Commit Graph

564 Commits

Author SHA1 Message Date
Enrico Shippole
f30dcc6359
Add GooseAI, CerebriumAI, Petals, ForefrontAI (#981)
Add GooseAI, CerebriumAI, Petals, ForefrontAI
2023-02-13 21:20:19 -08:00
Anton Troynikov
d43d430d86
Chroma persistence (#1028)
This PR adds persistence to the Chroma vector store.

Users can supply a `persist_directory` with any of the `Chroma` creation
methods. If supplied, the store will be automatically persisted at that
directory.

If a user creates a new `Chroma` instance with the same persistence
directory, it will get loaded up automatically. If they use `from_texts`
or `from_documents` in this way, the documents will be loaded into the
existing store.

There is the chance of some funky behavior if the user passes a
different embedding function from the one used to create the collection
- we will make this easier in future updates. For now, we log a warning.
2023-02-13 21:09:06 -08:00
Harrison Chase
012a6dfb16
Harrison/makefile (#1033)
Co-authored-by: blob42 <contact@blob42.xyz>
Co-authored-by: blob42 <spike@w530>
2023-02-13 21:08:47 -08:00
Harrison Chase
6a31a59400
add links (#1027) 2023-02-13 16:33:30 -08:00
Oliver Klingefjord
20889205e8
Added retry for openai.error.ServiceUnavailableError (#1022)
Imho retries should be performed for ServiceUnavailableError (which
tends to happen to me quite often).
2023-02-13 13:30:06 -08:00
Harrison Chase
fc2502cd81
bump version to 0085 (#1017) 2023-02-13 07:32:36 -08:00
Harrison Chase
0f0e69adce
agent refactors (#997) 2023-02-12 23:02:13 -08:00
Harrison Chase
7fb33fca47
chroma docs (#1012) 2023-02-12 23:02:01 -08:00
Harrison Chase
0c553d2064
Harrion/kg (#1016)
Co-authored-by: William FH <13333726+hinthornw@users.noreply.github.com>
2023-02-12 23:01:26 -08:00
Anton Troynikov
78abd277ff
Chroma in LangChain (#1010)
Chroma is a simple to use, open-source, zero-config, zero setup
vectorstore.

Simply `pip install chromadb`, and you're good to go. 

Out-of-the-box Chroma is suitable for most LangChain workloads, but is
highly flexible. I tested to 1M embs on my M1 mac, with out issues and
reasonably fast query times.

Look out for future releases as we integrate more Chroma features with
LangChain!
2023-02-12 17:43:48 -08:00
cragwolfe
05d8969c79
Unstructured example notebook: add a pdf, related deps (#1011)
Updates the Unstructured example notebook with a PDF example. Includes
additional dependencies for PDF processing (and images, etc).
2023-02-12 14:56:48 -08:00
Dhruv Anand
03e5794978
typo fix on chat vector db docs (#1007)
simple typo fix: because --> between
2023-02-12 12:09:21 -08:00
Harrison Chase
6d44a2285c
bump version to 0084 (#1005) 2023-02-12 07:47:10 -08:00
Harrison Chase
0998577dfe
Harrison/unstructured structured (#1004) 2023-02-12 07:36:11 -08:00
Harrison Chase
bbb06ca4cf
pdfminer (#1003) 2023-02-12 07:29:26 -08:00
Francisco Ingham
0b6aa6a024
Added initial capital letter to bullet points that had it missing (#1000)
Co-authored-by: Francisco Ingham <>
2023-02-11 20:31:34 -08:00
Harrison Chase
10e7297306
Harrison/fake llm (#990)
Co-authored-by: Stefan Keselj <skeselj@princeton.edu>
Co-authored-by: Harrison Chase <harrisonchase@Harrisons-MBP.attlocal.net>
2023-02-11 15:12:35 -08:00
Harrison Chase
e51fad1488
Harrison/0083 (#996)
Co-authored-by: Harrison Chase <harrisonchase@Harrisons-MBP.attlocal.net>
2023-02-11 08:29:28 -08:00
Shahriar Tajbakhsh
b7747017d7
Import of declarative_base when SQLAlchemy <1.4 (#883)
In
[pyproject.toml](https://github.com/hwchase17/langchain/blob/master/pyproject.toml),
the expectation is `SQLAlchemy = "^1"`. But, the way `declarative_base`
is imported in
[cache.py](https://github.com/hwchase17/langchain/blob/master/langchain/cache.py)
will only work with SQLAlchemy >=1.4. This PR makes sure Langchain can
be run in environments with SQLAlchemy <1.4
2023-02-10 18:33:47 -08:00
Harrison Chase
2e96704d59
Harrison/airbyte (#989)
Co-authored-by: zanderchase <zanderchase@gmail.com>
Co-authored-by: Harrison Chase <harrisonchase@Harrisons-MacBook-Pro.local>
2023-02-10 18:08:00 -08:00
Charles Frye
e9799d6821
improves huggingface_hub example (#988)
The provided example uses the default `max_length` of `20` tokens, which
leads to the example generation getting cut off. 20 tokens is way too
short to show CoT reasoning, so I boosted it to `64`.

