langchain

Commit Graph

Author	SHA1	Message	Date
Zeeland	92ef77da35	fix: remove useless variable k (#6524 ) remove useless variable k --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	1 year ago
Bagatur	7f8ff2a317	add tagger nb (#7637 )	1 year ago
Sidchat95	c5e50c40c9	Fix Document Similarity Check with passed Threshold (#6845 ) Converting the Similarity obtained in the similarity_search_with_score_by_vector method whilst comparing to the passed threshold. This is because the passed threshold is a number between 0 to 1 and is already in the relevance_score_fn format. As of now, the function is comparing two different scoring parameters and that wouldn't work. Dependencies None Issue: Different scores being compared in similarity_search_with_score_by_vector method in FAISS. Tag maintainer @hwchase17 <!-- Thank you for contributing to LangChain! Replace this comment with: - Description: a description of the change, - Issue: the issue # it fixes (if applicable), - Dependencies: any dependencies required for this change, - Tag maintainer: for a quicker response, tag the relevant maintainer (see below), - Twitter handle: we announce bigger features on Twitter. If your PR gets announced and you'd like a mention, we'll gladly shout you out! If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. Maintainer responsibilities: - General / Misc / if you don't know who to tag: @dev2049 - DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev - Models / Prompts: @hwchase17, @dev2049 - Memory: @hwchase17 - Agents / Tools / Toolkits: @vowelparrot - Tracing / Callbacks: @agola11 - Async: @agola11 If no one reviews your PR within a few days, feel free to @-mention the same people again. See contribution guidelines for more information on how to write/run tests, lint, etc: https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md --> --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	1 year ago
Jacob Ajit	a08baa97c5	Use modern OpenAI endpoints for embeddings (#6573 ) - Description: LangChain passes [engine](https://github.com/hwchase17/langchain/blob/master/langchain/embeddings/openai.py#L256) and not `model` as a field when making OpenAI requests. Within the `openai` Python library, for OpenAI requests, this [makes a call](https://github.com/openai/openai-python/blob/main/openai/api_resources/abstract/engine_api_resource.py#L58) to an endpoint of the form `https://api.openai.com/v1/engines/{engine_id}/embeddings`. These endpoints are [deprecated](https://help.openai.com/en/articles/6283125-what-happened-to-engines) in favor of endpoints of the format `https://api.openai.com/v1/embeddings`, where `model` is passed as a parameter in the request body. While these deprecated endpoints continue to function for now, they may not be supported indefinitely and should be avoided in favor of the newer API format. It appears that `engine` was passed in instead of `model` to make both Azure OpenAI and OpenAI calls work similarly. However, the inclusion of `engine` [causes](https://github.com/openai/openai-python/blob/main/openai/api_resources/abstract/engine_api_resource.py#L58) OpenAI to use the deprecated endpoint, requiring a diverging code path for Azure OpenAI calls where `engine` is passed in additionally (Azure OpenAI requires `engine` to specify a deployment, and can optionally take in `model`). In the long-term, it may be worth considering spinning off Azure OpenAI embeddings into a separate class for ease of use and maintenance, similar to the [implementation for chat models](https://github.com/hwchase17/langchain/blob/master/langchain/chat_models/azure_openai.py).	1 year ago
