -07:00
sergerdn
4bdcedab54
fix: some imports for integration tests (#2612)
Add more missed imports for integration tests. Bump `pytest` to the
current latest version.
Fix `tests/integration_tests/vectorstores/test_elasticsearch.py` to
update its cassette(easy fix).

Related PR: https://github.com/hwchase17/langchain/pull/2560
2023-04-11 20:45:36 -07:00
Ankush Gola
c1521ddbdb
Add workaround for not having async vector store methods (#2733)
This allows us to use the async API for the Retrieval chains, though it is not guaranteed to be thread safe.
2023-04-11 18:49:08 -07:00
vowelparrot
709f26b69e
Added bilibili loader (#2673) (#2724)
I've added a bilibili loader, bilibili is a very active video site in
China and I think we need this loader.

Example:
```python
from langchain.document_loaders.bilibili import BiliBiliLoader

loader = BiliBiliLoader(
       ["https://www.bilibili.com/video/BV1xt411o7Xu/",
       "https://www.bilibili.com/video/av330407025/"]
)
docs = loader.load()
```

Co-authored-by: 了空 <568250549@qq.com>
2023-04-11 10:40:32 -07:00
Abhik Singla
955bd2e1db
Fixed Ast Python Repl for Chatgpt multiline commands (#2406)
Resolves issue https://github.com/hwchase17/langchain/issues/2252

---------

Co-authored-by: Abhik Singla <abhiksingla@microsoft.com>
2023-04-10 21:25:03 -07:00
Naveen Tatikonda
4364d3316e
Add custom vector fields and text fields for OpenSearch (#2652)
**Description**
Add custom vector field name and text field name while indexing and
querying for OpenSearch

**Issues**
https://github.com/hwchase17/langchain/issues/2500

Signed-off-by: Naveen Tatikonda <navtat@amazon.com>
2023-04-10 21:02:02 -07:00
Ankush Gola
b82cbd1be0
Use run and arun in place of combine_docs and acombine_docs (#2635)
`combine_docs` does not go through the standard chain call path which
means that chain callbacks won't be triggered, meaning QA chains won't
be traced properly, this fixes that.

Also fix several errors in the chat_vector_db notebook
2023-04-09 18:47:59 -07:00
Chetanya Rastogi
50c511d75f
Add new loader to load pdf as html content (#2607)
Adds a new pdf loader using the existing dependency on PDFMiner. 

The new loader can be helpful for chunking texts semantically into
sections as the output html content can be parsed via `BeautifulSoup` to
get more structured and rich information about font size, page numbers,
pdf headers/footers, etc. which may not be available otherwise with
other pdf loaders
2023-04-09 17:57:25 -07:00
sergerdn
cd9336469e
fix: missed deps integrations tests (#2560)
Almost all integration tests have failed, but we haven't encountered any
import errors yet. Some tests failed due to lazy import issues. It
doesn't seem like a problem to resolve some of these errors in the next
PR.
I have a headache from resolving conflicts with `deeplake` and `boto3`,
so I will temporarily comment out `boto3`.


fix https://github.com/hwchase17/langchain/issues/2426
2023-04-07 20:43:53 -07:00
sergerdn
6dc86ad48f
feat: add pytest-vcr for recording HTTP interactions in integration tests (#2445)
Using `pytest-vcr` in integration tests has several benefits. Firstly,
it removes the need to mock external services, as VCR records and
replays HTTP interactions on the fly. Secondly, it simplifies the
integration test setup by eliminating the need to set up and tear down
external services in some cases. Finally, it allows for more reliable
and deterministic integration tests by ensuring that HTTP interactions
are always replayed with the same response.
Overall, `pytest-vcr` is a valuable tool for simplifying integration
test setup and improving their reliability

This commit adds the `pytest-vcr` package as a dependency for
integration tests in the `pyproject.toml` file. It also introduces two
new fixtures in `tests/integration_tests/conftest.py` files for managing
cassette directories and VCR configurations.

In addition, the
`tests/integration_tests/vectorstores/test_elasticsearch.py` file has
been updated to use the `@pytest.mark.vcr` decorator for recording and
replaying HTTP interactions.

Finally, this commit removes the `documents` fixture from the
`test_elasticsearch.py` file and replaces it with a new fixture defined
in `tests/integration_tests/vectorstores/conftest.py` that yields a list
of documents to use in any other tests.

This also includes my second attempt to fix issue :
https://github.com/hwchase17/langchain/issues/2386

Maybe related https://github.com/hwchase17/langchain/issues/2484
2023-04-07 07:28:57 -07:00
Vashisht Madhavan
aa439ac2ff
Adding an in-context QA evaluation chain + chain of thought reasoning chain for improved accuracy (#2444)
Right now, eval chains require an answer for every question. It's
cumbersome to collect this ground truth so getting around this issue
with 2 things:

* Adding a context param in `ContextQAEvalChain` and simply evaluating
if the question is answered accurately from context
* Adding chain of though explanation prompting to improve the accuracy
of this w/o GT.

