langchain

Commit Graph

Author	SHA1	Message	Date
Nuno Campos	18af149e91	nc/load (#5733 ) Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	1 year ago
Harrison Chase	704d56e241	support kwargs (#5990 )	1 year ago
Thomas B	ac3e6e3944	Fix IndexError in RecursiveCharacterTextSplitter (#5902 ) Fixes (not reported) an error that may occur in some cases in the RecursiveCharacterTextSplitter. An empty `new_separators` array ([]) would end up in the else path of the condition below and used in a function where it is expected to be non empty. ```python if new_separators is None: ... else: # _split_text() expects this array to be non-empty! other_info = self._split_text(s, new_separators) ``` resulting in an `IndexError` ```python def _split_text(self, text: str, separators: List[str]) -> List[str]: """Split incoming text and return chunks.""" final_chunks = [] # Get appropriate separator to use > separator = separators[-1] E IndexError: list index out of range langchain/text_splitter.py:425: IndexError ``` #### Who can review? @hwchase17 @eyurtsev --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	1 year ago
Harrison Chase	ca1afa7213	add test for structured tools (#5989 )	1 year ago
felpigeon	2791a753bf	Add start index to metadata in TextSplitter (#5912 ) <!-- Thank you for contributing to LangChain! Your PR will appear in our release under the title you set. Please make sure it highlights your valuable contribution. Replace this with a description of the change, the issue it fixes (if applicable), and relevant context. List any dependencies required for this change. After you're done, someone will review your PR. They may suggest improvements. If no one reviews your PR within a few days, feel free to @-mention the same people again, as notifications can get lost. Finally, we'd love to show appreciation for your contribution - if you'd like us to shout you out on Twitter, please also include your handle! --> #### Add start index to metadata in TextSplitter - Modified method `create_documents` to track start position of each chunk - The `start_index` is included in the metadata if the `add_start_index` parameter in the class constructor is set to `True` This enables referencing back to the original document, particularly useful when a specific chunk is retrieved. <!-- If you're adding a new integration, please include: 1. a test for the integration - favor unit tests that does not rely on network access. 2. an example notebook showing its use See contribution guidelines for more information on how to write tests, lint etc: https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md --> #### Who can review? Tag maintainers/contributors who might be interested: @eyurtsev @agola11 <!-- For a quicker response, figure out the right person to tag with @ @hwchase17 - project lead Tracing / Callbacks - @agola11 Async - @agola11 DataLoaders - @eyurtsev Models - @hwchase17 - @agola11 Agents / Tools / Toolkits - @vowelparrot VectorStores / Retrievers / Memory - @dev2049 -->	1 year ago
Lance Martin	4092fd21dc	YoutubeAudioLoader and updates to OpenAIWhisperParser (#5772 ) This introduces the `YoutubeAudioLoader`, which will load blobs from a YouTube url and write them. Blobs are then parsed by `OpenAIWhisperParser()`, as show in this [PR](https://github.com/hwchase17/langchain/pull/5580), but we extend the parser to split audio such that each chuck meets the 25MB OpenAI size limit. As shown in the notebook, this enables a very simple UX: ``` # Transcribe the video to text loader = GenericLoader(YoutubeAudioLoader([url],save_dir),OpenAIWhisperParser()) docs = loader.load() ``` Tested on full set of Karpathy lecture videos: ``` # Karpathy lecture videos urls = ["https://youtu.be/VMj-3S1tku0" "https://youtu.be/PaCmpygFfXo", "https://youtu.be/TCH_1BHY58I", "https://youtu.be/P6sfmUTpUmc", "https://youtu.be/q8SA3rM6ckI", "https://youtu.be/t3YJ5hKiMQ0", "https://youtu.be/kCc8FmEb1nY"] # Directory to save audio files save_dir = "~/Downloads/YouTube" # Transcribe the videos to text loader = GenericLoader(YoutubeAudioLoader(urls,save_dir),OpenAIWhisperParser()) docs = loader.load() ```	1 year ago
Ankush Gola	b177a29d3f	support returning run info for llms, chat models and chains (#5666 ) returning the run id is important for accessing the run later on	1 year ago
Yoann Poupart	65111eb2b3	Attribute support for html tags (#5782 ) # What does this PR do? Change the HTML tags so that a tag with attributes can be found. ## Before submitting - [x] Tests added - [x] CI/CD validated ### Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR.	1 year ago