Jacob Lee	cdb93ab5ca	Adds OpenAI functions powered document metadata tagger (#7521 ) Adds a new document transformer that automatically extracts metadata for a document based on an input schema. I also moved `document_transformers.py` to `document_transformers/__init__.py` to group it with this new transformer - it didn't seem to cause issues in the notebook, but let me know if I've done something wrong there. Also had a linter issue I couldn't figure out: ``` MacBook-Pro:langchain jacoblee$ make lint poetry run mypy . docs/dist/conf.py: error: Duplicate module named "conf" (also at "./docs/api_reference/conf.py") docs/dist/conf.py: note: See https://mypy.readthedocs.io/en/stable/running_mypy.html#mapping-file-paths-to-modules for more info docs/dist/conf.py: note: Common resolutions include: a) using `--exclude` to avoid checking one of them, b) adding `__init__.py` somewhere, c) using `--explicit-package-bases` or adjusting MYPYPATH Found 1 error in 1 file (errors prevented further checking) make: *** [lint] Error 2 ``` @rlancemartin @baskaryan --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	1 year ago
Jason Fan	8effd90be0	Add new types of document transformers (#7379 ) - Description: Add two new document transformers that translates documents into different languages and converts documents into q&a format to improve vector search results. Uses OpenAI function calling via the [doctran](https://github.com/psychic-api/doctran/tree/main) library. - Issue: N/A - Dependencies: `doctran = "^0.0.5"` - Tag maintainer: @rlancemartin @eyurtsev @hwchase17 - Twitter handle: @psychicapi or @jfan001 Notes - Adheres to the `DocumentTransformer` abstraction set by @dev2049 in #3182 - refactored `EmbeddingsRedundantFilter` to put it in a file under a new `document_transformers` module - Added basic docs for `DocumentInterrogator`, `DocumentTransformer` as well as the existing `EmbeddingsRedundantFilter` --------- Co-authored-by: Lance Martin <lance@langchain.dev> Co-authored-by: Bagatur <baskaryan@gmail.com>	1 year ago
Piyush Jain	f11d845dee	Fixed validation error when credentials_profile_name, or region_name is not passed (#7629 ) ## Summary This PR corrects the checks for credentials_profile_name, and region_name attributes. This was causing validation exceptions when either of these values were missing during creation of the retriever class. Fixes #7571 #### Requested reviewers: @baskaryan	1 year ago
Jamie Broomall	0e1d7a27c6	WhyLabsCallbackHandler updates (#7621 ) Updates to the WhyLabsCallbackHandler and example notebook - Update dependency to langkit 0.0.6 which defines new helper methods for callback integrations - Update WhyLabsCallbackHandler to use the new `get_callback_instance` so that the callback is mostly defined in langkit - Remove much of the implementation of the WhyLabsCallbackHandler here in favor of the callback instance This does not change the behavior of the whylabs callback handler implementation but is a reorganization that moves some of the implementation externally to our optional dependency package, and should make future updates easier. @agola11	1 year ago
Gaurang Pawar	53722dcfdc	Fixed a typo in pinecone_hybrid_search.ipynb (#7627 ) Fixed a small typo in documentation	1 year ago
Bagatur	1d4db1327a	fix openai structured chain with pydantic (#7622 ) should return pydantic class	1 year ago
Bagatur	ee70d4a0cd	mv tutorials (#7614 )	1 year ago
William FH	9b215e761e	Stop warning when parent run ID not present (#7611 )	1 year ago
William FH	2f848294cb	Rm Warning that Tracing is Experimental (#7612 )	1 year ago
Yaohui Wang	d85c33a5c3	Fix the markdown rendering issue with a code block inside a markdown code block (#6625 ) ### Description - Fix the markdown rendering issue with a code block inside a markdown, using a different number of backticks for the delimiters. Current doc site: <https://python.langchain.com/docs/modules/data_connection/document_transformers/text_splitters/code_splitter#markdown> After fix: <img width="480" alt="image" src="https://github.com/hwchase17/langchain/assets/3115235/d9921d59-64e6-4a34-9c62-79743667f528"> ### Who can review PTAL @dev2049 Co-authored-by: Yaohui Wang <wangyaohui.01@bytedance.com>	1 year ago
Yaroslav Halchenko	0d92a7f357	codespell: workflow, config + some (quite a few) typos fixed (#6785 ) Probably the most boring PR to review ;) Individual commits might be easier to digest --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	1 year ago
Sam	931e68692e	Adds a chain around sympy for symbolic math (#6834 ) - Description: Adds a new chain that acts as a wrapper around Sympy to give LLMs the ability to do some symbolic math. - Dependencies: SymPy --------- Co-authored-by: sreiswig <sreiswig@github.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	1 year ago
