Zep Authentication

[danielchalef]

• 2markdown loader (2markdown loader #4796)
• Add dev option (Add dev option #4828)
• Add Support for Flexible Input Format for LLM and Chat Model Runs (Add Support for Flexible Input Format for LLM and Chat Model Runs #4805)
• Typos (Typos #4851)
• Remove unnecessary comment (Remove unnecessary comment #4845)
• bump 172 (bump 172 #4864)
• Hugging Face Loader: Add lazy load (Hugging Face Loader: Add lazy load #4799)
• Fix TypeError in Vectorstore Redis class methods (Fix TypeError in Vectorstore Redis class methods #4857)
• Add beautiful soup 4 to extended testing extra (Add beautiful soup 4 to extended testing extra #4869)
• Remove unused variables in Milvus vectorstore (Remove unused variables in Milvus vectorstore #4868)
• Update getting_started.ipynb (Update getting_started.ipynb #4850)
• docs retriever improvements (docs retriever improvements #4430)
• fix homepage typo (fix homepage typo #4883)
• Tiny code review and docs fix for Docugami DataLoader (Tiny code review and docs fix for Docugami DataLoader #4877)
• feat(Add FastAPI + Vercel deployment option): (feat(Add FastAPI + Vercel deployment option): #4520)
• Bold Crumbs (Bold Crumbs #4876)
• ConversationalChatAgent: Allow customizing TEMPLATE_TOOL_RESPONSE (ConversationalChatAgent: Allow customizing TEMPLATE_TOOL_RESPONSE #2361)
• Faiss no avx2 (Faiss no avx2 #4895)
• Add a generic document loader (Add a generic document loader #4875)
• Add html parsers (Add html parsers #4874)
• Cadlabs/python tool sanitization (Cadlabs/python tool sanitization #4754)
• Zep memory (Zep memory #4898)
• Update gallery (Update gallery #4873)
• Fix AzureOpenAI embeddings documentation example. model -> deployment (Fix AzureOpenAI embeddings documentation example. model -> deployment #4389)
• Update getting_started.md (Update getting_started.md #4482)
• docs: text splitters improvements (docs: text splitters improvements #4490)
• Harrison/serper api bug (Harrison/serper api bug #4902)
• Harrison/faiss norm (Harrison/faiss norm #4903)
• Harrison/improved retry tool (Harrison/improved retry tool #4842)
• Harrison/unified objectives (Harrison/unified objectives #4905)
• bump version to 173 (bump version to 173 #4910)
• Load specific file types from Google Drive (issue Add the possibility to define what file types you want to load from a Google Drive #4878) (Load specific file types from Google Drive (issue #4878) #4926)
• API update: Engines -> Models (API update: Engines -> Models #4915)
• feat TextLoader: auto detect file encodings #4479: TextLoader auto detect encoding and improved exceptions (feat #4479: TextLoader auto detect encoding and improved exceptions #4927)
• Fix bilibili (Fix bilibili #4860)
• Add human message as input variable to chat agent prompt creation (Add human message as input variable to chat agent prompt creation #4542)
• add alias for model (add alias for model #4553)
• dont error on sql import (dont error on sql import #4647)
• docs: compound ecosystem and integrations (docs: compound ecosystem and integrations #4870)
• Update GPT4ALL integration (Update GPT4ALL integration #4567)
• FIX: GPTCache cache_obj creation loop (FIX: GPTCache cache_obj creation loop #4827)
• Redis kwargs fix (Redis kwargs fix #4936)
• Update redis integration tests (Update redis integration tests #4937)
• docs supabase update (docs supabase update #4935)
• Correct typo in APIChain example notebook (Farenheit -> Fahrenheit) (Correct typo in APIChain example notebook (Farenheit -> Fahrenheit) #4938)
• fix: error in gptcache example nb (fix: error in example code #4930)
• Update custom_multi_action_agent.ipynb (Update custom_multi_action_agent.ipynb #4931)
• docs: added ecosystem/dependents page (docs: added ecosystem/dependents page #4941)
• docs: vectorstores, different updates and fixes (docs: vectorstores, different updates and fixes #4939)
• Chatconv agent: output parser exception (Chatconv agent: output parser exception #4923)
• Zep Retriever - Vector Search Over Chat History (Zep Retriever - Vector Search Over Chat History #4533)
• Fix get_num_tokens for Anthropic models (Fix get_num_tokens for Anthropic models #4911)
• NIT: Instead of hardcoding k in each definition, define it as a param above. (NIT: Instead of hardcoding k in each definition, define it as a param above. #2675)
• [nit] Simplify Spark Creation Validation Check A Little Bit ([nit] Simplify Spark Creation Validation Check A Little Bit #4761)
• Fix for syntax when setting search_path for Snowflake database (Fix for syntax when setting search_path for Snowflake database #4747)
• Harrison/spell executor (Harrison/spell executor #4914)
• Add Spark SQL support (Add Spark SQL support #4602) (Add Spark SQL support (#4602) #4956)
• Support Databricks in SQLDatabase (Support Databricks in SQLDatabase #4702)
• Fixed assumptions misspelling (Fixed assumptions misspelling #4961)
• Update tutorials.md (Update tutorials.md #4960)
• Update planner_prompt.py (Update planner_prompt.py #4967)
• power bi api wrapper integration tests & bug fix (power bi api wrapper integration tests & bug fix #4983)