Zander Chase	204a73c1d9	Use client from LCP-SDK (#5695 ) - Remove the client implementation (this breaks backwards compatibility for existing testers. I could keep the stub in that file if we want, but not many people are using it yet - Add SDK as dependency - Update the 'run_on_dataset' method to be a function that optionally accepts a client as an argument - Remove the langchain plus server implementation (you get it for free with the SDK now) We could make the SDK optional for now, but the plan is to use w/in the tracer so it would likely become a hard dependency at some point.	1 year ago
Ilya	d5b1608216	fix markdown text splitter horizontal lines (#5625 ) Fixes #5614 #### Issue The `**` combination produces an exception when used as a seperator in `re.split`. Instead `\\\` should be used for regex exprations. #### Who can review? @eyurtsev	1 year ago
Lance Martin	aea090045b	Create OpenAIWhisperParser for generating Documents from audio files (#5580 ) # OpenAIWhisperParser This PR creates a new parser, `OpenAIWhisperParser`, that uses the [OpenAI Whisper model](https://platform.openai.com/docs/guides/speech-to-text/quickstart) to perform transcription of audio files to text (`Documents`). Please see the notebook for usage.	1 year ago
Daniel Chalef	0551bc90a5	Zep Hybrid Search (#5742 ) Zep now supports persisting custom metadata with messages and hybrid search across both message embeddings and structured metadata. This PR implements custom metadata and enhancements to the `ZepChatMessageHistory` and `ZepRetriever` classes to implement this support. Tag maintainers/contributors who might be interested: VectorStores / Retrievers / Memory - @dev2049 --------- Co-authored-by: Daniel Chalef <daniel.chalef@private.org>	1 year ago
Tomaz Bratanic	a0ea6f6b6b	Cypher search: Check if generated Cypher is provided in backticks (#5541 ) # Check if generated Cypher code is wrapped in backticks Some LLMs like the VertexAI like to explain how they generated the Cypher statement and wrap the actual code in three backticks: ![Screenshot from 2023-06-01 08-08-23](https://github.com/hwchase17/langchain/assets/19948365/1d8eecb3-d26c-4882-8f5b-6a9bc7e93690) I have observed a similar pattern with OpenAI chat models in a conversational settings, where multiple user and assistant message are provided to the LLM to generate Cypher statements, where then the LLM wants to maybe apologize for previous steps or explain its thoughts. Interestingly, both OpenAI and VertexAI wrap the code in three backticks if they are doing any explaining or apologizing. Checking if the generated cypher is wrapped in backticks seems like a low-hanging fruit to expand the cypher search to other LLMs and conversational settings.	1 year ago
Nathan Azrak	26ec845921	Raise an exception in MKRL and Chat Output Parsers if parsing text which contains both an action and a final answer (#5609 ) Raises exception if OutputParsers receive a response with both a valid action and a final answer Currently, if an OutputParser receives a response which includes both an action and a final answer, they return a FinalAnswer object. This allows the parser to accept responses which propose an action and hallucinate an answer without the action being parsed or taken by the agent. This PR changes the logic to: 1. store a variable checking whether a response contains the `FINAL_ANSWER_ACTION` (this is the easier condition to check). 2. store a variable checking whether the response contains a valid action 3. if both are present, raise a new exception stating that both are present 4. if an action is present, return an AgentAction 5. if an answer is present, return an AgentAnswer 6. if neither is present, raise the relevant exception based around the action format (these have been kept consistent with the prior exception messages) Disclaimer: * Existing mock data included strings which did include an action and an answer. This might indicate that prioritising returning AgentAnswer was always correct, and I am patching out desired behaviour? @hwchase17 to advice. Curious if there are allowed cases where this is not hallucinating, and we do want the LLM to output an action which isn't taken. * I have not passed `send_to_llm` through this new exception Fixes #5601 ## Who can review? Community members can review the PR once tests pass. Tag maintainers/contributors who might be interested: @hwchase17 - project lead @vowelparrot	1 year ago