Bharat Ramanathan	be29a6287d	feat: add model architecture back to wandb tracer (#6806 ) # Description This PR adds model architecture to the `WandbTracer` from the Serialized Run kwargs. This allows visualization of the calling parameters of an Agent, LLM and Tool in Weights & Biases. 1. Safely serialize the run objects to WBTraceTree model_dict 2. Refactors the run processing logic to be more organized. - Twitter handle: @parambharat --------- Co-authored-by: Bharat Ramanathan <ramanathan.parameshwaran@gohuddl.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	1 year ago
Alex Iribarren	adc96d60b6	Implement Function Callback tracer (#6835 ) Description: I wanted to be able to redirect debug output to a function, but it wasn't very easy. I figured it would make sense to implement a `FunctionCallbackHandler`, and reimplement `ConsoleCallbackHandler` as a subclass that calls the `print` function. Now I can create a simple subclass in my project that calls `logging.info` or whatever I need. Tag maintainer: @agola11 Twitter handle: `@andandaraalex`	1 year ago
Ducasse-Arthur	93a84f6182	Update bedrock.py - support of other endpoint url (esp. for users of … (#7592 ) Added an _endpoint_url_ attribute to Bedrock(LLM) class - I have access to Bedrock only via us-west-2 endpoint and needed to change the endpoint url, this could be useful to other users	1 year ago
Bagatur	22525bad65	bump 231 (#7584 )	1 year ago
Subsegment	6e1000dc8d	docs : Use more meaningful cnosdb examples (#7587 ) This change makes the ecosystem integrations cnosdb documentation more realistic and easy to understand. - change examples of question and table - modify typo and format	1 year ago
Samuel ROZE	f3c9bf5e4b	fix(typo): Clarify the point of `llm_chain` (#7593 ) Fixes a typo introduced in https://github.com/hwchase17/langchain/pull/7080 by @hwchase17. In the example (visible on [the online documentation](https://api.python.langchain.com/en/latest/chains/langchain.chains.conversational_retrieval.base.ConversationalRetrievalChain.html#langchain-chains-conversational-retrieval-base-conversationalretrievalchain)), the `llm_chain` variable is unused as opposed to being used for the question generator. This change makes it clearer.	1 year ago
Alec Flett	6cdd4b5edc	only add handlers if they are new (#7504 ) When using callbacks, there are times when callbacks can be added redundantly: for instance sometimes you might need to create an llm with specific callbacks, but then also create and agent that uses a chain that has those callbacks already set. This means that "callbacks" might get passed down again to the llm at predict() time, resulting in duplicate calls to the `on_llm_start` callback. For the sake of simplicity, I made it so that langchain never adds an exact handler/callbacks object in `add_handler`, thus avoiding the duplicate handler issue. Tagging @hwchase17 for callback review --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	1 year ago
ausboss	50316f6477	Adding LLM wrapper for Kobold AI (#7560 ) - Description: add wrapper that lets you use KoboldAI api in langchain - Issue: n/a - Dependencies: none extra, just what exists in lanchain - Tag maintainer: @baskaryan - Twitter handle: @zanzibased --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	1 year ago
Rohit Kumar Singh	603a0bea29	Fixes incorrect docstore creation in faiss.py (#7026 ) - Description: Current implementation assumes that the length of `texts` and `ids` should be same but if the passed `ids` length is not equal to the passed length of `texts`, current code `dict(zip(index_to_id.values(), documents))` is not failing or giving any warning and silently creating docstores only for the passed `ids` i.e. if `ids = ['A']` and `texts=["I love Open Source","I love langchain"]` then only one `docstore` will be created. But either two docstores should be created assuming same id value for all the elements of `texts` or an error should be raised. - Issue: My change fixes this by using dictionary comprehension instead of `zip`. This was if lengths of `ids` and `texts` mismatches an explicit `IndexError` will be raised. @rlancemartin, @eyurtsev	1 year ago