• bump v0.0.174 (bump v0.0.174 #4988)
• Remove autoreload in examples (Remove autoreload in examples #4994)
• Bug fixes and error handling in Redis - Vectorstore (Bug fixes and error handling in Redis - Vectorstore #4932)
• Add async search with relevance score (Add async search with relevance score #4558)
• Make test gha workflow manually runnable (Make test gha workflow manually runnable #4998)
• Adds 'IN' metadata filter for pgvector for checking set presence (Adds 'IN' metadata filter for pgvector for checking set presence #4982)
• Update python.py (Update python.py #4971)
• PGVector logger message level (PGVector logger message level #4920)
• feature/4493 Improve Evernote Document Loader (feature/4493 Improve Evernote Document Loader #4577)
• Fix graphql tool (Fix graphql tool #4984)
• changed ValueError to ImportError (changed ValueError to ImportError #5006)
• docs: Big Mendable Improvements (docs: Big Mendable Improvements #4964)
• added instruction about pip install google-gerativeai (added instruction about pip install google-generativeai #5004)
• Update the GPTCache example (Update the GPTCache example #4985)
• Revert "API update: Engines -> Models (API update: Engines -> Models #4915)" (Revert "API update: Engines -> Models (#4915)" #5008)
• Add self query translator for weaviate vectorstore (Add self query translator for weaviate vectorstore #4804)
• Check for single prompt in call method of the BaseLLM class (Check for single prompt in __call__ method of the BaseLLM class #4892)
• Add logs command (Add logs command #5007)
• fix prompt saving (fix prompt saving #4987)
• Streaming only final output of agent (using a Agent and wanted to stream just the final response #2483) (Streaming only final output of agent (#2483) #4630)
• bump v175 (bump v175 #5041)
• Fix annoying typo in docs (Fix annoying typo in docs #5029)
• Add documentation for Databricks integration (Add documentation for Databricks integration #5013)
• DOC: Misspelling in agents.rst documentation (DOC: Misspelling in agents.rst documentation #5038)
• change to type checking (change to type checking #5062)
• Harrison/psychic (Harrison/psychic #5063)
• bump to 176 (bump to 176 #5064)
• move docs
• feat: batch multiple files in a single Unstructured API request (feat: batch multiple files in a single Unstructured API request #4525)
• preserve language in conversation retrieval (preserve language in conversation retrieval #4969)
• docs: Deployments page moved into Ecosystem/ (docs: Deployments page moved into Ecosystem/ #4949)
• Separate Runner Functions from Client (Separate Runner Functions from Client #5079)
• Add 'get_token_ids' method (Add 'get_token_ids' method #4784)
• Improved query, print & exception handling in REPL Tool (Improved query, print & exception handling in REPL Tool #4997)
• Harrison/neo4j (Harrison/cypher #5078)
• Bump 177 (Bump 177 #5095)
• fix: revert docarray explicit transitive dependencies and use extras instead (fix: revert docarray explicit transitive dependencies and use extras instead #5015)
• Improving Resilience of MRKL Agent (Improving Resilience of MRKL Agent #5014)
• Improve pinecone hybrid search retriever adding metadata support ( Improve pinecone hybrid search retriever adding metadata support #5098)
• Add the usage of SSL certificates for Elasticsearch and user password authentication (Add the usage of SSL certificates for Elasticsearch and user password authentication #5058)
• add get_top_k_cosine_similarity method to get max top k score and index (add get_top_k_cosine_similarity method to get max top k score and index #5059)
• PowerBI major refinement in working of tool and tweaks in the rest (PowerBI major refinement in working of tool and tweaks in the rest #5090)
• fix: add_texts method of Weaviate vector store creats wrong embeddings (fix: add_texts method of Weaviate vector store creats wrong embeddings #4933)
• update langchainplus client and docker file to reflect port changes (update langchainplus client and docker file to reflect port changes #5005)
• Fixed import error for AutoGPT e.g. from langchain.experimental.auton… (Fixed import error for AutoGPT e.g. from langchain.experimental.auton… #5101)
• Update serpapi.py (Update serpapi.py #4947)
• changed ValueError to ImportError (changed ValueError to ImportError #5103)
• fix: assign current_time to datetime.now() if current_time is None (fix: assign current_time to datetime.now() if current_time is None #5045)
• Add Mastodon toots loader (Add Mastodon toots loader #5036)
• Add OpenLM LLM multi-provider (Add OpenLM LLM multi-provider #4993)
• Pass Dataset Name by Name not Position (Pass Dataset Name by Name not Position #5108)
• Fixes issue Add option to use _additional fields while executing a Weaviate query #5072 - adds additional support to Weaviate (Fixes issue #5072 - adds additional support to Weaviate #5085)
• Improve effeciency of TextSplitter.split_documents, iterate once (Improve effeciency of TextSplitter.split_documents, iterate once #5111)
• WhyLabs callback (WhyLabs callback #4906)
