Commit Graph

898 Commits

Author SHA1 Message Date
Harrison Chase
86085bc1e4 cr 2023-03-20 19:11:08 -07:00
Harrison Chase
5f41f07b8b Merge branch 'master' into harrison/guarded-output-parser 2023-03-20 19:10:51 -07:00
Harrison Chase
ccc18973b4 cr 2023-03-20 19:10:13 -07:00
jerwelborn
32a8507829 showcase guarded pydantic parsing 2023-03-20 16:25:35 -07:00
jerwelborn
3ee755897e tweak pydantic parser 2023-03-20 16:25:18 -07:00
jerwelborn
a0cde05839 try make guarded/retriable output parser an instance of parser 2023-03-20 13:58:12 -07:00
jerwelborn
325825d55f add example nb 2023-03-20 12:54:21 -07:00
jerwelborn
bfa858b3a6 make parser and guarded parser roughly swappable 2023-03-20 12:41:57 -07:00
jerwelborn
fa2d98c487 factor out 'naive' retry chain 2023-03-20 11:27:04 -07:00
Harrison Chase
0ca1641b14 release 0.0.117 (#1819) v0.0.117 2023-03-20 08:04:04 -07:00
Harrison Chase
d5b4393bb2 Harrison/llm math (#1808)
Co-authored-by: Vadym Barda <vadim.barda@gmail.com>
2023-03-20 07:53:26 -07:00
Bryan Helmig
7b6ff7fe00 Follow up to #1803 to remove dynamic docs route. (#1818)
The base docs are going to be more stable and familiar for folks.
Dynamic route is currently in flux.
2023-03-20 07:52:41 -07:00
Harrison Chase
76c7b1f677 Harrison/wandb (#1764)
Co-authored-by: Anish Shah <93145909+ash0ts@users.noreply.github.com>
2023-03-20 07:52:27 -07:00
Paul
5aa8ece211 Corrected small typo in error message. (#1791) 2023-03-20 07:51:35 -07:00
Harrison Chase
f6d24d5740 fix bug with openai token count (#1806) 2023-03-20 07:51:18 -07:00
Harrison Chase
b1c4480d7c fix typing (#1807) 2023-03-20 07:50:49 -07:00
Daniel Chalef
b6ba989f2f Add request timeout to ChatOpenAI (#1798)
Add request_timeout field to ChatOpenAI. Defaults to 60s.

---------

Co-authored-by: Daniel Chalef <daniel.chalef@private.org>
2023-03-19 20:19:42 -07:00
Ankush Gola
04acda55ec Don't use dynamic api endpoint for Zapier NLA (#1803)
From Robert "Right now the dynamic/ route for specifically the above
endpoints is acting on all providers a user has set up, not just the
provider for the supplied API key."
2023-03-19 20:12:33 -07:00
Harrison Chase
6898d8391f cr 2023-03-19 18:05:37 -07:00
Harrison Chase
1af560cca8 cr 2023-03-19 18:00:23 -07:00
Harrison Chase
44d2492427 guarded output parser 2023-03-19 17:57:42 -07:00
Harrison Chase
8e5c4ac867 bump version to 0.0.116 (#1788) v0.0.116 2023-03-19 11:01:16 -07:00
Aratako
df8702fead Small fix: Remove unused variable summary_message_role (#1789)
After the changes in #1783, `summary_message_role` is no longer used in
`ConversationSummaryBufferMemory`, so this PR removes it.
2023-03-19 11:01:03 -07:00
Harrison Chase
d5d50c39e6 Harrison/azure embeddings (#1787)
Co-authored-by: Hemant <4627288+ghaccount@users.noreply.github.com>
2023-03-19 10:42:33 -07:00
Harrison Chase
1f18698b2a Harrison/token buffer memory (#1786)
Co-authored-by: Aratako <127325395+Aratako@users.noreply.github.com>
2023-03-19 10:42:24 -07:00
Harrison Chase
ef4945af6b Harrison/chat token usage (#1785) 2023-03-19 10:32:31 -07:00
Harrison Chase
7de2ada3ea Harrison/add source column (#1784)
Co-authored-by: Brian Graham <46691715+briangrahamww@users.noreply.github.com>
Co-authored-by: briangrahamww <brian.graham@ww.com>
2023-03-19 10:32:13 -07:00
Bernat Felip i Díaz
262d4cb9a8 Use embedding instead of embedding function in ElasticVectorStore (#1692)
While it might be a bit more restrictive, I find that using the
Embedding interface as an input for the vector store creation is better
than an embedding function because we can use bulk requests and possibly
the retry logic if needed.

I have seen that some vector store implementations use Embedding while
others use embedding function so I don't know what is the criteria to
have one or the other, in my opinion they should all just be Embedding
or have a way more complex embedding function that accepts multiple
texts instead of one by one.

---------

Co-authored-by: Bernat Felip <bernat.felip@rea.ch>
2023-03-19 10:23:38 -07:00
Harrison Chase
951c158106 Harrison/summary message rol (#1783)
Co-authored-by: Aratako <127325395+Aratako@users.noreply.github.com>
2023-03-19 10:09:18 -07:00
Bao Nguyen
85e4dd7fc3 Fix wrong prompt in refine chain (#1770)
I got this during testing 

```
ValueError: Missing some input keys: {'existing_answer'}
```

Upon review, the initial prompt should be `QUESTION_PROMPT_SELECTOR`.