Tommy Hyeonwoo Kim	3f7213586e	add supported properties for notiondb document loader's metadata (#7570 ) fix #7569 add following properties for Notion DB document loader's metadata - `unique_id` - `status` - `people` @rlancemartin, @eyurtsev (Since this is a change related to `DataLoaders`) --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	1 year ago
Junlin Zhou	5f17c57174	Update chat agents' output parser to extract action by regex (#7511 ) Currently `ChatOutputParser` extracts actions by splitting the text on "```", and then load the second part as a json string. But sometimes the LLM will wrap the action in markdown code block like: ````markdown ```json { "action": "foo", "action_input": "bar" } ``` ```` Splitting text on "```" will cause `OutputParserException` in such case. This PR changes the behaviour to extract the `$JSON_BLOB` by regex, so that it can handle both ` ``` ``` ` and ` ```json ``` ` @hinthornw --------- Co-authored-by: Junlin Zhou <jlzhou@zjuici.com>	1 year ago
Bagatur	ebcb144342	unit test sqlalachemy (#7582 )	1 year ago
Harrison Chase	641fd74baa	Harrison/pg vector move (#7580 )	1 year ago
os1ma	2667ddc686	Fix `make docs_build` and related scripts (#7276 ) Description: a description of the change Fixed `make docs_build` and related scripts which caused errors. There are several changes. First, I made the build of the documentation and the API Reference into two separate commands. This is because it takes less time to build. The commands for documents are `make docs_build`, `make docs_clean`, and `make docs_linkcheck`. The commands for API Reference are `make api_docs_build`, `api_docs_clean`, and `api_docs_linkcheck`. It looked like `docs/.local_build.sh` could be used to build the documentation, so I used that. Since `.local_build.sh` was also building API Rerefence internally, I removed that process. `.local_build.sh` also added some Bash options to stop in error or so. Futher more added `cd "${SCRIPT_DIR}"` at the beginning so that the script will work no matter which directory it is executed in. `docs/api_reference/api_reference.rst` is removed, because which is generated by `docs/api_reference/create_api_rst.py`, and added it to .gitignore. Finally, the description of CONTRIBUTING.md was modified. Issue: the issue # it fixes (if applicable) https://github.com/hwchase17/langchain/issues/6413 Dependencies: any dependencies required for this change `nbdoc` was missing in group docs so it was added. I installed it with the `poetry add --group docs nbdoc` command. I am concerned if any modifications are needed to poetry.lock. I would greatly appreciate it if you could pay close attention to this file during the review. Tag maintainer - General / Misc / if you don't know who to tag: @baskaryan If this PR needs any additional changes, I'll be happy to make them! --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	1 year ago
Pharbie	74c28df363	Update Pinecone Upsert method usage (#7358 ) Description: Refactor the upsert method in the Pinecone class to allow for additional keyword arguments. This change adds flexibility and extensibility to the method, allowing for future modifications or enhancements. The upsert method now accepts the `**kwargs` parameter, which can be used to pass any additional arguments to the Pinecone index. This change has been made in both the `upsert` method in the `Pinecone` class and the `upsert` method in the `similarity_search_with_score` class method. Falls in line with the usage of the upsert method in [Pinecone-Python-Client](`4640c4cf27/pinecone/index.py (L73)`) Issue: [This feature request in Pinecone Repo](https://github.com/pinecone-io/pinecone-python-client/issues/184) Maintainer responsibilities: - General / Misc / if you don't know who to tag: @baskaryan - Memory: @hwchase17 --------- Co-authored-by: kwesi <22204443+yankskwesi@users.noreply.github.com> Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Lance Martin <122662504+rlancemartin@users.noreply.github.com>	1 year ago
