Harrison Chase
52490e2dcd
add explicit agent end method ( #486 )
2022-12-29 22:23:15 -05:00
Harrison Chase
7e36f28e78
Harrison/not verbose ( #487 )
2022-12-29 22:23:02 -05:00
Harrison Chase
5d43246694
WIP: stdout callback ( #479 )
...
first pass at stdout callback
for the most part, went pretty smoothly. aside from the code here, here
are some comments/observations.
1.
should somehow default to stdouthandler so i dont have to do
```
from langchain.callbacks import get_callback_manager
from langchain.callbacks.stdout import StdOutCallbackHandler
get_callback_manager().add_handler(StdOutCallbackHandler())
```
2. I kept around the verbosity flag. 1) this is pretty important for
getting the stdout to look good for agents (and other things). 2) I
actually added this for LLM class since it didn't have it.
3. The only part that isn't basically perfectly moved over is the end of
the agent run. Here's a screenshot of the new stdout tracing
Noticing it is missing logging of the final thought, eg before this is
what it looked like
The reason its missing is that this was previously logged as part of
agent end (lines 205 and 206)
this is probably only relevant for the std out logger? any thoughts for
how to get it back in?
2022-12-29 21:34:47 -05:00
Ankush Gola
36922318d3
allow for optional CallbackManager in LLM, Chain, and Agent ( #482 )
2022-12-29 17:30:31 -08:00
Ankush Gola
46b31626b5
Add BaseCallbackHandler and CallbackManager ( #476 )
2022-12-29 15:11:37 -05:00
Harrison Chase
0f1df0dc2c
bump to version 0.0.52 ( #470 )
2022-12-29 09:23:19 -05:00
Parth Chadha
e88e66f982
Pass verbose argument to LLMChains when using *DocumentsChain ( #458 )
...
When using chains such as Summarization chain (`load_summarize_chain`),
the verbose flag wasn't propagated to the `LLMChain`.
2022-12-29 08:22:31 -05:00
Harrison Chase
d0f194de73
add logic for agent stopping ( #420 )
2022-12-29 08:21:11 -05:00
Harrison Chase
c65efd2986
fix llm math prompt ( #466 )
...
basically, it didnt realize that the question was over after the input
and would some times hallucinate more input
2022-12-29 08:20:55 -05:00
Harrison Chase
95157d0aad
Add schema property to sql database utility class ( #448 ) ( #462 )
...
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Signed-off-by: Diwank Singh Tomer <diwank.singh@gmail.com>
Co-authored-by: Nuno Campos <nuno@boringbits.io>
Co-authored-by: Diwank Singh Tomer <diwank.singh@gmail.com>
2022-12-28 17:37:53 -05:00
Nuno Campos
451665cfdf
Add watch mode for test runner ( #453 )
2022-12-28 17:13:08 -05:00
Harrison Chase
2b84e5cda3
Harrison/fix memory and serp ( #457 )
...
Co-authored-by: Bruno Bornsztein <bruno.bornsztein@gmail.com>
2022-12-28 11:07:57 -05:00
Harrison Chase
d98607408b
Harrison/v0050 ( #452 )
2022-12-28 09:22:43 -05:00
Harrison Chase
55007e71be
add output key for memory ( #443 )
...
this allows chains that return multiple values to use memory
2022-12-28 09:04:15 -05:00
Harrison Chase
5208bb8c36
make tools editable ( #445 )
...
use dataclass instead of namedtuple, which makes it editable
add example in notebook
2022-12-28 09:03:16 -05:00
Harrison Chase
5cc6bf1a9c
fix regex parser ( #446 )
2022-12-28 09:02:40 -05:00
Harrison Chase
90e8ccc898
Harrison/update links ( #450 )
...
Co-authored-by: Sam Ching <samuelcwl@gmail.com>
Co-authored-by: Ikko Ashimine <eltociear@gmail.com>
2022-12-28 09:02:07 -05:00
Ikko Ashimine
f3c3288761
chore: fix typo in prompt.py ( #447 )
...
seperator -> separator
2022-12-28 00:19:43 -05:00
Harrison Chase
9ec01dfc16
regex output parser ( #435 )
2022-12-27 20:28:08 -05:00
Harrison Chase
c994ce6b7f
Harrison/serp api imp ( #444 )
...
improve serp api
Co-authored-by: Bruno Bornsztein <bruno.bornsztein@gmail.com>
2022-12-27 20:27:18 -05:00
Harrison Chase
ffe35c396c
unify return types across map-reduce and refine ( #442 )
2022-12-27 19:53:45 -05:00
Harrison Chase
0c5d3fd894
version 0.0.49 ( #436 )
2022-12-27 09:17:01 -05:00
Harrison Chase
f8b605293f
Harrison/improve memory ( #432 )
...
add AI prefix
add new type of memory
Co-authored-by: Jason <chisanch@usc.edu>
2022-12-27 08:23:51 -05:00
Harrison Chase
150b67de10
Harrison/weaviate improvements ( #433 )
...