Co-authored-by: Bao Nguyen <bnguyen@roku.com>
2023-03-19 10:03:45 -07:00
Harrison Chase
b1b4a4065a change chat default (#1782)
Resolves https://github.com/hwchase17/langchain/issues/1532, resolves
https://github.com/hwchase17/langchain/issues/1652.
2023-03-19 10:01:59 -07:00
Huang Chongdi
08f23c95d9 add encoding parameter to ObsidianLoader (#1752) 2023-03-19 09:48:31 -07:00
hitoshi44
3cf493b089 Fix Document & Expose StringPromptTemplate as a custom-prompt-template. (#1753)
Regarding [this
issue](https://github.com/hwchase17/langchain/issues/1754), the code in
the document [Creating a custom prompt
template](https://langchain.readthedocs.io/en/latest/modules/prompts/examples/custom_prompt_template.html)
is no longer functional and outdated.

To address this, I have made the following changes:

1. Updated the guide in the document to use `StringPromptTemplate`
instead of `BasePromptTemplate`.
2. Exposed `StringPromptTemplate` in `prompts/__init__.py` for easier
importing.
2023-03-19 09:47:56 -07:00
hitoshi44
e635c86145 Slightly modified the docstring in BasePromptTemplate and StringPromptTemplate. (#1755)
Regarding [this
issue](https://github.com/hwchase17/langchain/issues/1754),
`BasePromptTample` class docstring is a little outdated, thus it
requires new method `format_prompt` for now.

As such, I have made some modifications to the docstring to bring it up
to date.

I tried to adhere to the established document style, and would
appreciate you for taking a look at this PR.
2023-03-19 09:47:37 -07:00
Harrison Chase
779790167e Harrison/add warning to openaichat (#1781) 2023-03-19 09:43:56 -07:00
Nils Durner
3161ced4bc GPT-4 support (#1778) 2023-03-19 09:29:44 -07:00
hung_ng__
3d6fcb85dc Add load json prompt example (#1776)
Hi, I just want to add a PR on the prompt serialization examples of
loading from JSON so that it can contain the same as loading from YAML.
2023-03-19 09:28:56 -07:00
LeoGrin
3701b2901e use namespace argument in Pinecone constructor (#1757)
Fix #1756

Use the `namespace` argument of `Pinecone.from_exisiting_index` to set
the default value of `namespace` for other methods. Leads to more
expected behavior and easier integration in chains.

For the test, I've added a line to delete and rebuild the
`langchain-demo` index at the beginning of the test. I'm not 100% sure
if it's a good idea but it makes the test reproducible.
2023-03-18 19:55:38 -07:00
Ben Gahtan
280cb4160d Update tool.py (#1760)
Fixed typo that said the Wikipedia tool was using Wolfram Alpha (instead
of Wikipedia)
2023-03-18 19:55:26 -07:00
Kevin
80d8db5f60 Add service account support to Google Drive (#1761)
Having service account support in the drive document loader would be
nice.

This is already present in the youtube loader. 

cb646082ba/langchain/document_loaders/youtube.py (L76-L78)
2023-03-18 19:55:17 -07:00
Piyush Jain
1a8790d808 Corrects copyright year (#1762)
Corrected copyright year.
2023-03-18 19:55:05 -07:00
Eric Zhu
34840f3aee AzureChatOpenAI for Azure Open AI's ChatGPT API (#1673)
Add support for Azure OpenAI's ChatGPT API, which uses ChatML markups to
format messages instead of objects.

Related issues: #1591, #1659
2023-03-18 19:54:20 -07:00
Harrison Chase
8685d53adc querying tabular data (#1758) 2023-03-18 11:12:18 -07:00
Harrison Chase
2f6833d433 hotfix (#1742) v0.0.115 2023-03-17 09:05:08 -07:00
Harrison Chase
dd90fd02d5 Harrison/move docs (#1741) 2023-03-17 08:49:10 -07:00
Harrison Chase
07766a69f3 move docs (#1740) 2023-03-17 08:42:28 -07:00
Harrison Chase
aa854988bf bump version to 114 (#1739) v0.0.114 2023-03-17 08:26:06 -07:00
Harrison Chase
96ebe98dc2 Harrison/latex splitter (#1738)
Co-authored-by: Aidan Holland <thehappydinoa@gmail.com>
Co-authored-by: Jan de Boer <44832123+Janldeboer@users.noreply.github.com>
2023-03-17 08:10:27 -07:00
Harrison Chase
45f05fc939 Harrison/blackboard loader (#1737)
Co-authored-by: Aidan Holland <thehappydinoa@gmail.com>
2023-03-17 08:02:44 -07:00
Vincent Liao
cf9c3f54f7 docs: add docs link to agent toolkits (#1735)
New to Langchain, was a bit confused where I should find the toolkits
section when I'm at `agent/key_concepts` docs. I added a short link that
points to the how to section.
2023-03-17 07:59:49 -07:00