Harrison Chase	b9040669a0	Harrison/pipeline prompt (#5540 ) idea is to make prompts more composable	1 year ago
Harrison Chase	ad09367a92	Harrison/pubmed integration (#5664 ) Co-authored-by: younis basher <71520361+younis-ba@users.noreply.github.com> Co-authored-by: Younis Bashir <younis@omicmd.com>	1 year ago
Davis Chase	ae3611730a	handle single arg to and/or (#5637 ) @ryderwishart @eyurtsev thoughts on handling this in the parser itself? related to #5570	1 year ago
Zander Chase	20ec1173f4	Update Tracer Auth / Reduce Num Calls (#5517 ) Update the session creation and calls --------- Co-authored-by: Ankush Gola <ankush.gola@gmail.com>	1 year ago
Waldecir Santos	db45970a66	Fix SQLAlchemy truncating text when it is too big (#5206 ) # Fixes SQLAlchemy truncating the result if you have a big/text column with many chars. SQLAlchemy truncates columns if you try to convert a Row or Sequence to a string directly For comparison: - Before: ```[('Harrison', 'That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio ... (2 characters truncated) ... hat is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio ')]``` - After: ```[('Harrison', 'That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio ')]``` ## Who can review? Community members can review the PR once tests pass. Tag maintainers/contributors who might be interested: I'm not sure who to tag for chains, maybe @vowelparrot ?	1 year ago
Harrison Chase	342b671d05	add brave search util (#5538 ) Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>	1 year ago
Harrison Chase	5ce74b5958	code splitter docs (#5480 ) Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>	1 year ago
Ankush Gola	1671c2afb2	py tracer fixes (#5377 )	1 year ago
Blithe	e31705b5ab	convert the parameter 'text' to uppercase in the function 'parse' of the class BooleanOutputParser (#5397 ) when the LLMs output 'yes\|no'，BooleanOutputParser can parse it to 'True\|False', fix the ValueError in parse(). <!-- when use the BooleanOutputParser in the chain_filter.py, the LLMs output 'yes\|no'，the function 'parse' will throw ValueError。 --> Fixes # (issue) #5396 https://github.com/hwchase17/langchain/issues/5396 --------- Co-authored-by: gaofeng27692 <gaofeng27692@hundsun.com>	1 year ago
Harrison Chase	eab4b4ccd7	add simple test for imports (#5461 ) Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>	1 year ago
Janos Tolgyesi	1111f18eb4	Add maximal relevance search to SKLearnVectorStore (#5430 ) # Add maximal relevance search to SKLearnVectorStore This PR implements the maximum relevance search in SKLearnVectorStore. Twitter handle: jtolgyesi (I submitted also the original implementation of SKLearnVectorStore) ## Before submitting Unit tests are included. Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>	1 year ago
Matt Wells	1d861dc37a	MRKL output parser no longer breaks well formed queries (#5432 ) # Handles the edge scenario in which the action input is a well formed SQL query which ends with a quoted column There may be a cleaner option here (or indeed other edge scenarios) but this seems to robustly determine if the action input is likely to be a well formed SQL query in which we don't want to arbitrarily trim off `"` characters Fixes #5423 ## Who can review? Community members can review the PR once tests pass. Tag maintainers/contributors who might be interested: For a quicker response, figure out the right person to tag with @ @hwchase17 - project lead Agents / Tools / Toolkits - @vowelparrot	1 year ago
ByronHsu	9d658aaa5a	Add more code splitters (go, rst, js, java, cpp, scala, ruby, php, swift, rust) (#5171 ) As the title says, I added more code splitters. The implementation is trivial, so i don't add separate tests for each splitter. Let me know if any concerns. Fixes # (issue) https://github.com/hwchase17/langchain/issues/5170 ## Who can review? Community members can review the PR once tests pass. Tag maintainers/contributors who might be interested: @eyurtsev @hwchase17 --------- Signed-off-by: byhsu <byhsu@linkedin.com> Co-authored-by: byhsu <byhsu@linkedin.com>	1 year ago
UmerHA	8259f9b7fa	DocumentLoader for GitHub (#5408 ) # Creates GitHubLoader (#5257) GitHubLoader is a DocumentLoader that loads issues and PRs from GitHub. Fixes #5257 --------- Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>	1 year ago