Kazuki Maeda	5c3fe8b0d1	Enhance Makefile with 'format_diff' Option and Improved Readability (#7394 ) ### Description: This PR introduces a new option format_diff to the existing Makefile. This option allows us to apply the formatting tools (Black and isort) only to the changed Python and ipynb files since the last commit. This will make our development process more efficient as we only format the codes that we modify. Along with this change, comments were added to make the Makefile more understandable and maintainable. ### Issue: N/A ### Dependencies: Add dependency to black. ### Tag maintainer: @baskaryan ### Twitter handle: [kzk_maeda](https://twitter.com/kzk_maeda) --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	1 year ago
Bagatur	2babe3069f	Revert pinecone v4 support (#7566 ) Revert `9d13dcd`	1 year ago
schop-rob	e811c5e8c6	Add OpenAI organization ID to docs (#7398 ) Description: I added an example of how to reference the OpenAI API Organization ID, because I couldn't find it before. In the example, it is mentioned how to achieve this using environment variables as well as parameters for the OpenAI()-class Issue: - Dependencies: - Twitter @schop-rob	1 year ago
Kenny	8741e55e7c	Template formats documentation (#7404 ) Simple addition to the documentation, adding the correct import statement & showcasing using Python FStrings.	1 year ago
Fielding Johnston	00c466627a	minor bug fix: properly await AsyncRunManager's method call in MulitRouteChain (#7487 ) This simply awaits `AsyncRunManager`'s method call in `MulitRouteChain`. Noticed this while playing around with Langchain's implementation of `MultiPromptChain`. @baskaryan cheers --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	1 year ago
tonomura	cc0585af42	Improvement/add finish reason to generation info in chat open ai (#7478 ) Description: ChatOpenAI model does not return finish_reason in generation_info. Issue: #2702 Dependencies: None Tag maintainer: @baskaryan Thank you --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	1 year ago
Junlin Zhou	b96ac13f3d	Minor update to reference other sql tool by tool names instead of hard coded string. (#7514 ) <!-- Thank you for contributing to LangChain! Replace this comment with: - Description: a description of the change, - Issue: the issue # it fixes (if applicable), - Dependencies: any dependencies required for this change, - Tag maintainer: for a quicker response, tag the relevant maintainer (see below), - Twitter handle: we announce bigger features on Twitter. If your PR gets announced and you'd like a mention, we'll gladly shout you out! If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. Maintainer responsibilities: - General / Misc / if you don't know who to tag: @baskaryan - DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev - Models / Prompts: @hwchase17, @baskaryan - Memory: @hwchase17 - Agents / Tools / Toolkits: @hinthornw - Tracing / Callbacks: @agola11 - Async: @agola11 If no one reviews your PR within a few days, feel free to @-mention the same people again. See contribution guidelines for more information on how to write/run tests, lint, etc: https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md --> Currently there are 4 tools in SQL agent-toolkits, and 2 of them have reference to the other 2. This PR change the reference from hard coded string to `{tool.name}` Co-authored-by: Junlin Zhou <jlzhou@zjuici.com>	1 year ago
OwenElliott	9cb2347453	Fix broken link from Marqo Ecosystem (#7510 ) Small fix to a link from the Marqo page in the ecosystem. The link was not updated correctly when the documentation structure changed to html pages instead of links to notebooks.	1 year ago
Matt Robinson	c4d53f98dc	docs: update unstructured docstrings (#7561 ) ### Summary Updates the docstrings in the Unstructured document loaders to display more useful information on the integrations page.	1 year ago
Ben Auffarth	2c2f0e15a6	clarify about api key (#7540 ) I found it unclear, where to get the API keys for JinaChat. Mentioning this in the docstring should be helpful. #7490 Twitter handle: benji1a @delgermurun	1 year ago