Co-authored-by: Connor Shorten <connorshorten300@gmail.com>
2022-12-27 08:23:13 -05:00
Harrison Chase
b7566b5ec3
Harrison/return intermediate steps ( #428 )
2022-12-27 08:22:48 -05:00
Harrison Chase
7fc4b4b3e1
Harrison/ver 0048 ( #429 )
2022-12-26 11:36:49 -05:00
Harrison Chase
b50a56830d
Harrison/evaluation notebook ( #426 )
2022-12-26 09:16:37 -05:00
Harrison Chase
97f4000d3a
fix react docstore ( #427 )
2022-12-26 08:46:38 -05:00
Ikko Ashimine
9ae1d75318
Update integrations.md ( #424 )
...
HuggingFace -> Hugging Face
2022-12-25 23:03:05 -05:00
Harrison Chase
f9562d7f1c
version 0047 ( #423 )
2022-12-25 11:17:41 -05:00
Harrison Chase
ee3b8e89b3
better parsing of agent output ( #418 )
2022-12-25 09:53:36 -05:00
Harrison Chase
0d7aa1ee99
Harrison/docs to index ( #419 )
...
Add method for going directly from documents to VectorStores
Update notebook to showcase this functionality
2022-12-25 09:53:07 -05:00
Harrison Chase
48ae981d69
Harrison/multi input tools ( #421 )
...
add documentation on how to use tools that require multiple inputs
2022-12-25 09:52:48 -05:00
Andrew Wang
4416dc9d5d
Update prompt_serialization.ipynb ( #417 )
...
Fix typo.
Originally "support methods are..."
Now "support methods *that* are.."
2022-12-24 17:53:11 -05:00
Harrison Chase
22dd743eba
Harrison/version 0046 ( #416 )
2022-12-24 10:46:23 -05:00
Harrison Chase
01d06c1f9f
check memory variables ( #411 )
...
can have multiple input keys, if some come from memory
2022-12-24 08:36:06 -05:00
Harrison Chase
20959d8c36
check memory variables ( #411 )
...
can have multiple input keys, if some come from memory
2022-12-24 08:35:46 -05:00
altryne
f990395211
Readme typos ( #409 )
...
I was honored by the twitter mention, so used PyCharm to try and... help
docs even a little bit.
Mostly typo-s and correct spellings.
PyCharm really complains about "really good" being used all the time and
recommended alternative wordings haha
2022-12-23 13:13:07 -05:00
Harrison Chase
2ad285aab2
bump version to 0045 ( #408 )
2022-12-23 11:19:30 -05:00
Shreya Rajpal
f40b3ce347
Updated VectorDBQA docs to updated argument name ( #405 )
2022-12-23 10:52:20 -05:00
Dheeraj Agrawal
ea3da9a469
Fix documentation error langchain explanation of combine_docs.md ( #404 )
...
This PR is regarding the issue here -
https://github.com/hwchase17/langchain/issues/403
2022-12-23 08:54:26 -05:00
Harrison Chase
77e1743341
update example ( #402 )
2022-12-22 17:09:47 -05:00
Keiji Kanazawa
5528265142
Add macOS .DS_Store to .gitignore ( #401 )
...
These are macOS specific files left around in directories (to save
user's display settings)
2022-12-22 13:05:57 -05:00
Samantha Whitmore
6bc8ae63ef
Add Redis cache implementation ( #397 )
...
I'm using a hash function for the key just to make sure its length
doesn't get out of hand, otherwise the implementation is quite similar.
2022-12-22 12:31:27 -05:00
Harrison Chase
ff03242fa0
Harrison/ver 044 ( #400 )
2022-12-22 11:20:18 -05:00
mrbean
136f759492
Mrbean/support timeout ( #398 )
...
Add support for passing in a request timeout to the API
2022-12-21 23:39:07 -05:00
Harrison Chase
6b60c509ac
(WIP) add HyDE ( #393 )
...
Co-authored-by: cameronccohen <cameron.c.cohen@gmail.com>
Co-authored-by: Cameron Cohen <cameron.cohen@quantco.com>
2022-12-21 20:46:41 -05:00
Keiji Kanazawa
543db9c2df
Add Azure OpenAI LLM ( #395 )
...
Hi! This PR adds support for the Azure OpenAI service to LangChain.
I've tried to follow the contributing guidelines.
Co-authored-by: Keiji Kanazawa <{ID}+{username}@users.noreply.github.com>
2022-12-21 20:45:37 -05:00
Harrison Chase
bb76440bfa
bump version to 0.0.43 ( #394 )
2022-12-20 22:28:29 -05:00
Harrison Chase
c104d507bf
Harrison/improve data augmented generation docs ( #390 )
...
Co-authored-by: cameronccohen <cameron.c.cohen@gmail.com>
Co-authored-by: Cameron Cohen <cameron.cohen@quantco.com>
2022-12-20 22:24:08 -05:00