• Add AzureCognitiveServicesToolkit to call Azure Cognitive Services API (Add AzureCognitiveServicesToolkit to call Azure Cognitive Services API #5012)
• Add link to Psychic from document loaders documentation page (Add link to Psychic from document loaders documentation page #5115)
• bump 178 (bump 178 #5130)
• docs: fix minor typo + add wikipedia package installation part in human_input_llm.ipynb (docs: fix minor typo + add wikipedia package installation part in human_input_llm.ipynb #5118)
• solving About fine tune model #2887 (solving #2887 #5127)
• Improve PlanningOutputParser whitespace handling (Improve PlanningOutputParser whitespace handling #5143)
• Add ElasticsearchEmbeddings class for generating embeddings using Elasticsearch models (Add ElasticsearchEmbeddings class for generating embeddings using Elasticsearch models #3401)
• Adding Weather Loader (Adding Weather Loader #5056)
• Add MosaicML inference endpoints (Add MosaicML inference endpoints #4607)
• Empty check before pop (Empty check before pop #4929)
• Add async versions of predict() and predict_messages() (Add async versions of predict() and predict_messages() #4867)
• fix: fix current_time=Now bug for aadd_documents in TimeWeightedRetriever (fix: fix current_time=Now bug for aadd_documents in TimeWeightedRetriever #5155)
• Docs: updated getting_started.md (Docs: updated getting_started.md #5151)
• Clarification of the reference to the "get_text_legth" function in ge… (Clarification of the reference to the "get_text_legth" function in ge… #5154)
• docs: added missed document_loaders examples (docs: added missed document_loaders examples #5150)
• Add Typesense vector store (Add Typesense vector store #1674)
• Vectara (Vectara #5069)
• Beam (Beam #4996)
• Update rellm_experimental.ipynb (Update rellm_experimental.ipynb #5189)
• example usage (example usage #5182)
• adjust docarray docstrings (adjust docarray docstrings #5185)
• bump 179 (bump 179 #5200)
• Harrison/modelscope (Harrison/modelscope #5156)
• Reuse length_func in MapReduceDocumentsChain (Reuse length_func in MapReduceDocumentsChain #5181)
• Update Cypher QA prompt (Update Cypher QA prompt #5173)
• Improve weaviate vectorstore docs (Improve weaviate vectorstore docs #5201)
• tfidf retriever (tfidf retriever #5114)
• standardize json parsing (standardize json parsing #5168)
• fixing total cost finetuned model giving zero (fixing total cost finetuned model giving zero #5144)
• Fixes scope of query Session in PGVector (Fixes scope of query Session in PGVector #5194)
• Output parsing variation allowance (Output parsing variation allowance #5178)
• Allow readthedoc loader to pass custom html tag (Allow readthedoc loader to pass custom html tag #5175)
• Add Iugu document loader (add a Iugu loader #5162)
• Add Joplin document loader (Add Joplin document loader #5153)
• nit (nit #5208)
• add option to pass openai key to langchain plus command (add option to pass openai key to langchain plus command #5213)
• Log warning (Log warning #5192)
• Add Delete Session Method (Add Delete Session Method #5193)
• Add 'status' command to get server status (Add 'status' command to get server status #5197)
• Harrison/vertex (Harrison/vertex #5049)
• fix a mistake in concepts.md (fix a mistake in concepts.md #5222)
• Create async copy of from_text() inside GraphIndexCreator. (Create async copy of from_text() inside GraphIndexCreator. #5214)
• Remove API key from docs (Remove API key from docs #5223)
• Change Default GoogleDriveLoader Behavior to not Load Trashed Files (issue GoogleDriveLoader seems to be pulling trashed documents from the folder #5104) (Change Default GoogleDriveLoader Behavior to not Load Trashed Files (issue #5104) #5220)
• Allow to specify ID when adding to the FAISS vectorstore. (Allow to specify ID when adding to the FAISS vectorstore. #5190)
• Bibtex integration for document loader and retriever (Bibtex integration for document loader and retriever #5137)
• Add MiniMax embeddings (Add MiniMax embeddings #5174)
• Weaviate: Add QnA with sources example (Weaviate: Add QnA with sources example #5247)
• Fix typo in docstring of RetryWithErrorOutputParser (Fix typo in docstring of RetryWithErrorOutputParser #5244)
• bump 180 (bump 180 #5248)
• remove extra "\n" to ensure that the format of the description, examp… (remove extra "\n" to ensure that the format of the description, examp… #5232)
• Resolve error in StructuredOutputParser docs (Resolve error in StructuredOutputParser docs #5240)
• Added the option of specifying a proxy for the OpenAI API (Added the option of specifying a proxy for the OpenAI API #5246)
• OpenSearch top k parameter fix (OpenSearch top k parameter fix #5216)
• Fixed regression in JoplinLoader's get note url (Fixed regression in JoplinLoader's get note url #5265)
• Docs link custom agent page in getting started (Docs link custom agent page in getting started #5250)
• Zep sdk version (Zep sdk version #5267)
• Add C Transformers for GGML Models (Add C Transformers for GGML Models #5218)
• Add visible_only and strict_mode options to ClickTool (Add visible_only and strict_mode options to ClickTool #4088)
