Commit Graph

145 Commits

Author SHA1 Message Date
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
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
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
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
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
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
Ankush Gola
4d730a9bbc
improve AsyncCallbackManager (#2410) 2023-04-05 09:31:42 +02:00
Harrison Chase
c7b083ab56
bump version to 131 (#2391) 2023-04-04 07:21:50 -07:00
Harrison Chase
fe1eb8ca5f
requests wrapper (#2367) 2023-04-03 21:57:19 -07:00
Shrined
10dab053b4
Add Enum for agent types (#2321)
This pull request adds an enum class for the various types of agents
used in the project, located in the `agent_types.py` file. Currently,
the project is using hardcoded strings for the initialization of these
agents, which can lead to errors and make the code harder to maintain.
With the introduction of the new enums, the code will be more readable
and less error-prone.

The new enum members include:

- ZERO_SHOT_REACT_DESCRIPTION
- REACT_DOCSTORE
- SELF_ASK_WITH_SEARCH
- CONVERSATIONAL_REACT_DESCRIPTION
- CHAT_ZERO_SHOT_REACT_DESCRIPTION
- CHAT_CONVERSATIONAL_REACT_DESCRIPTION

In this PR, I have also replaced the hardcoded strings with the
appropriate enum members throughout the codebase, ensuring a smooth
transition to the new approach.
2023-04-03 21:56:20 -07:00
Harrison Chase
acfda4d1d8
Harrison/multiline commands (#2280)
Co-authored-by: Marc Päpper <mpaepper@users.noreply.github.com>
2023-04-01 12:54:06 -07:00
leo-gan
579ad85785
skip unit tests that fail in Windows (#2238)
Issue #2174
Several unit tests fail in Windows.
Added pytest attribute to skip these tests automatically.
2023-04-01 12:52:21 -07:00
Harrison Chase
2d3918c152
make requests more general (#2209) 2023-03-30 20:41:56 -07:00
Harrison Chase
5c907d9998
Harrison/base agent without docs (#2166) 2023-03-29 22:11:25 -07:00
Harrison Chase
f5a4bf0ce4
remove prep (#2136)
agents should be stateless or async stuff may not work
2023-03-29 14:38:21 -07:00
Harrison Chase
e2c26909f2
Harrison/memory check (#2119)
Co-authored-by: JIAQIA <jqq1716@gmail.com>
2023-03-28 15:40:36 -07:00
Harrison Chase
f281033362
rm pandas dependency (#2102) 2023-03-28 08:38:19 -07:00
Harrison Chase
9e74df2404
Fix issue#1645: Parse llm_output even there's newline (#2092) (#2099)
Fix issue#1645: Parse either whitespace or newline after 'Action Input:'
in llm_output in mrkl agent.
Unittests added accordingly.

Co-authored-by: ₿ingnan.ΞTH <brillliantz@outlook.com>
2023-03-28 08:14:09 -07:00
b7f392fdd6
[agent_executor] convenience func: lookup tool by name (#2001)
A quick convenience function to lookup a tool by name

Co-authored-by: blob42 <spike@w530>
2023-03-27 23:10:34 -07:00
Harrison Chase
30e3b31b04
Harrison/document cleanup (#2062)
Co-authored-by: Delip Rao <delip@users.noreply.github.com>
2023-03-27 16:32:55 -07:00
Daniel Chalef
6598beacdb
PydanticOutputParser unit test (#2047)
Unit test for PydanticOutputParser

---------

Co-authored-by: Daniel Chalef <daniel.chalef@private.org>
2023-03-27 14:32:56 -07:00
Harrison Chase
705431aecc
big docs refactor (#1978)
Co-authored-by: Ankush Gola <ankush.gola@gmail.com>
2023-03-26 19:49:46 -07:00
Harrison Chase
ce5d97bcb3
Harrison/guarded output parser (#1804)
Co-authored-by: jerwelborn <jeremy.welborn@gmail.com>
2023-03-21 22:07:23 -07:00
Matt Tucker
a92344f476
Use regex match for bash process error output test assertion. (#1837)
I was getting the same issue reported in #1339 by
[MacYang555](https://github.com/MacYang555) when running the test suite
on my Mac. I implemented the fix they suggested to use a regex match in
the output assertion for the scenario under test.