Without knowing HF's API well, it can be hard to figure out just where
those `model_kwargs` come from, and `max_length` is a super critical
one.
2023-02-10 17:56:15 -08:00
zanderchase
c2d1d903fa
Zander/online pdf loader (#984) 2023-02-10 15:42:30 -08:00
Harrison Chase
055a53c27f
add texts example (#985)
Co-authored-by: Harrison Chase <harrisonchase@Harrisons-MacBook-Pro.local>
2023-02-10 12:32:44 -08:00
Harrison Chase
231da14771
bump version to 0082 (#980)
Co-authored-by: Harrison Chase <harrisonchase@Harrisons-MacBook-Pro.local>
2023-02-10 11:38:24 -08:00
jeff
6ab432d62e
docs: update spelling typos (#982)
Wonder why "with" is spelled "wiht" so many times by human
2023-02-10 11:37:59 -08:00
Matt Robinson
07a407d89a
feat: adds UnstructuredURLLoader for loading data from urls (#979)
### Summary

Adds a `UnstructuredURLLoader` that supports loading data from a list of
URLs.


### Testing

```python
from langchain.document_loaders import UnstructuredURLLoader

urls = [
    "https://www.understandingwar.org/backgrounder/russian-offensive-campaign-assessment-february-8-2023",
    "https://www.understandingwar.org/backgrounder/russian-offensive-campaign-assessment-february-9-2023"
]
loader = UnstructuredURLLoader(urls=urls)
raw_documents = loader.load()
```
2023-02-10 10:18:38 -08:00
Harrison Chase
c64f98e2bb
Harrison/format agent instructions (#973)
Co-authored-by: Andrew White <white.d.andrew@gmail.com>
Co-authored-by: Harrison Chase <harrisonchase@Harrisons-MBP.attlocal.net>
Co-authored-by: Peng Qu <82029664+pengqu123@users.noreply.github.com>
2023-02-10 10:07:26 -08:00
Harrison Chase
5469d898a9
Harrison/everynote (#974)
Co-authored-by: Harrison Chase <harrisonchase@Harrisons-MBP.attlocal.net>
2023-02-10 08:02:35 -08:00
Harrison Chase
3d639d1539
update lint (#975)
Co-authored-by: Harrison Chase <harrisonchase@Harrisons-MBP.attlocal.net>
2023-02-10 08:01:13 -08:00
Harrison Chase
91c6cea227
Harrison/batch embeds (#972)
Co-authored-by: John Dagdelen <jdagdelen@users.noreply.github.com>
Co-authored-by: Harrison Chase <harrisonchase@Harrisons-MBP.attlocal.net>
2023-02-10 06:59:50 -08:00
Harrison Chase
ba54d36787
Harrison/tiktoken spec (#964)
Co-authored-by: James Briggs <35938317+jamescalam@users.noreply.github.com>
Co-authored-by: Harrison Chase <harrisonchase@Harrisons-MBP.attlocal.net>
2023-02-09 23:30:18 -08:00
Harrison Chase
5f8082bdd7
Harrison/deps (#963)
Co-authored-by: Jon Luo <20971593+jzluo@users.noreply.github.com>
Co-authored-by: Harrison Chase <harrisonchase@Harrisons-MBP.attlocal.net>
2023-02-09 23:19:19 -08:00
Kevin Huo
512c523368
remove sample_row_in_table_info and simplify set operations in SQLDB (#932)
-Address TODO: deprecate for sample_row_in_table_info
-Simplify set operations by casting to sets to not need multiple set
casts + .difference() calls
2023-02-09 23:15:41 -08:00
Harrison Chase
e323d0cfb1
bump version 0081 (#956)
Co-authored-by: Harrison Chase <harrisonchase@Harrisons-MBP.attlocal.net>
2023-02-09 08:29:11 -08:00