Jona Sassenhagen	0ea7224535	[Minor] Remove tagger from spacy sentencizer (#7534 ) @svlandeg gave me a tip for how to improve a bit on https://github.com/hwchase17/langchain/pull/7442 for some extra speed and memory gains. The tagger isn't needed for sentencization, so can be disabled too.	1 year ago
Kacper Łukawski	1f83b5f47e	Reuse the existing collection if configured properly in Qdrant.from_texts (#7530 ) This PR changes the behavior of `Qdrant.from_texts` so the collection is reused if not requested to recreate it. Previously, calling `Qdrant.from_texts` or `Qdrant.from_documents` resulted in removing the old data which was confusing for many.	1 year ago
Leonid Kuligin	6674b33cf5	Added support for chat_history (#7555 ) #7469 Co-authored-by: Leonid Kuligin <kuligin@google.com>	1 year ago
Felix Brockmeier	406a9dc11f	Add notebook example for Lemon AI NLP Workflow Automation (#7556 ) - Description: Added notebook to LangChain docs that explains how to use Lemon AI NLP Workflow Automation tool with Langchain - Issue: not applicable - Dependencies: not applicable - Tag maintainer: @agola11 - Twitter handle: felixbrockm	1 year ago
Lance Martin	9e067b8cc9	Add env setup (#7550 ) Include setup	1 year ago
Bagatur	3c4338470e	bump 230 (#7544 )	1 year ago
Bagatur	d2137eea9f	fix cpal docs (#7545 )	1 year ago
Boris	9129318466	CPAL (#6255 ) # Causal program-aided language (CPAL) chain ## Motivation This builds on the recent [PAL](https://arxiv.org/abs/2211.10435) to stop LLM hallucination. The problem with the [PAL](https://arxiv.org/abs/2211.10435) approach is that it hallucinates on a math problem with a nested chain of dependence. The innovation here is that this new CPAL approach includes causal structure to fix hallucination. For example, using the below word problem, PAL answers with 5, and CPAL answers with 13. "Tim buys the same number of pets as Cindy and Boris." "Cindy buys the same number of pets as Bill plus Bob." "Boris buys the same number of pets as Ben plus Beth." "Bill buys the same number of pets as Obama." "Bob buys the same number of pets as Obama." "Ben buys the same number of pets as Obama." "Beth buys the same number of pets as Obama." "If Obama buys one pet, how many pets total does everyone buy?" The CPAL chain represents the causal structure of the above narrative as a causal graph or DAG, which it can also plot, as shown below. ![complex-graph](https://github.com/hwchase17/langchain/assets/367522/d938db15-f941-493d-8605-536ad530f576) . The two major sections below are: 1. Technical overview 2. Future application Also see [this jupyter notebook](https://github.com/borisdev/langchain/blob/master/docs/extras/modules/chains/additional/cpal.ipynb) doc. ## 1. Technical overview ### CPAL versus PAL Like [PAL](https://arxiv.org/abs/2211.10435), CPAL intends to reduce large language model (LLM) hallucination. The CPAL chain is different from the PAL chain for a couple of reasons. * CPAL adds a causal structure (or DAG) to link entity actions (or math expressions). * The CPAL math expressions are modeling a chain of cause and effect relations, which can be intervened upon, whereas for the PAL chain math expressions are projected math identities. PAL's generated python code is wrong. It hallucinates when complexity increases. ```python def solution(): """Tim buys the same number of pets as Cindy and Boris.Cindy buys the same number of pets as Bill plus Bob.Boris buys the same number of pets as Ben plus Beth.Bill buys the same number of pets as Obama.Bob buys the same number of pets as Obama.Ben buys the same number of pets as Obama.Beth buys the same number of pets as Obama.If Obama buys one pet, how many pets total does everyone buy?""" obama_pets = 1 tim_pets = obama_pets cindy_pets = obama_pets + obama_pets boris_pets = obama_pets + obama_pets total_pets = tim_pets + cindy_pets + boris_pets result = total_pets return result # math result is 5 ``` CPAL's generated python code is correct. ```python story outcome data name code value depends_on 0 obama pass 1.0 [] 1 bill bill.value = obama.value 1.0 [obama] 2 bob bob.value = obama.value 1.0 [obama] 3 ben ben.value = obama.value 1.0 [obama] 4 beth beth.value = obama.value 1.0 [obama] 5 cindy