Resolves #1339
2023-03-21 09:06:52 -07:00
Jon Luo
0a1b1806e9
sql: do not hard code the LIMIT clause in the table_info section (#1563)
Seeing a lot of issues in Discord in which the LLM is not using the
correct LIMIT clause for different SQL dialects. ie, it's using `LIMIT`
for mssql instead of `TOP`, or instead of `ROWNUM` for Oracle, etc.
I think this could be due to us specifying the LIMIT statement in the
example rows portion of `table_info`. So the LLM is seeing the `LIMIT`
statement used in the prompt.
Since we can't specify each dialect's method here, I think it's fine to
just replace the `SELECT... LIMIT 3;` statement with `3 rows from
table_name table:`, and wrap everything in a block comment directly
following the `CREATE` statement. The Rajkumar et al paper wrapped the
example rows and `SELECT` statement in a block comment as well anyway.
Thoughts @fpingham?
2023-03-13 23:08:27 -07:00
Luis
562d9891ea
Add regex dict: (#1616)
This class enables us to send a dictionary containing an output key and
the expected format, which in turn allows us to retrieve the result of
the matching formats and extract specific information from it.

To exclude irrelevant information from our return dictionary, we can
prompt the LLM to use a specific command that notifies us when it
doesn't know the answer. We refer to this variable as the
"no_update_value".

Regarding the updated regular expression pattern
(r"{}:\s?([^.'\n']*).?"), it enables us to retrieve a format as 'Output
Key':'value'.

We have improved the regex by adding an optional space between ':' and
'value' with "s?", and by excluding points and line jumps from the
matches using "[^.'\n']*".
2023-03-13 23:05:39 -07:00
Harrison Chase
aed9f9febe
Harrison/return intermediate (#1633)
Co-authored-by: Mario Kostelac <mario@intercom.io>
2023-03-13 07:54:29 -07:00
yakigac
acd86d33bc
Add read only shared memory (#1491)
Provide shared memory capability for the Agent.
Inspired by #1293 .

## Problem

If both Agent and Tools (i.e., LLMChain) use the same memory, both of
them will save the context. It can be annoying in some cases.


## Solution

Create a memory wrapper that ignores the save and clear, thereby
preventing updates from Agent or Tools.
2023-03-12 09:34:36 -07:00
Harrison Chase
c9b5a30b37
move output parsing (#1605) 2023-03-11 16:41:03 -08:00
Harrison Chase
f95d551f7a
Harrison/shallow metadata (#1599)
Co-authored-by: Jesse Zhang <jessetanzhang@gmail.com>
2023-03-11 09:18:25 -08:00
Harrison Chase
9f78717b3c
Harrison/callbacks (#1587) 2023-03-10 12:53:09 -08:00
Harrison Chase
cc423f40f1
Harrison/youtube loader (#1545)
Co-authored-by: Julian Wustl <57504258+Julianwustl@users.noreply.github.com>
2023-03-08 20:53:27 -08:00
Harrison Chase
7ade419a0e
allow passing of messages into prompt template (#1505) 2023-03-07 21:10:12 -08:00
Harrison Chase
064741db58
Harrison/fix text splitter (#1511)
Co-authored-by: ajaysolanky <ajsolanky@gmail.com>
Co-authored-by: Ajay Solanky <ajaysolanky@saw-l14668307kd.myfiosgateway.com>
2023-03-07 15:42:28 -08:00
Harrison Chase
7bec461782
Harrison/memory refactor (#1478)
moves memory to own module, factors out common stuff
2023-03-07 07:59:37 -08:00
Harrison Chase
0e21463f07
(rfc) chat models (#1424)
Co-authored-by: Ankush Gola <ankush.gola@gmail.com>
2023-03-06 08:34:24 -08:00
Harrison Chase
63a5614d23
Harrison/simple memory (#1435)
Co-authored-by: Tim Asp <707699+timothyasp@users.noreply.github.com>
2023-03-04 08:15:52 -08:00
Harrison Chase
1cd8996074
Harrison/summarizer chain (#1356)
Co-authored-by: Tim Asp <707699+timothyasp@users.noreply.github.com>
2023-03-01 20:59:07 -08:00
Ankush Gola
82baecc892
Add a SQL agent for interacting with SQL Databases and JSON Agent for interacting with large JSON blobs (#1150)
This PR adds 

