langchain

Commit Graph

Author	SHA1	Message	Date
liviuasnash1	6396a4ad8d	Fix documentation typos (#3870 ) Co-authored-by: Liviu Asnash <liviua@maximallearning.com>	1 year ago
Harrison Chase	f7a828685d	Harrison/constitutional chain (#3931 ) Co-authored-by: Sam Ching <samuel@duolingo.com>	1 year ago
Ankush Gola	d3ec00b566	Callbacks Refactor [base] (#3256 ) Co-authored-by: Nuno Campos <nuno@boringbits.io> Co-authored-by: Davis Chase <130488702+dev2049@users.noreply.github.com> Co-authored-by: Zander Chase <130414180+vowelparrot@users.noreply.github.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	1 year ago
Zander Chase	ee670c448e	Persistent Bash Shell (#3580 ) Clean up linting and make more idiomatic by using an output parser --------- Co-authored-by: FergusFettes <fergusfettes@gmail.com>	1 year ago
Jon Luo	f3180f05f9	Update sql chain notebook to clarify use of SQLAlchemy for connections (#2850 ) Have seen questions about whether or not the `SQLDatabaseChain` supports more than just sqlite, which was unclear in the docs, so tried to clarify that and how to connect to other dialects.	1 year ago
Harrison Chase	b38a6ea7df	Harrison/apply llm flag (#2743 ) Co-authored-by: Nick Gibb <gibbnick@gmail.com> Co-authored-by: Nick Gibb <nick.gibb@bluedot.global>	1 year ago
Harrison Chase	e63f9a846b	Harrison/docs agents (#2647 )	1 year ago
William FH	e56673c7f9	BabyAGI Notebook Example (#2559 ) Create a notebook implementing [BabyAGI](https://github.com/yoheinakajima/babyagi/tree/main) by [Yohei Nakajima](https://twitter.com/yoheinakajima) as LLM Chains.	1 year ago
Harrison Chase	7aba18ea77	Harrison/docs cleanup (#2633 )	1 year ago
William FH	5c0c5fafb2	Multi-Hop / Multi-Spec LLM Chain (#2549 ) Add a notebook showing how to make a chain that composes multiple OpenAPI Endpoint operations to accomplish tasks.	1 year ago
Harrison Chase	247a88f2f9	Harrison/move eval (#2533 )	1 year ago
William FH	632c65d64b	Add to notebook to assist in ground truth question generation (#2523 ) At the bottom of the notebook, continue to show how to generate example test cases with the assistance of an LLM	1 year ago
William FH	629fda3957	Use JSON rather than JSON5 (#2520 ) Evaluation so far has shown that agents do a reasonable job of emitting `json` blocks as arguments when cued (instead of typescript), and `json` permits the `strict=False` flag to permit control characters, which are likely to appear in the response in particular. This PR makes this change to the request and response synthesizer chains, and fixes the temperature to the OpenAI agent in the eval notebook. It also adds a `raise_error = False` flag in the notebook to facilitate debugging	1 year ago
William FH	f8e4048cd8	Add an Example Evaluation Notebook for the API Chain (#2516 ) Taking the Klarna API as an example, uses evaluation chain's to judge the quality of the request and response synthesizers based on a small set of curated queries. Also updates intermediate steps for chain to emit a dict so each step can be keyed for lookup ![image](https://user-images.githubusercontent.com/13333726/230505771-5cdb4de4-6fe7-4f54-b944-f29d438fa42c.png)	1 year ago
William FH	f240651bd8	Add Request body (#2507 ) This still doesn't handle the following - non-JSON media types - anyOf, allOf, oneOf's And doesn't emit the typescript definitions for referred types yet, but that can be saved for a separate PR. Also, we could have better support for Swagger 2.0 specs and OpenAPI 3.0.3 (can use the same lib for the latter) recommend offline conversion for now.	1 year ago
Harrison Chase	1e19e004af	Harrison/openapi spec (#2474 ) Co-authored-by: William Fu-Hinthorn <13333726+hinthornw@users.noreply.github.com>	1 year ago
akmhmgc	715bd06f04	Minor text correction (#2298 ) # Description Just fixed sentence :)	1 year ago
Abdulla Al Blooshi	90e388b9f8	Update simple typo in llm_bash md (#2269 )	1 year ago
Harrison Chase	2ffc643086	add listen api docs (#1855 )	2 years ago
Ikko Eltociear Ashimine	9555bbd5bb	Fix typo in sqlite.ipynb (#1828 ) overriden -> overridden	2 years ago
Harrison Chase	2d098e8869	Harrison/agent eval (#1620 ) Co-authored-by: jerwelborn <jeremy.welborn@gmail.com>	2 years ago