cindy.value = bill.value + bob.value 2.0 [bill, bob] 6 boris boris.value = ben.value + beth.value 2.0 [ben, beth] 7 tim tim.value = cindy.value + boris.value 4.0 [cindy, boris] query data { "question": "how many pets total does everyone buy?", "expression": "SELECT SUM(value) FROM df", "llm_error_msg": "" } # query result is 13 ``` Based on the comments below, CPAL's intended location in the library is `experimental/chains/cpal` and PAL's location is`chains/pal`. ### CPAL vs Graph QA Both the CPAL chain and the Graph QA chain extract entity-action-entity relations into a DAG. The CPAL chain is different from the Graph QA chain for a few reasons. * Graph QA does not connect entities to math expressions * Graph QA does not associate actions in a sequence of dependence. * Graph QA does not decompose the narrative into these three parts: 1. Story plot or causal model 4. Hypothetical question 5. Hypothetical condition ### Evaluation Preliminary evaluation on simple math word problems shows that this CPAL chain generates less hallucination than the PAL chain on answering questions about a causal narrative. Two examples are in [this jupyter notebook](https://github.com/borisdev/langchain/blob/master/docs/extras/modules/chains/additional/cpal.ipynb) doc. ## 2. Future application ### "Describe as Narrative, Test as Code" The thesis here is that the Describe as Narrative, Test as Code approach allows you to represent a causal mental model both as code and as a narrative, giving you the best of both worlds. #### Why describe a causal mental mode as a narrative? The narrative form is quick. At a consensus building meeting, people use narratives to persuade others of their causal mental model, aka. plan. You can share, version control and index a narrative. #### Why test a causal mental model as a code? Code is testable, complex narratives are not. Though fast, narratives are problematic as their complexity increases. The problem is LLMs and humans are prone to hallucination when predicting the outcomes of a narrative. The cost of building a consensus around the validity of a narrative outcome grows as its narrative complexity increases. Code does not require tribal knowledge or social power to validate. Code is composable, complex narratives are not. The answer of one CPAL chain can be the hypothetical conditions of another CPAL Chain. For stochastic simulations, a composable plan can be integrated with the [DoWhy library](https://github.com/py-why/dowhy). Lastly, for the futuristic folk, a composable plan as code allows ordinary community folk to design a plan that can be integrated with a blockchain for funding. An explanation of a dependency planning application is [here.](https://github.com/borisdev/cpal-llm-chain-demo) --- Twitter handle: @boris_dev --------- Co-authored-by: Boris Dev <borisdev@Boriss-MacBook-Air.local>	1 year ago
Alejandra De Luna	2e4047e5e7	feat: support generate as an early stopping method for `OpenAIFunctionsAgent` (#7229 ) This PR proposes an implementation to support `generate` as an `early_stopping_method` for the new `OpenAIFunctionsAgent` class. The motivation behind is to facilitate the user to set a maximum number of actions the agent can take with `max_iterations` and force a final response with this new agent (as with the `Agent` class). The following changes were made: - The `OpenAIFunctionsAgent.return_stopped_response` method was overwritten to support `generate` as an `early_stopping_method` - A boolean `with_functions` parameter was added to the `OpenAIFunctionsAgent.plan` method This way the `OpenAIFunctionsAgent.return_stopped_response` method can call the `OpenAIFunctionsAgent.plan` method with `with_function=False` when the `early_stopping_method` is set to `generate`, making a call to the LLM with no functions and forcing a final response from the `"assistant"`. - Relevant maintainer: @hinthornw - Twitter handle: @aledelunap --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	1 year ago

1 2 3 4 5 ...

3128 Commits (b8b8a138df0e70a2073682d9082f7cc6ae2acb41) All Branches Search

3128 Commits (b8b8a138df0e70a2073682d9082f7cc6ae2acb41)

All Branches