github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-08-31 18:38:48 +00:00
Code Issues Packages Projects Releases Wiki Activity
1,401 Commits 976 Branches 959 Tags
5e66d05928516c8e30d2f6fabac3b87d0d926572
Commit Graph

1401 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Harrison Chase
67808bad0e expose more serpapi parameters (#609) 2023-01-13 17:36:10 -08:00
Nicolas
b7225fd010 docs: fix small typo (#611) 2023-01-13 17:31:33 -08:00
Harrison Chase
e9301bf833 bump version to 0.0.62 (#607) 2023-01-13 07:47:59 -08:00
Harrison Chase
9f9afbb6a8 add custom prompt for LLMMathChain and SQLDatabase chain (#605) 2023-01-13 06:28:51 -08:00
Smit Shah
a87a2aacaa [Minor Fix] Fix spacy TextSplitter init (#606) 2023-01-13 06:24:44 -08:00
Sasmitha Manathunga
3e55f1474e docs: fix typo (#604) 2023-01-12 21:36:03 -08:00
babbldev
b5eb91536a Added filter argument to pinecone queries, fixes #600 (#601) 
Added filter argument to similarity_search() and
similarity_search_with_score()

Co-authored-by: Sam Cartford (MBP) <cartford@hey.com>
 2023-01-12 21:15:51 -08:00
Sam Ching
c4c6bf6e6e Add subsection for colab notebooks (#599) 
Motivation is that these don't get lost in the Twitterverse!
 2023-01-12 18:16:55 -08:00
Rukmal Weerawarana
0f544a8811 Fix minor error in LLM documentation (#602) 2023-01-12 18:16:32 -08:00
Ikko Eltociear Ashimine
60dfe58325 Fix typo in vector_db_qa.ipynb (#597) 
paramter -> parameter
 2023-01-12 08:23:24 -08:00
Harrison Chase
950a81399a bump version to 61 (#596) 2023-01-12 07:20:16 -08:00
Harrison Chase
d574bf0a27 add documentation on how to load different chain types (#595) 2023-01-12 06:47:38 -08:00
Harrison Chase
956416c150 Harrison/update links1 (#594) 
update links to be relative

Co-authored-by: Marc Green <marcgreen@users.noreply.github.com>
 2023-01-12 06:29:42 -08:00
Harrison Chase
8ab09c18a1 Return source documents option in VectorDBQA (#585) (#592) 
Co-authored-by: lesscomfortable <pancho_ingham@hotmail.com>

Co-authored-by: Francisco Ingham <fpingham@gmail.com>
Co-authored-by: lesscomfortable <pancho_ingham@hotmail.com>
 2023-01-12 06:09:32 -08:00
Harrison Chase
4c6c5f0391 wolfram alpha improvements (#591) 
Co-authored-by: Nicolas <nicolascamara29@gmail.com>
 2023-01-12 06:09:12 -08:00
Harrison Chase
a5ee7de650 pinecone changes (#590) 
Co-authored-by: Smit Shah <who828@gmail.com>
Co-authored-by: iocuydi <46613640+iocuydi@users.noreply.github.com>
 2023-01-12 06:08:47 -08:00
Harrison Chase
7b6e7f6e12 bump to version 60 (#583) 2023-01-11 07:09:30 -08:00
Harrison Chase
3f2ea5c35e Harrison/load from hub (#580) 2023-01-11 06:34:11 -08:00
Harrison Chase
f74ce7a104 Harrison/combine memories (#582) 
Signed-off-by: Diwank Singh Tomer <diwank.singh@gmail.com>
Co-authored-by: Diwank Singh Tomer <diwank.singh@gmail.com>
 2023-01-11 06:08:58 -08:00
Harrison Chase
2aa08631cb add similarity score method to faiss (#574) 
adds `similarity_search_with_score` to faiss wrapper
 2023-01-11 06:06:17 -08:00
Harrison Chase
5ba46f6d0c Harrison/namespace pinecone (#581) 
Co-authored-by: mmorzywolek <89693033+mmorzywolek@users.noreply.github.com>
 2023-01-11 06:05:48 -08:00
Harrison Chase
ffc7e04d44 Harrison/wolfram alpha (#579) 
Co-authored-by: Nicolas <nicolascamara29@gmail.com>
 2023-01-11 05:52:19 -08:00
Harrison Chase
94765e7487 more gallery (#577) 2023-01-10 08:24:00 -08:00
Harrison Chase
50a49eff15 gallery updates (#573) 2023-01-10 07:41:29 -08:00
Harrison Chase
6966863d7d Harrison/deployments (#572) 2023-01-10 07:41:16 -08:00
Harrison Chase
7de5139750 add example selector docs (#564) 2023-01-09 19:17:29 -08:00
Yong723
94c06c55e8 modify docstring (#569) 
Sorry for the detail. this is a correction to the docstring.
 2023-01-09 19:12:59 -08:00
Yong723
e1f3871a78 fix typo (#570) 
I found a typo, which might be important for a conversational Agent.