Jon Luo	0a1b1806e9	sql: do not hard code the LIMIT clause in the table_info section (#1563 ) Seeing a lot of issues in Discord in which the LLM is not using the correct LIMIT clause for different SQL dialects. ie, it's using `LIMIT` for mssql instead of `TOP`, or instead of `ROWNUM` for Oracle, etc. I think this could be due to us specifying the LIMIT statement in the example rows portion of `table_info`. So the LLM is seeing the `LIMIT` statement used in the prompt. Since we can't specify each dialect's method here, I think it's fine to just replace the `SELECT... LIMIT 3;` statement with `3 rows from table_name table:`, and wrap everything in a block comment directly following the `CREATE` statement. The Rajkumar et al paper wrapped the example rows and `SELECT` statement in a block comment as well anyway. Thoughts @fpingham?	2 years ago
Kacper Łukawski	9ac442624c	Add Qdrant named arguments (#1386 ) This PR: - Increases `qdrant-client` version to 1.0.4 - Introduces custom content and metadata keys (as requested in #1087) - Moves all the `QdrantClient` parameters into the method parameters to simplify code completion	2 years ago
Harrison Chase	1cd8996074	Harrison/summarizer chain (#1356 ) Co-authored-by: Tim Asp <707699+timothyasp@users.noreply.github.com>	2 years ago
Jon Luo	92ab27e4b8	sql doc formatting (#1350 ) My bad, missed a few tabs between the two PRs	2 years ago
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	2 years ago
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!	2 years ago
CG80499	af8f5c1a49	Added constitutional chain. (#1147 ) - Added self-critique constitutional chain based on this [paper](https://www.anthropic.com/constitutional.pdf).	2 years ago
Harrison Chase	45b5640fe5	fix sql (#1141 )	2 years ago
Harrison Chase	5e10e19bfe	Harrison/align table (#1081 ) Co-authored-by: Francisco Ingham <fpingham@gmail.com>	2 years ago
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>	2 years ago
Harrison Chase	f95cedc443	Harrison/sql rows (#915 ) Co-authored-by: Jon Luo <20971593+jzluo@users.noreply.github.com>	2 years ago
Zach Schillaci	4c79100b15	Correct prompt typo + update example for SQLDatabaseChain (#868 ) See https://github.com/hwchase17/langchain/issues/821	2 years ago
Harrison Chase	0de55048b7	return code for pal (#844 )	2 years ago
Harrison Chase	94ae126747	return sql intermediate steps (#792 )	2 years ago
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>	2 years ago
Harrison Chase	6be5f4e4c4	Harrison/sql db chain (#641 ) Co-authored-by: Bruno Bornsztein <bruno.bornsztein@gmail.com>	2 years ago
Harrison Chase	3d43906572	Harrison/new api chain (#623 ) Co-authored-by: Francisco Ingham <fpingham@gmail.com> Co-authored-by: lesscomfortable <pancho_ingham@hotmail.com>	2 years ago
Harrison Chase	1c71fadfdc	more complex sql chain (#619 ) add a more complex sql chain that first subsets the necessary tables	2 years ago
Francisco Ingham	1787c473b8	Custom prompt option for llm_bash and api chains (#612 ) Co-authored-by: lesscomfortable <pancho_ingham@hotmail.com>	2 years ago
Harrison Chase	9f9afbb6a8	add custom prompt for LLMMathChain and SQLDatabase chain (#605 )	2 years ago
Harrison Chase	985496f4be	Docs refactor (#480 ) Big docs refactor! Motivation is to make it easier for people to find resources they are looking for. To accomplish this, there are now three main sections: - Getting Started: steps for getting started, walking through most core functionality - Modules: these are different modules of functionality that langchain provides. Each part here has a "getting started", "how to", "key concepts" and "reference" section (except in a few select cases where it didnt easily fit). - Use Cases: this is to separate use cases (like summarization, question answering, evaluation, etc) from the modules, and provide a different entry point to the code base. There is also a full reference section, as well as extra resources (glossary, gallery, etc) Co-authored-by: Shreya Rajpal <ShreyaR@users.noreply.github.com>	2 years ago

42 Commits (1c68cbdb28f5f6758dfc9ccf21b7f7beff3ba633)