• Add Multi-CSV/DF support in CSV and DataFrame Toolkits (Add Multi-CSV/DF support in CSV and DataFrame Toolkits #5009)
• OpenAI lint (OpenAI lint #5273)
• Added pipline args to HuggingFacePipeline.from_model_id (Added pipline args to HuggingFacePipeline.from_model_id #5268)
• Support bigquery dialect - SQL (Support bigquery dialect - SQL #5261)
• feat: add Momento as a standard cache and chat message history provider (feat: add Momento as a standard cache and chat message history provider #5221)
• Fixed typo: 'ouput' to 'output' in all documentation (Fixed typo: 'ouput' to 'output' in all documentation #5272)
• Tedma4/twilio tool (Tedma4/twilio tool #5136)
• LLM wrapper for Databricks (LLM wrapper for Databricks #5142)
• Add an example to make the prompt more robust (Add an example to make the prompt more robust #5291)
• Update CONTRIBUTION guidelines and PR Template (Update CONTRIBUTION guidelines and PR Template #5140)
• Fixed passing creds to VertexAI LLM (Fixed passing creds to VertexAI LLM #5297)
• bump 181 (bump 181 #5302)
• Better docs for weaviate hybrid search (Better docs for weaviate hybrid search #5290)
• Add instructions to pyproject.toml (Add instructions to pyproject.toml #5138)
• docs: improve flow of llm caching notebook (docs: improve flow of llm caching notebook #5309)
• Fix typos (Fix typos #5323)
• docs: added link to LangChain Handbook (docs: added link to LangChain Handbook #5311)
• add enum output parser (add enum output parser #5165)
• add enum output parser (add enum output parser #5165)
• Add Chainlit to deployment options (Add Chainlit to deployment options #5314)
• Fixing blank thoughts in verbose for "_Exception" Action (Fixing blank thoughts in verbose for "_Exception" Action #5331)
• fix: remove empty lines that cause InvalidRequestError (fix: remove empty lines that cause InvalidRequestError #5320)
• Sample Notebook for DynamoDB Chat Message History (Sample Notebook for DynamoDB Chat Message History #5351)
• added cosmos kwargs option (added cosmos kwargs option #5292)
• feat: support for shopping search in SerpApi (feat: support for shopping search in SerpApi #5259)
• Add SKLearnVectorStore (Add SKLearnVectorStore #5305)
• bump 182 (bump 182 #5364)
• Fixes iter error in FAISS add_embeddings call (Fixes iter error in FAISS add_embeddings call #5367)
• revert bad json (revert bad json #5370)
• bump to 183 (bump to 183 #5372)
• Add path validation to DirectoryLoader (Add path validation to DirectoryLoader #5327)
• Fix: Handle empty documents in ContextualCompressionRetriever (Issue CohereAPIError thrown when base retriever returns empty documents in ContextualCompressionRetriever using Cohere Rank #5304) (Fix: Handle empty documents in ContextualCompressionRetriever (Issue #5304) #5306)
• handle json parsing errors (handle json parsing errors #5371)
• Use Default Factory (Use Default Factory #5380)
• Update PR template with Twitter handle request (Update PR template with Twitter handle request #5382)
• fix: Blob.from_data mimetype is lost (fix: Blob.from_data mimetype is lost #5395)
• Add async support to routing chains (Add async support to routing chains #5373)
• Fix update_document function, add test and documentation. (Fix update_document function, add test and documentation. #5359)
• Update llamacpp demonstration notebook (Update llamacpp demonstration notebook #5344)
• Removed deprecated llm attribute for load_chain (Removed deprecated llm attribute for load_chain #5343)
• Harrison/llamacpp (Harrison/llamacpp #5402)
• Add pagination for Vertex AI embeddings (Add pagination for Vertex AI embeddings #5325)
• Reformat openai proxy setting as code (Reformat openai proxy setting as code #5330)
• Harrison/deep infra (Harrison/deep infra #5403)
• Harrison/prediction guard update (Harrison/prediction guard update #5404)
• Implemented appending arbitrary messages (Implemented appending arbitrary messages #5293)
• docs: ecosystem/integrations update 2 (docs: ecosystem/integrations update 2 #5282)
• docs: ecosystem/integrations update 1 (docs: ecosystem/integrations update 1 #5219)
• Harrison/datetime parser (Harrison/datetime parser #4693)
• bump version 184 (bump version 184 #5407)
• Add ToolException that a tool can throw. (Add ToolException that a tool can throw. #5050)
• Harrison/text splitter (Harrison/text splitter #5417)
• New Trello document loader (New Trello document loader #4767)
• DocumentLoader for GitHub (DocumentLoader for GitHub #5408)
• Harrison/spark reader (Harrison/spark reader #5405)
• Set old LCTracer to default to port 8000 (Set old LCTracer to default to port 8000 #5381)
• Rename and fix typo in lancedb (Rename and fix typo in lancedb #5425)
• Harrison/condense q llm (Harrison/condense q llm #5438)
• adding MongoDBAtlasVectorSearch (adding MongoDBAtlasVectorSearch #5338)
• Add more code splitters (go, rst, js, java, cpp, scala, ruby, php, swift, rust) (Add more code splitters (go, rst, js, java, cpp, scala, ruby, php, swift, rust) #5171)
• bump 185 (bump 185 #5442)
• fix (fix #5457)
• bump 186 (bump 186 #5459)
• Fixed docstring in faiss.py for load_local (Fixed docstring in faiss.py for load_local #5440)
