Commit Graph

56 Commits

Author SHA1 Message Date
Jon Luo
92ab27e4b8
sql doc formatting (#1350)
My bad, missed a few tabs between the two PRs
2023-02-28 19:54:46 -08:00
Jon Luo
35f1e8f569
separate columns by tabs instead of single space in sql sample rows (#1348)
Use tabs to separate columns instead of a single space - confusing when
there are spaces in a cell
2023-02-28 18:59:53 -08:00
Jon Luo
5bf8772f26
add option to use user-defined SQL table info (#1347)
Currently, table information is gathered through SQLAlchemy as complete
table DDL and a user-selected number of sample rows from each table.
This PR adds the option to use user-defined table information instead of
automatically collecting it. This will use the provided table
information and fall back to the automatic gathering for tables that the
user didn't provide information for.

Off the top of my head, there are a few cases where this can be quite
useful:
- The first n rows of a table are uninformative, or very similar to one
another. In this case, hand-crafting example rows for a table such that
they provide the good, diverse information can be very helpful. Another
approach we can think about later is getting a random sample of n rows
instead of the first n rows, but there are some performance
considerations that need to be taken there. Even so, hand-crafting the
sample rows is useful and can guarantee the model sees informative data.
- The user doesn't want every column to be available to the model. This
is not an elegant way to fulfill this specific need since the user would
have to provide the table definition instead of a simple list of columns
to include or ignore, but it does work for this purpose.
- For the developers, this makes it a lot easier to compare/benchmark
the performance of different prompting structures for providing table
information in the prompt.

These are cases I've run into myself (particularly cases 1 and 3) and
I've found these changes useful. Personally, I keep custom table info
for a few tables in a yaml file for versioning and easy loading.

Definitely open to other opinions/approaches though!
2023-02-28 18:58:04 -08:00
Eugene Yurtsev
c14cff60d0
Documentation: Minor typo fixes (#1327)
Fixing a few minor typos in the documentation (and likely introducing
other
ones in the process).
2023-02-27 14:40:43 -08:00
Harrison Chase
71709ad5d5
Update key_concepts.md (#1209) (#1237)
Link for easier navigation (it's not immediately clear where to find
more info on SimpleSequentialChain (3 clicks away)

---------

Co-authored-by: Larry Fisherman <l4rryfisherman@protonmail.com>
2023-02-22 13:30:53 -08:00
Harrison Chase
d90a287d8f
Harrison/updating docs (#1196) 2023-02-20 22:54:26 -08:00
Harrison Chase
4f3fbd7267
improve docs for indexes (#1146) 2023-02-19 23:14:50 -08:00
Nan Wang
e8f224fd3a
docs: add missing links to toc (#1163)
add missing links to toc

---------

Signed-off-by: Nan Wang <nan.wang@jina.ai>
2023-02-19 21:15:11 -08:00
Harrison Chase
955c89fccb
pass in prompts to vectordbqa (#1158) 2023-02-19 20:47:17 -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
Harrison Chase
45b5640fe5
fix sql (#1141) 2023-02-18 11:49:08 -08:00
Harrison Chase
511d41114f
return source documents for chat vector db chain (#1128) 2023-02-17 13:40:52 -08:00
Francisco Ingham
3462130e2d
Modify number of types of chains (#1089)
Changed number of types of chains to make it consistent with the rest of
the docs
2023-02-16 07:06:30 -08:00
Harrison Chase
7745505482
chat qa with sources (#1084) 2023-02-16 00:29:47 -08:00
Harrison Chase
badeeb37b0
fix stuff count (#1083) 2023-02-15 23:57:13 -08:00
Harrison Chase
971458c5de
docs for batch size (#1082) 2023-02-15 23:53:56 -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
d8ac274fc2
add to async chain notebook (#1056) 2023-02-14 18:20:38 -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
Sasmitha Manathunga
c67c5383fd
docs: fix typo in notebook (#1046) 2023-02-14 07:06:08 -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
Harrison Chase
6a31a59400
add links (#1027) 2023-02-13 16:33:30 -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
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
e51fad1488
Harrison/0083 (#996)
Co-authored-by: Harrison Chase <harrisonchase@Harrisons-MBP.attlocal.net>
2023-02-11 08:29:28 -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
Harrison Chase
87fad8fc00
analyze document (#731)
add analyze document chain, which does text splitting and then analysis
2023-02-06 20:02:19 -08:00
Harrison Chase
f95cedc443
Harrison/sql rows (#915)
Co-authored-by: Jon Luo <20971593+jzluo@users.noreply.github.com>
2023-02-06 18:56:18 -08:00
Harrison Chase
2a68be3e8d
chat vector db chain (#902) 2023-02-05 21:38:47 -08:00
Zach Schillaci
4c79100b15
Correct prompt typo + update example for SQLDatabaseChain (#868)
See https://github.com/hwchase17/langchain/issues/821
2023-02-03 08:34:41 -08:00
Harrison Chase
fc0cfd7d1f
docs (#848) 2023-02-02 11:35:36 -08:00
Harrison Chase
0de55048b7
return code for pal (#844) 2023-02-02 08:47:20 -08:00
Harrison Chase
94ae126747
return sql intermediate steps (#792) 2023-01-30 15:10:48 -08:00
Harrison Chase
248c297f1b
Sample row in table info for SQLDatabase (#769) (#782)
The agents usually benefit from understanding what the data looks like
to be able to filter effectively. Sending just one row in the table info
allows the agent to understand the data before querying and get better
results.

---------

Co-authored-by: Francisco Ingham <>

---------

Co-authored-by: Francisco Ingham <fpingham@gmail.com>
2023-01-28 13:37:07 -08:00
Harrison Chase
b9ad214801
add docs for loading from hub (#763) 2023-01-27 07:10:26 -08:00
Harrison Chase
bd0bf4e0a9
Harrison/generate blog post (#732)
Co-authored-by: Ren <yirenlu92@users.noreply.github.com>
2023-01-24 22:54:12 -08:00
Harrison Chase
0ffeabd14f
Harrison/serialize llm chain (#671) 2023-01-24 21:36:19 -08:00
Nicolas
66fd57878a
docs: Update vector_db_qa_with_sources.ipynb (#706) 2023-01-23 23:06:54 -08:00
Harrison Chase
6be5f4e4c4
Harrison/sql db chain (#641)
Co-authored-by: Bruno Bornsztein <bruno.bornsztein@gmail.com>
2023-01-17 22:32:28 -08:00
Francis
b374d481c8
fix typo (#636)
there is a small typo in one of the docs.
2023-01-17 22:17:50 -08:00
Harrison Chase
3d43906572
Harrison/new api chain (#623)
Co-authored-by: Francisco Ingham <fpingham@gmail.com>
Co-authored-by: lesscomfortable <pancho_ingham@hotmail.com>
2023-01-15 18:34:43 -08:00
Harrison Chase
1c71fadfdc
more complex sql chain (#619)
add a more complex sql chain that first subsets the necessary tables
2023-01-15 17:07:21 -08:00
Francisco Ingham
1787c473b8
Custom prompt option for llm_bash and api chains (#612)
Co-authored-by: lesscomfortable <pancho_ingham@hotmail.com>
2023-01-14 07:22:52 -08:00
Harrison Chase
9f9afbb6a8
add custom prompt for LLMMathChain and SQLDatabase chain (#605) 2023-01-13 06:28:51 -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
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