if My PR is wrong, I am so sorry
 2023-01-09 19:12:34 -08:00
Harrison Chase
6374df5a31 bump version (#565) 2023-01-09 12:34:47 -08:00
Harrison Chase
b06a2a6191 improve documentation on how to pass in custom prompts (#561) 2023-01-08 19:20:13 -08:00
Harrison Chase
1511606799 Harrison/fix splitting (#563) 
fix issue where text splitting could possibly create empty docs
 2023-01-08 19:19:32 -08:00
Harrison Chase
1192cc0767 smart text splitter (#530) 
smart text splitter that iteratively tries different separators until it
works!
 2023-01-08 15:11:10 -08:00
Harrison Chase
8dfad874a2 map rerank chain (#516) 
add a chain that applies a prompt to all inputs and then returns not
only an answer but scores it

add examples for question answering and question answering with sources
 2023-01-08 06:49:22 -08:00
Nicolas
948eee9fe1 Docs: side menu to match the order (llms) (#557) 
Small quick fix:

Suggest making the order of the menu the same as it is written on the
page (Getting Started -> Key Concepts). Before the menu order was not
the same as it was on the page. Not sure if this is the only place the
menu is affected.

Mismatch is found here:
https://langchain.readthedocs.io/en/latest/modules/llms.html
 2023-01-06 09:34:08 -08:00
Harrison Chase
823a44ef80 bump to 0058 (#556) 2023-01-06 07:58:38 -08:00
Benjamin
42d5d988fa add openai logit bias (#553) 
Add
[`logit_bias`](https://beta.openai.com/docs/api-reference/completions/create#completions/create-logit_bias)
params to OpenAI

See [here](https://beta.openai.com/tokenizer) for the tokenizer.

NB: I see that others (like Cohere) have the same parameter, but since I
don't have an access to it, I don't want to make a mistake.

---

Just to make sure the default "{}" works for openai:
```
from langchain.llms import OpenAI

OPENAI_API_KEY="XXX"

llm = OpenAI(openai_api_key=OPENAI_API_KEY)
llm.generate('Write "test":')

llm = OpenAI(openai_api_key=OPENAI_API_KEY, logit_bias={'9288': -100, '1332': -100, '14402': -100, '6208': -100})
llm.generate('Write "test":')
```
 2023-01-06 07:48:52 -08:00
Harrison Chase
9833fcfe32 fix caching (#555) 2023-01-06 07:30:10 -08:00
Harrison Chase
74932f2516 RFC: conversational agent (#464) 
Co-authored-by: Bruno Bornsztein <bruno.bornsztein@gmail.com>
 2023-01-06 07:25:55 -08:00
Harrison Chase
330a5b42d4 fix map reduce chain (#550) 2023-01-06 07:15:57 -08:00
Diwank Singh Tomer
ba0cbb4a41 Add finish reason to Generation for usage downstream (#526) 
Add `finish_reason` to `Generation` as well as extend
`BaseOpenAI._generate` to include it in the output. This can be useful
for usage in downstream tasks when we need to filter for only
generations that finished because of `"stop"` for example. Maybe we
should add this to `LLMChain` as well?

For more details, see
https://beta.openai.com/docs/guides/completion/best-practices

Signed-off-by: Diwank Singh Tomer <diwank.singh@gmail.com>
 2023-01-06 07:15:25 -08:00
Harrison Chase
e64ed7b975 Harrison/tools priority (#554) 
Co-authored-by: Yong723 <50616781+Yongtae723@users.noreply.github.com>
 2023-01-06 06:56:11 -08:00
Harrison Chase
4974f49bb7 add return_direct flag to tool (#537) 
adds a return_direct flag to tools, which just returns the tool output
as the final output
 2023-01-06 06:40:32 -08:00
Harrison Chase
1f248c47f3 bump version to 0.0.57 (#548) 2023-01-05 09:46:44 -08:00
Harrison Chase
0c2f7d8da1 changes to qa chain (#543) 2023-01-05 09:33:59 -08:00
Hunter Gerlach
5b4c972fc5 Add linkcheck badge to signify when/if links are failing (#546) 
Detect whether or not most recent GitHub Action running linkcheck was
successful.
 2023-01-05 08:37:01 -08:00
Harrison Chase
9753bccc71 Feature: linkcheck-action (#534) (#542) 
- Add support for local build and linkchecking of docs
- Add GitHub Action to automatically check links before prior to
publication
- Minor reformat of Contributing readme
- Fix existing broken links

Co-authored-by: Hunter Gerlach <hunter@huntergerlach.com>

Co-authored-by: Hunter Gerlach <HunterGerlach@users.noreply.github.com>
Co-authored-by: Hunter Gerlach <hunter@huntergerlach.com>
 2023-01-04 21:39:50 -08:00
Harrison Chase
5aefc2b7ce add handling on error (#541) 2023-01-04 20:23:55 -08:00
Harrison Chase
1631981f84 Harrison/fix and test caching (#538) 2023-01-04 18:39:06 -08:00
Harrison Chase
73f7ebd9d1 Harrison/sqlalchemy cache store (#536) 
Co-authored-by: Jason Gill <jasongill@gmail.com>
 2023-01-04 18:38:15 -08:00
Sam Ching
870cccb877 Add info to Contributors.md to avoid Conda/Pyenv dependency conflicts (#540) 
As discussed in the
[Discord](https://discord.com/channels/1038097195422978059/1038097349660135474/1060194710485995521),
adding the following instructions to help future contributors avoid
dependency conflicts if they use Conda / Pyenv on their system.
 2023-01-04 18:28:42 -08:00