German Martin	0b3e0dd1d2	New Trello document loader (#4767 ) # Added New Trello loader class and documentation Simple Loader on top of py-trello wrapper. With a board name you can pull cards and to do some field parameter tweaks on load operation. I included documentation and examples. Included unit test cases using patch and a fixture for py-trello client class. --------- Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>	1 year ago
Harrison Chase	72f99ff953	Harrison/text splitter (#5417 ) adds support for keeping separators around when using recursive text splitter	1 year ago
小铭	cf5803e44c	Add ToolException that a tool can throw. (#5050 ) # Add ToolException that a tool can throw This is an optional exception that tool throws when execution error occurs. When this exception is thrown, the agent will not stop working,but will handle the exception according to the handle_tool_error variable of the tool,and the processing result will be returned to the agent as observation,and printed in pink on the console.It can be used like this: ```python from langchain.schema import ToolException from langchain import LLMMathChain, SerpAPIWrapper, OpenAI from langchain.agents import AgentType, initialize_agent from langchain.chat_models import ChatOpenAI from langchain.tools import BaseTool, StructuredTool, Tool, tool from langchain.chat_models import ChatOpenAI llm = ChatOpenAI(temperature=0) llm_math_chain = LLMMathChain(llm=llm, verbose=True) class Error_tool: def run(self, s: str): raise ToolException('The current search tool is not available.') def handle_tool_error(error) -> str: return "The following errors occurred during tool execution:"+str(error) search_tool1 = Error_tool() search_tool2 = SerpAPIWrapper() tools = [ Tool.from_function( func=search_tool1.run, name="Search_tool1", description="useful for when you need to answer questions about current events.You should give priority to using it.", handle_tool_error=handle_tool_error, ), Tool.from_function( func=search_tool2.run, name="Search_tool2", description="useful for when you need to answer questions about current events", return_direct=True, ) ] agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True, handle_tool_errors=handle_tool_error) agent.run("Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?") ``` ![image](https://github.com/hwchase17/langchain/assets/32786500/51930410-b26e-4f85-a1e1-e6a6fb450ada) ## Who can review? - @vowelparrot --------- Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>	1 year ago
Harrison Chase	2da8c48be1	Harrison/datetime parser (#4693 ) Co-authored-by: Jacob Valdez <jacobfv@msn.com> Co-authored-by: Jacob Valdez <jacob.valdez@limboid.ai> Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	1 year ago
Eduard van Valkenburg	ccb6238de1	Implemented appending arbitrary messages (#5293 ) # Implemented appending arbitrary messages to the base chat message history, the in-memory and cosmos ones. <!-- Thank you for contributing to LangChain! Your PR will appear in our next release under the title you set. Please make sure it highlights your valuable contribution. Replace this with a description of the change, the issue it fixes (if applicable), and relevant context. List any dependencies required for this change. After you're done, someone will review your PR. They may suggest improvements. If no one reviews your PR within a few days, feel free to @-mention the same people again, as notifications can get lost. --> As discussed this is the alternative way instead of #4480, with a add_message method added that takes a BaseMessage as input, so that the user can control what is in the base message like kwargs. <!-- Remove if not applicable --> Fixes # (issue) ## Before submitting <!-- If you're adding a new integration, include an integration test and an example notebook showing its use! --> ## Who can review? Community members can review the PR once tests pass. Tag maintainers/contributors who might be interested: @hwchase17 --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	1 year ago
Gael Grosch	8b7721ebbb	fix: Blob.from_data mimetype is lost (#5395 ) # Fix lost mimetype when using Blob.from_data method The mimetype is lost due to a typo in the class attribue name Fixes # - (no issue opened but I can open one if needed) ## Changes * Fixed typo in name * Added unit-tests to validate the output Blob ## Review @eyurtsev	1 year ago
Harrison Chase	6df90ad9fd	handle json parsing errors (#5371 ) adds tests cases, consolidates a lot of PRs	1 year ago