• Removes duplicated call from langchain/client/langchain.py (Removes duplicated call from langchain/client/langchain.py #5449)
• encoding_kwargs for InstructEmbeddings (encoding_kwargs for InstructEmbeddings #5450)
• MRKL output parser no longer breaks well formed queries (MRKL output parser no longer breaks well formed queries #5432)
• docs: cleaning (docs: cleaning #5413)
• Added async _acall to FakeListLLM (Added async _acall to FakeListLLM #5439)
• Feat: Add batching to Qdrant (Feat: Add batching to Qdrant #5443)
• Update psychicapi version (Update psychicapi version #5471)
• Add maximal relevance search to SKLearnVectorStore (Add maximal relevance search to SKLearnVectorStore #5430)
• add simple test for imports (add simple test for imports #5461)
• Ability to specify credentials wihen using Google BigQuery as a data loader (Ability to specify credentials wihen using Google BigQuery as a data loader #5466)
• convert the parameter 'text' to uppercase in the function 'parse' of the class BooleanOutputParser (convert the parameter 'text' to uppercase in the function 'parse' of the class BooleanOutputParser #5397)
• added n_threads functionality for gpt4all (added n_threads functionality for gpt4all #5427)
• Allow for async use of SelfAskWithSearchChain (Allow for async use of SelfAskWithSearchChain #5394)
• Allow ElasticsearchEmbeddings to create a connection with ES Client object (Allow ElasticsearchEmbeddings to create a connection with ES Client object #5321)
• SQLite-backed Entity Memory (SQLite-backed Entity Memory #5129)
• py tracer fixes (py tracer fixes #5377)
• Harrison/html splitter (Harrison/html splitter #5468)
• Feature: Qdrant filters supports (Feature: Qdrant filters supports #5446)
• Add matching engine vectorstore (Harrison/matching engine vectorstore #3350)
• code splitter docs (code splitter docs #5480)
• Bedrock llm and embeddings (Bedrock llm and embeddings #5464)
• add more vars to text splitter (add more vars to text splitter #5503)
• bump 187 (bump 187 #5504)
• Add Feedback Methods + Evaluation examples (Add Feedback Methods + Evaluation examples #5166)
• Add allow_download as attribute for GPT4All (add allow_download as class attribute for GPT4All #5512)
• added DeepLearing.AI course link (added DeepLearing.AI course link #5518)
• Skips creating boto client for Bedrock if passed in constructor (Skips creating boto client for Bedrock if passed in constructor #5523)
• Add Managed Motorhead (Add Managed Motorhead #5507)
• Replace enumerate with zip. (Replace enumerate with zip. #5527)
• Add minor fixes for PySpark Document Loader Docs (Add minor fixes for PySpark Document Loader Docs #5525)
• docs: unstructured no longer requires installing detectron2 from source (docs: unstructured no longer requires installing detectron2 from source #5524)
• Replace list comprehension with generator. (Replace list comprehension with generator. #5526)
• Add param requests_kwargs for WebBaseLoader (Add param requests_kwargs for WebBaseLoader #5485)
• Replace loop appends with list comprehension. (Replace loop appends with list comprehension. #5528)
• [retrievers][knn] Replace loop appends with list comprehension. ([retrievers][knn] Replace loop appends with list comprehension. #5529)
• Fix wrong class instantiation in docs MMR example (Fix wrong class instantiation in docs MMR example #5501)
• Add texts with embeddings to PGVector wrapper (Add texts with embeddings to PGVector wrapper #5500)
• make BaseEntityStore inherit from BaseModel (make BaseEntityStore inherit from BaseModel #5478)
• docs ecosystem/integrations update 3 (docs ecosystem/integrations update 3 #5470)
• feat(integrations): Add WandbTracer (feat(integrations): Add WandbTracer #4521)
• add maxcompute (add maxcompute #5533)
• add brave search util (add brave search util #5538)
• Corrects inconsistently misspelled variable name. (Corrects inconsistently misspelled variable name. #5559)
• Qdrant self query (Qdrant self query #5567)
• bump 188 (bump 188 #5568)
• make the elasticsearch api support version which below 8.x (make the elasticsearch api support version which below 8.x #5495)
• Fix typo in docugami.ipynb (Fix typo in docugami.ipynb #5571)
• Add missing comma in conv chat agent prompt json (Add missing comma in conv chat agent prompt json #5573)
• Fix bedrock auth validation (Fix bedrock boto3 client instantiation #5574)
• Documentation fixes (linting and broken links) (Documentation fixes (linting and broken links) #5563)
• nit (nit #5578)
• Fix SQLAlchemy truncating text when it is too big (Fix SQLAlchemy truncating text when it is too big #5206)
• docs(integration): update colab and external links in WandbTracing docs (docs(integration): update colab and external links in WandbTracing docs #5602)
• Rm Template Title (Rm Template Title #5616)
• human approval callback (human approval callback #5581)
• Es knn index search 5346 (Es knn index search 5346 #5569)
• Fix: Qdrant ids (Fix: Qdrant ids #5515)
• Dev2049/add argilla callback (Dev2049/add argilla callback #5621)
• bump 189 (bump 189 #5620)