This also gets to feature parity with openai/evals which has the same
contextual eval w/o GT.

TODO in follow-up:
* Better prompt inheritance. No need for seperate prompt for CoT
reasoning. How can we merge them together

---------

Co-authored-by: Vashisht Madhavan <vashishtmadhavan@Vashs-MacBook-Pro.local>
2023-04-06 22:32:41 -07:00
Alex Rad
bd780a8223
Add support for rwkv (#2422)
This adds support for running RWKV with pytorch. 

https://github.com/hwchase17/langchain/issues/2398

This does not yet support  rwkv.cpp
2023-04-06 14:41:06 -07:00
William FH
f240651bd8
Add Request body (#2507)
This still doesn't handle the following

- non-JSON media types
- anyOf, allOf, oneOf's

And doesn't emit the typescript definitions for referred types yet, but
that can be saved for a separate PR.

Also, we could have better support for Swagger 2.0 specs and OpenAPI
3.0.3 (can use the same lib for the latter) recommend offline conversion
for now.
2023-04-06 13:02:42 -07:00
Zach Jones
13d1df2140
Feature: AgentExecutor execution time limit (#2399)
`AgentExecutor` already has support for limiting the number of
iterations. But the amount of time taken for each iteration can vary
quite a bit, so it is difficult to place limits on the execution time.
This PR adds a new field `max_execution_time` to the `AgentExecutor`
model. When called asynchronously, the agent loop is wrapped in an
`asyncio.timeout()` context which triggers the early stopping response
if the time limit is reached. When called synchronously, the agent loop
checks for both the max_iteration limit and the time limit after each
iteration.

When used asynchronously `max_execution_time` gives really tight control
over the max time for an execution chain. When used synchronously, the
chain can unfortunately exceed max_execution_time, but it still gives
more control than trying to estimate the number of max_iterations needed
to cap the execution time.

---------

Co-authored-by: Zachary Jones <zjones@zetaglobal.com>
2023-04-06 12:54:32 -07:00
Davit Buniatyan
b4914888a7
Deep Lake upgrade to include attribute search, distance metrics, returning scores and MMR (#2455)
### Features include

- Metadata based embedding search
- Choice of distance metric function (`L2` for Euclidean, `L1` for
Nuclear, `max` L-infinity distance, `cos` for cosine similarity, 'dot'
for dot product. Defaults to `L2`
- Returning scores
- Max Marginal Relevance Search
- Deleting samples from the dataset

### Notes
- Added numerous tests, let me know if you would like to shorten them or
make smarter

---------

Co-authored-by: Davit Buniatyan <d@activeloop.ai>
2023-04-06 12:47:33 -07:00
leo-gan
fd69cc7e42
Removed duplicate BaseModel dependencies (#2471)
Removed duplicate BaseModel dependencies in class inheritances.
Also, sorted imports by `isort`.
2023-04-06 12:45:16 -07:00
Harrison Chase
1e19e004af
Harrison/openapi spec (#2474)
Co-authored-by: William Fu-Hinthorn <13333726+hinthornw@users.noreply.github.com>
2023-04-06 09:47:37 -07:00
Harrison Chase
26314d7004
Harrison/openapi parser (#2461)
Co-authored-by: William FH <13333726+hinthornw@users.noreply.github.com>
2023-04-05 22:19:09 -07:00
William FH
007babb363
Add a mock server (#2443)
It's useful to evaluate API Chains against a mock server. This PR makes
an example "robot" server that exposes endpoints for the following:
- Path, Query, and Request Body argument passing
- GET, PUT, and DELETE endpoints exposed OpenAPI spec.


Relies on FastAPI + Uvicorn - I could add to the dev dependencies list
if you'd like
2023-04-05 10:35:46 -07:00
sergerdn
b410dc76aa
fix: elasticsearch (#2402)
- Create a new docker-compose file to start an Elasticsearch instance
for integration tests.
- Add new tests to `test_elasticsearch.py` to verify Elasticsearch
functionality.
- Include an optional group `test_integration` in the `pyproject.toml`
file. This group should contain dependencies for integration tests and
can be installed using the command `poetry install --with
test_integration`. Any new dependencies should be added by running
`poetry add some_new_deps --group "test_integration" `

Note:
New tests running in live mode, which involve end-to-end testing of the
OpenAI API. In the future, adding `pytest-vcr` to record and replay all
API requests would be a nice feature for testing process.More info:
https://pytest-vcr.readthedocs.io/en/latest/

Fixes https://github.com/hwchase17/langchain/issues/2386
2023-04-05 06:51:32 -07:00