os1ma	1366d070fc	Add path validation to DirectoryLoader (#5327 ) # Add path validation to DirectoryLoader This PR introduces a minor adjustment to the DirectoryLoader by adding validation for the path argument. Previously, if the provided path didn't exist or wasn't a directory, DirectoryLoader would return an empty document list due to the behavior of the `glob` method. This could potentially cause confusion for users, as they might expect a file-loading error instead. So, I've added two validations to the load method of the DirectoryLoader: - Raise a FileNotFoundError if the provided path does not exist - Raise a ValueError if the provided path is not a directory Due to the relatively small scope of these changes, a new issue was not created. ## Before submitting <!-- If you're adding a new integration, please include: 1. a test for the integration - favor unit tests that does not rely on network access. 2. an example notebook showing its use See contribution guidelines for more information on how to write tests, lint etc: https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md --> ## Who can review? Community members can review the PR once tests pass. Tag maintainers/contributors who might be interested: @eyurtsev	1 year ago
Janos Tolgyesi	5f4552391f	Add SKLearnVectorStore (#5305 ) # Add SKLearnVectorStore This PR adds SKLearnVectorStore, a simply vector store based on NearestNeighbors implementations in the scikit-learn package. This provides a simple drop-in vector store implementation with minimal dependencies (scikit-learn is typically installed in a data scientist / ml engineer environment). The vector store can be persisted and loaded from json, bson and parquet format. SKLearnVectorStore has soft (dynamic) dependency on the scikit-learn, numpy and pandas packages. Persisting to bson requires the bson package, persisting to parquet requires the pyarrow package. ## Before submitting Integration tests are provided under `tests/integration_tests/vectorstores/test_sklearn.py` Sample usage notebook is provided under `docs/modules/indexes/vectorstores/examples/sklear.ipynb` Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>	1 year ago
Harrison Chase	179ddbe88b	add enum output parser (#5165 )	1 year ago
Davis Chase	ca88b25da6	Zep sdk version (#5267 ) zep-python's sync methods no longer need an asyncio wrapper. This was causing issues with FastAPI deployment. Zep also now supports putting and getting of arbitrary message metadata. Bump zep-python version to v0.30 Remove nest-asyncio from Zep example notebooks. Modify tests to include metadata. --------- Co-authored-by: Daniel Chalef <daniel.chalef@private.org> Co-authored-by: Daniel Chalef <131175+danielchalef@users.noreply.github.com>	1 year ago
Eugene Yurtsev	5cfa72a130	Bibtex integration for document loader and retriever (#5137 ) # Bibtex integration Wrap bibtexparser to retrieve a list of docs from a bibtex file. * Get the metadata from the bibtex entries * `page_content` get from the local pdf referenced in the `file` field of the bibtex entry using `pymupdf` * If no valid pdf file, `page_content` set to the `abstract` field of the bibtex entry * Support Zotero flavour using regex to get the file path * Added usage example in `docs/modules/indexes/document_loaders/examples/bibtex.ipynb` --------- Co-authored-by: Sébastien M. Popoff <sebastien.popoff@espci.fr> Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>	1 year ago
ByronHsu	f0730c6489	Allow readthedoc loader to pass custom html tag (#5175 ) ## Description The html structure of readthedocs can differ. Currently, the html tag is hardcoded in the reader, and unable to fit into some cases. This pr includes the following changes: 1. Replace `find_all` with `find` because we just want one tag. 2. Provide `custom_html_tag` to the loader. 3. Add tests for readthedoc loader 4. Refactor code ## Issues See more in https://github.com/hwchase17/langchain/pull/2609. The problem was not completely fixed in that pr. --------- Signed-off-by: byhsu <byhsu@linkedin.com> Co-authored-by: byhsu <byhsu@linkedin.com> Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>	1 year ago
Tommaso De Lorenzo	52714cedd4	fixing total cost finetuned model giving zero (#5144 ) # OpanAI finetuned model giving zero tokens cost Very simple fix to the previously committed solution to allowing finetuned Openai models. Improves #5127 --------- Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>	1 year ago
Harrison Chase	94cf391ef1	standardize json parsing (#5168 ) Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>	1 year ago
Davis Chase	2b2176a3c1	tfidf retriever (#5114 ) Co-authored-by: vempaliakhil96 <vempaliakhil96@gmail.com>	1 year ago