• fix chroma update_document to embed entire documents, fixes a characer-wise embedding bug (fix chroma update_document to embed entire documents, fixes a characer-wise embedding bug #5584)
• Fix bedrock llm boto3 client instantiation (Fix bedrock llm boto3 client instantiation #5629)
• Update Tracer Auth / Reduce Num Calls (Update Tracer Auth / Reduce Num Calls #5517)
• fix import issue (fix import issue #5636)
• feat: add UnstructuredExcelLoader for .xlsx and .xls files (feat: add UnstructuredExcelLoader for .xlsx and .xls files #5617)
• Fixed multi input prompt for MapReduceChain (Fixed multi input prompt for MapReduceChain #4979)
• docs: modules pages simplified (docs: modules pages simplified #5116)
• minor refactor GenerativeAgentMemory (minor refactor GenerativeAgentMemory #5315)
• pref: reduce DB query error rate (pref: reduce DB query error rate #5339)
• Update confluence.py to return spaces between elements (Update confluence.py to return spaces between elements #5383)
• Implements support for Personal Access Token Authentication in the ConfluenceLoader (Implements support for Personal Access Token Authentication in the ConfluenceLoader #5385)
• Adds the option to pass the original prompt into the AgentExecutor for PlanAndExecute agents (Adds the option to pass the original prompt into the AgentExecutor for PlanAndExecute agents #5401)
• QuickFix for FinalStreamingStdOutCallbackHandler: Ignore new lines & white spaces (QuickFix for FinalStreamingStdOutCallbackHandler: Ignore new lines & white spaces #5497)
• Add parameters to send_message() call for vertexai chat models (PaLM2) (Add parameters to send_message() call for vertexai chat models (PaLM2) #5566)
• handle single arg to and/or (handle single arg to and/or #5637)
• docs ecosystem/integrations update 4 (docs ecosystem/integrations update 4 #5590)
• nit: pgvector python example notebook, fix variable reference (nit: pgvector python example notebook, fix variable reference #5595)
• Harrison/update azure nb (Harrison/update azure nb #5665)
• Harrison/pubmed integration (Harrison/pubmed integration #5664)
• removing client+namespace in favor of collection (removing client+namespace in favor of collection #5610)
• fix: correct momento chat history notebook typo and title (fix: correct momento chat history notebook typo and title #5646)
• Created fix for 5475 (Created fix for 5475 #5659)
• FileCallbackHandler (FileCallbackHandler #5589)
• refactor: BaseStringMessagePromptTemplate from_template method (refactor: BaseStringMessagePromptTemplate from_template method  #5332)
• Update youtube.py - Fix metadata validation error in YoutubeLoader (Update youtube.py - Fix metadata validation error in YoutubeLoader #5479)
• Improve Error Messaging for APOC Procedure Failure in Neo4jGraph (Improve Error Messaging for APOC Procedure Failure in Neo4jGraph #5547)
• Support similarity_score_threshold retrieval with Chroma (Support similarity_score_threshold retrieval with Chroma #5655)
• This fixes issue AttributeError: 'LLModel' object has no attribute 'model_type' (gpt4all) #5651 - GPT4All wrapper loading issue (This fixes issue #5651 - GPT4All wrapper loading issue #5657)
• Add args_schema to google_places tool (Add args_schema to google_places tool #5680)
• Harrison/pipeline prompt (Harrison/pipeline prompt #5540)
• Added Dependencies Status, Open issues and releases badges in Readme.md (Added Dependencies Status, Open issues and releases badges in Readme.md #5681)
• SQL agent : Improved prompt engineering prevents agent guessing database column names. (SQL agent : Improved prompt engineering prevents agent guessing database column names. #5671)
• Retitles Bedrock doc to appear in correct alphabetical order in site nav (Retitles Bedrock doc to appear in correct alphabetical order in site nav #5639)
• Update MongoDBChatMessageHistory to create an index on SessionId (Update MongoDBChatMessageHistory to create an index on SessionId #5632)
• Raise an exception in MKRL and Chat Output Parsers if parsing text which contains both an action and a final answer (Raise an exception in MKRL and Chat Output Parsers if parsing text which contains both an action and a final answer #5609)
• refactor: extract token text splitter function (refactor: extract token text splitter function #5179)
• sqlalchemy MovedIn20Warning declarative_base DEPRICATION fix (sqlalchemy MovedIn20Warning declarative_base DEPRICATION fix  #5676)
• top_k and top_p transposed in vertexai (top_k and top_p transposed in vertexai #5673)
• bump version to 190 (bump version to 190 #5704)
• Addresses GPT4All wrapper model_type attribute issues AttributeError: 'GPT4All' object has no attribute 'model_type' (langchain 0.0.190) #5720. (Addresses GPT4All wrapper model_type attribute issues #5720. #5743)
• docs: Added Deploying LLMs into production + a new ecosystem (docs: Added Deploying LLMs into production + a new ecosystem #4047)
• Adding support to save multiple memories at a time. Cuts save time by … (Adding support to save multiple memories at a time. Cuts save time by … #5172)
• Cypher search: Check if generated Cypher is provided in backticks (Cypher search: Check if generated Cypher is provided in backticks #5541)