* `ZeroShotAgent.as_sql_agent`, which returns an agent for interacting
with a sql database. This builds off of `SQLDatabaseChain`. The main
advantages are 1) answering general questions about the db, 2) access to
a tool for double checking queries, and 3) recovering from errors
* `ZeroShotAgent.as_json_agent` which returns an agent for interacting
with json blobs.
* Several examples in notebooks

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-02-28 19:44:39 -08:00
Harrison Chase
786852e9e6
partial variables (#1308) 2023-02-28 08:40:35 -08:00
Harrison Chase
b7708bbec6
rfc: callback changes (#1165)
conceptually, no reason a tool should know what an "agent action" is

unless any objections, can change in all callback handlers
2023-02-20 22:54:15 -08:00
CG80499
af8f5c1a49
Added constitutional chain. (#1147)
- Added self-critique constitutional chain based on this
[paper](https://www.anthropic.com/constitutional.pdf).
2023-02-18 19:31:51 -08:00
Ankush Gola
7b5e160d28
Make Tools own model, add ToolKit Concept (#1095)
Follow-up of @hinthornw's PR:

- Migrate the Tool abstraction to a separate file (`BaseTool`).
- `Tool` implementation of `BaseTool` takes in function and coroutine to
more easily maintain backwards compatibility
- Add a Toolkit abstraction that can own the generation of tools around
a shared concept or state

---------

Co-authored-by: William FH <13333726+hinthornw@users.noreply.github.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Francisco Ingham <fpingham@gmail.com>
Co-authored-by: Dhruv Anand <105786647+dhruv-anand-aintech@users.noreply.github.com>
Co-authored-by: cragwolfe <cragcw@gmail.com>
Co-authored-by: Anton Troynikov <atroyn@users.noreply.github.com>
Co-authored-by: Oliver Klingefjord <oliver@klingefjord.com>
Co-authored-by: William Fu-Hinthorn <whinthorn@Williams-MBP-3.attlocal.net>
Co-authored-by: Bruno Bornsztein <bruno.bornsztein@gmail.com>
2023-02-18 13:40:43 -08:00
Francisco Ingham
3f29742adc
Sql alchemy commands used in table info (#1135)
This approach has several advantages:

* it improves the readability of the code
* removes incompatibilities between SQL dialects
* fixes a bug with `datetime` values in rows and `ast.literal_eval`

Huge thanks and credits to @jzluo for finding the weaknesses in the
current approach and for the thoughtful discussion on the best way to
implement this.

---------

Co-authored-by: Francisco Ingham <>
Co-authored-by: Jon Luo <20971593+jzluo@users.noreply.github.com>
2023-02-18 10:58:29 -08:00
Harrison Chase
5e10e19bfe
Harrison/align table (#1081)
Co-authored-by: Francisco Ingham <fpingham@gmail.com>
2023-02-15 23:53:37 -08:00
Ankush Gola
caa8e4742e
Enable streaming for OpenAI LLM (#986)
* Support a callback `on_llm_new_token` that users can implement when
`OpenAI.streaming` is set to `True`
2023-02-14 15:06:14 -08:00
Harrison Chase
ec727bf166
Align table info (#999) (#1034)
Currently the chain is getting the column names and types on the one
side and the example rows on the other. It is easier for the llm to read
the table information if the column name and examples are shown together
so that it can easily understand to which columns do the examples refer
to. For an instantiation of this, please refer to the changes in the
`sqlite.ipynb` notebook.

Also changed `eval` for `ast.literal_eval` when interpreting the results
from the sample row query since it is a better practice.

---------

Co-authored-by: Francisco Ingham <>

---------

Co-authored-by: Francisco Ingham <fpingham@gmail.com>
2023-02-13 21:48:41 -08:00