Tian Wei	d7f807b71f	Add AzureCognitiveServicesToolkit to call Azure Cognitive Services API (#5012 ) # Add AzureCognitiveServicesToolkit to call Azure Cognitive Services API: achieve some multimodal capabilities This PR adds a toolkit named AzureCognitiveServicesToolkit which bundles the following tools: - AzureCogsImageAnalysisTool: calls Azure Cognitive Services image analysis API to extract caption, objects, tags, and text from images. - AzureCogsFormRecognizerTool: calls Azure Cognitive Services form recognizer API to extract text, tables, and key-value pairs from documents. - AzureCogsSpeech2TextTool: calls Azure Cognitive Services speech to text API to transcribe speech to text. - AzureCogsText2SpeechTool: calls Azure Cognitive Services text to speech API to synthesize text to speech. This toolkit can be used to process image, document, and audio inputs. --------- Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>	1 year ago
Eugene Yurtsev	d56313acba	Improve effeciency of TextSplitter.split_documents, iterate once (#5111 ) # Improve TextSplitter.split_documents, collect page_content and metadata in one iteration ## Who can review? Community members can review the PR once tests pass. Tag maintainers/contributors who might be interested: @eyurtsev In the case where documents is a generator that can only be iterated once making this change is a huge help. Otherwise a silent issue happens where metadata is empty for all documents when documents is a generator. So we expand the argument from `List[Document]` to `Union[Iterable[Document], Sequence[Document]]` --------- Co-authored-by: Steven Tartakovsky <tartakovsky.developer@gmail.com>	1 year ago
Gergely Imreh	69de33e024	Add Mastodon toots loader (#5036 ) # Add Mastodon toots loader. Loader works either with public toots, or Mastodon app credentials. Toot text and user info is loaded. I've also added integration test for this new loader as it works with public data, and a notebook with example output run now. --------- Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>	1 year ago
Eduard van Valkenburg	1cb04f2b26	PowerBI major refinement in working of tool and tweaks in the rest (#5090 ) # PowerBI major refinement in working of tool and tweaks in the rest I've gained some experience with more complex sets and the earlier implementation had too many tries by the agent to create DAX, so refactored the code to run the LLM to create dax based on a question and then immediately run the same against the dataset, with retries and a prompt that includes the error for the retry. This works much better! Also did some other refactoring of the inner workings, making things clearer, more concise and faster.	1 year ago
hwaking	e57ebf3922	add get_top_k_cosine_similarity method to get max top k score and index (#5059 ) # Row-wise cosine similarity between two equal-width matrices and return the max top_k score and index, the score all greater than threshold_score. Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>	1 year ago
Deepak S V	5cd12102be	Improving Resilience of MRKL Agent (#5014 ) This is a highly optimized update to the pull request https://github.com/hwchase17/langchain/pull/3269 Summary: 1) Added ability to MRKL agent to self solve the ValueError(f"Could not parse LLM output: `{llm_output}`") error, whenever llm (especially gpt-3.5-turbo) does not follow the format of MRKL Agent, while returning "Action:" & "Action Input:". 2) The way I am solving this error is by responding back to the llm with the messages "Invalid Format: Missing 'Action:' after 'Thought:'" & "Invalid Format: Missing 'Action Input:' after 'Action:'" whenever Action: and Action Input: are not present in the llm output respectively. For a detailed explanation, look at the previous pull request. New Updates: 1) Since @hwchase17 , requested in the previous PR to communicate the self correction (error) message, using the OutputParserException, I have added new ability to the OutputParserException class to store the observation & previous llm_output in order to communicate it to the next Agent's prompt. This is done, without breaking/modifying any of the functionality OutputParserException previously performs (i.e. OutputParserException can be used in the same way as before, without passing any observation & previous llm_output too). --------- Co-authored-by: Deepak S V <svdeepak99@users.noreply.github.com>	1 year ago

1 2 3 4 5 ...

307 Commits (18af149e91e62b3ac7728ddea420688d41043734)