• Zep Hybrid Search (Zep Hybrid Search #5742)
• Removes unnecessary backslash escaping for backticks in python (Removes unnecessary backslash escaping for backticks in python #5751)
• Fix a typo in the documentation for the Slack document loader (Fix a typo in the documentation for the Slack document loader #5745)
• Error in documentation: Chroma constructor (Error in documentation: Chroma constructor #5731)
• Integrate Clickhouse as Vector Store (Clickhouse based Vector Store #5650)
• Create OpenAIWhisperParser for generating Documents from audio files (Create OpenAIWhisperParser for generating Documents from audio files #5580)
• docs: ecosystem/integrations update 5 (docs: ecosystem/integrations update 5 #5752)
• docs: updated ecosystem/dependents (docs: updated ecosystem/dependents #5753)
• Add class attribute "return_generated_question" to class "BaseConversationalRetrievalChain" (Add class attribute "return_generated_question" to class "BaseConversationalRetrievalChain" #5749)
• Add aviary support (Add aviary support #5661)
• cohere retries (cohere retries #5757)
• Strips whitespace and \n from loc before filtering urls from sitemap (Strips whitespace and \n from loc before filtering urls from sitemap #5728)
• Harrison/youtube multi language (Harrison/youtube multi language #5758)
• fix markdown text splitter horizontal lines (fix markdown text splitter horizontal lines #5625)
• Tracing Group (Tracing Group #5326)
• Update tutorials.md (Update tutorials.md #5761)
• feat: Support for Tigris Vector Database for vector search (feat: Support for Tigris Vector Database for vector search #5703)
• Scores are explained in vectorestore docs (Scores are explained in vectorestore docs #5613)
• bump ver 191 (bump ver 191 #5766)
• Use client from LCP-SDK (Use client from LCP-SDK #5695)
• fix ver 191 (fix ver 191 #5784)
• Set Falsey (Set Falsey #5783)
• Attribute support for html tags (Attribute support for html tags #5782)
• support returning run info for llms, chat models and chains (support returning run info for llms, chat models and chains #5666)
• fixing from_documents method of the MongoDB Atlas vector store (fixing from_documents method of the MongoDB Atlas vector store #5794)
• Revise DATABRICKS_API_TOKEN as DATABRICKS_TOKEN (Revise DATABRICKS_API_TOKEN as DATABRICKS_TOKEN #5796)
• YoutubeAudioLoader and updates to OpenAIWhisperParser (YoutubeAudioLoader and updates to OpenAIWhisperParser #5772)
• Base RunEvaluator Chain (Base RunEvaluator Chain #5750)
• [Docs][Hotfix] Fix broken links ([Docs][Hotfix] Fix broken links #5800)
• Add UTF-8 json ouput support while langchain.debug is set to True. (Add UTF-8 json ouput support while langchain.debug is set to True. #5802)
• WIP: openai settings (WIP: openai settings #5792)
• added support for different types in ResponseSchema class (added support for different types in ResponseSchema class #5789)
• fixed faiss integ tests (fixed faiss integ tests #5808)
• add doc about reusing MongoDBAtlasVectorSearch (add doc about reusing MongoDBAtlasVectorSearch #5805)
• Update adding_memory.ipynb (Update adding_memory.ipynb #5806)
• rm docs mongo (rm docs mongo #5811)
• bump ver to 192 (bump ver to 192 #5812)
• fix: fullfill openai params when embedding (fix: fullfill openai params when embedding #5821)
• bump version to 193 (bump version to 193 #5838)
• Add in the async methods and link the run id (Add in the async methods and link the run id #5810)
• feat: issue-5712 add sleep tool (feat: issue-5712 add sleep tool #5715)
• Rm extraneous args to the trace group helper (Rm extraneous args to the trace group helper #5801)
• FIX: backslash escaped (FIX: backslash escaped #5815)
• Add DeepInfra embeddings integration with tests and examples, better exception handling for Deep Infra LLM (Add DeepInfra embeddings integration with tests and examples, better exception handling for Deep Infra LLM #5854)
• Add how to use a custom scraping function with the sitemap loader. (Add how to use a custom scraping function with the sitemap loader. #5847)
• feat: Add UnstructuredCSVLoader for CSV files (feat: Add UnstructuredCSVLoader for CSV files #5844)
• Add logging in PBI tool (Add logging in PBI tool #5841)
• Add additional VertexAI Params (Add additional VertexAI Params #5837)
• Update microsoft loader example with docx2txt dependency (Update microsoft loader example with docx2txt dependency #5832)
• docs: add Shale Protocol integration guide (docs: add Shale Protocol integration guide #5814)
• qdrant vector store - search with relevancy scores (qdrant vector store - search with relevancy scores #5781)
• Update to Getting Started docs page for Memory (Update to Getting Started docs page for Memory #5855)
• Fix exporting GCP Vertex Matching Engine from vectorstores (Fix exporting GCP Vertex Matching Engine from vectorstores #5793)
• Add knn and query search field options to ElasticKnnSearch (Add knn and query search field options to ElasticKnnSearch #5641)
• propagate callbacks to ConversationalRetrievalChain (propagate callbacks to ConversationalRetrievalChain #5572)