Harrison Chase
01fa2d8117
Harrison/youtube fixes (#955)
Co-authored-by: Ji <jizhang.work@gmail.com>
Co-authored-by: Harrison Chase <harrisonchase@Harrisons-MBP.attlocal.net>
2023-02-09 08:12:22 -08:00
zanderchase
8e126bc9bd
adding webpage loading logic (#942) 2023-02-09 07:52:50 -08:00
Harrison Chase
c71027e725
add docs for steamship deployment (#949)
Co-authored-by: Harrison Chase <harrisonchase@Harrisons-MBP.attlocal.net>
2023-02-08 16:01:19 -08:00
Usama Navid
e85c53ce68
Update readthedocs.py (#943)
Sometimes, the docs may be empty. For example for the text =
soup.find_all("main", {"id": "main-content"}) was an empty list. To
cater to these edge cases, the clean function needs to be checked if it
is empty or not.
2023-02-08 16:01:07 -08:00
Harrison Chase
3e1901e1aa
gutenberg books (#946)
Co-authored-by: zanderchase <zander@unfold.ag>
Co-authored-by: Harrison Chase <harrisonchase@Harrisons-MBP.attlocal.net>
2023-02-08 12:00:47 -08:00
jeff
6a4f602156
docs: fix spelling typo (#934) 2023-02-08 11:13:35 -08:00
Ikko Eltociear Ashimine
6023d5be09
Update huggingface_hub.ipynb (#944)
HuggingFace -> Hugging Face
2023-02-08 11:05:28 -08:00
Harrison Chase
a306baacd1
bump version to 0080 (#941) 2023-02-08 07:41:25 -08:00
Harrison Chase
44ecec3896
Harrison/add roam loader (#939) 2023-02-08 00:35:33 -08:00
Ankush Gola
bc7e56e8df
Add asyncio support for LLM (OpenAI), Chain (LLMChain, LLMMathChain), and Agent (#841)
Supporting asyncio in langchain primitives allows for users to run them
concurrently and creates more seamless integration with
asyncio-supported frameworks (FastAPI, etc.)

Summary of changes:

**LLM**
* Add `agenerate` and `_agenerate`
* Implement in OpenAI by leveraging `client.Completions.acreate`

**Chain**
* Add `arun`, `acall`, `_acall`
* Implement them in `LLMChain` and `LLMMathChain` for now

**Agent**
* Refactor and leverage async chain and llm methods
* Add ability for `Tools` to contain async coroutine
* Implement async SerpaPI `arun`

Create demo notebook.

Open questions:
* Should all the async stuff go in separate classes? I've seen both
patterns (keeping the same class and having async and sync methods vs.
having class separation)
2023-02-07 21:21:57 -08:00
Vincent Elster
afc7f1b892
Fix typos (#929)
accomplisehd -> accomplished
2023-02-07 14:39:45 -08:00
Harrison Chase
d43250bfa5
Harrison/ver0079 (#927) 2023-02-07 07:59:35 -08:00
Harrison Chase
bc53c928fc
Harrison/athropic (#921)
Co-authored-by: Mike Lambert <mlambert@gmail.com>
Co-authored-by: mrbean <sam@you.com>
Co-authored-by: mrbean <43734688+sam-h-bean@users.noreply.github.com>
Co-authored-by: Ivan Vendrov <ivendrov@gmail.com>
2023-02-06 22:29:25 -08:00
Harrison Chase
637c0d6508
Harrison/obsidian (#920) 2023-02-06 22:21:16 -08:00
Harrison Chase
1e56879d38
Harrison/save faiss (#916)
Co-authored-by: Shrey Joshi <shreyjoshi2004@gmail.com>
2023-02-06 21:44:50 -08:00
Ankush Gola
6bd1529cb7
add GoogleDriveLoader (#914)
only deal with docs files for now
2023-02-06 21:44:35 -08:00