• Fix serialization issue with W&B (Fix serialization issue with W&B #5693)
• Added SingleStoreDB Vector Store (Added SingleStoreDB Vector Store #5619)
• Refactor and update databricks integration page (Refactor and update databricks integration page #5575)
• Implement saving and loading of RetrievalQA chain (Implement saving and loading of RetrievalQA chain #5818)
• Harrison/fauna loader (Harrison/fauna loader #5864)
• Harrison/nebula graph (Harrison/nebula graph #5865)
• bump version to 194 (bump version to 194 #5866)
• fix: update qa_chain doc for "chai_type" (fix: update qa_chain doc for "chai_type" #5877)
• Update run eval imports in init (Update run eval imports in init #5858)
• Fix the shortcut conflict for document page search (Fix the shortcut conflict for document page search #5874)
• Fixes model arguments for amazon models (Fixes model arguments for amazon models #5896)
• Feature/add AWS Kendra Index Retriever (Feature/add AWS Kendra Index Retriever #5856)
• Use LCP Client in Tracer (Use LCP Client in Tracer #5908)
• Create snowflake Loader (Create snowflake Loader #5825)
• arxiv: Correct name of search client attribute to 'arxiv_search' from incorrect 'arxiv_client' (arxiv: Correct name of search client attribute to 'arxiv_search' from incorrect 'arxiv_client' #5917)
• Fix typo (Fix typo #5894)
• Baseten integration (Baseten integration #5862)
• Add start index to metadata in TextSplitter (Add start index to metadata in TextSplitter #5912)
• Fix openai proxy error (Fix openai proxy error #5914)
• Fix the issue where the parameters passed to VertexAI ignored When inialztion VertexAI() all passed parameters got ignored #5889 (Fix the issue where the parameters passed to VertexAI ignored #5889 #5891)
• Add support for the endpoint URL in DynamoDBChatMesasgeHistory (Add support for the endpoint URL in DynamoDBChatMesasgeHistory #5836)
• Expose full params in Qdrant (Expose full params in Qdrant #5947)
• fixes to docs (fixes to docs #5919)
• bump ver to 195 (bump ver to 195 #5949)
• Add load() to snowflake loader (Add load() to snowflake loader #5956)
• LOTR: Lord of the Retrievers. A retriever that merge several retrievers together applying document_formatters to them. (LOTR: Lord of the Retrievers. A retriever that merge several retrievers together applying document_formatters to them. #5798)
• bump version to 196 (bump version to 196 #5988)
• Fix: SnowflakeLoader returning empty documents (Fix: SnowflakeLoader returning empty documents #5967)
• Fixed typo missing "use" (Fixed typo missing "use" #5991)
• add test for structured tools (add test for structured tools #5989)
• Fix handling of missing action & input for async MRKL agent (Fix handling of missing action & input for async MRKL agent #5985)
• Add additional parameters to Graph Cypher Chain (Add additional parameters to Graph Cypher Chain  #5979)
• Add a new vector store - AwaDB (Add a new vector store - AwaDB  #5971) (Add a new vector store - AwaDB (#5971) #5992)
• Create Airtable loader (Create Airtable loader #5958)
• feat: Add UnstructuredXMLLoader for .xml files (feat: Add UnstructuredXMLLoader for .xml files #5955)
• Update to Vectara integration (Update to Vectara integration #5950)
• fix: use model token limit not tokenizer ditto (fix: use model token limit not tokenizer ditto #5939)
• Fix: Grammer fix in documentation (Fix: Grammer fix in documentation #5925)
• Fix IndexError in RecursiveCharacterTextSplitter (Fix IndexError in RecursiveCharacterTextSplitter #5902)
• add ocr_languages param for ConfluenceLoader.load() (add ocr_languages param for ConfluenceLoader.load() #5823)
• Harrison/arxiv fix (Harrison/arxiv fix #5993)
• Obey handler.raise_error in _ahandle_event_for_handler (Obey handler.raise_error in _ahandle_event_for_handler #6001)
• support kwargs (support kwargs #5990)
• bump version to 197 (bump version to 197 #6007)
• Update databricks.md (Update databricks.md #6006)
• [APIChain] enhance the robustness or url ([APIChain] enhance the robustness or url #6008)
• feat: ✨ Added filtering option to FAISS vectorstore (feat: ✨ Added filtering option to FAISS vectorstore #5966)
• fix: TypeError when loading confluence pages by cql (fix: TypeError when loading confluence pages by cql #5878)
• Harrison/embaas (Harrison/embaas #6010)
• I before E (I before E #6015)
• nc/load (nc/load #5733)
• Update check (Update check #6020)
• Langchain decorators (Langchain decorators #6017)
• Remove from PR template (Remove from PR template #6018)
• add from_documents interface in awadb vector store (add from_documents interface in awadb vector store #6023)
• Harrison/hologres (Harrison/hologres #6012)
• Update MongoDB Atlas support docs (Update MongoDB Atlas support docs #6022)
• add dashscope text embedding (add dashscope text embedding #5929)
• Harrison/cognitive search (Harrison/cognitive search #6011)
• bump ver to 198 (bump ver to 198 #6026)
• Mongo db doc fix (Mongo db doc fix #6042)
• embaas title
• comment out
• chore: spedd up integration test by using smaller model (chore: spedd up integration test by using smaller model #6044)
• Text splitter for Markdown files by header (Text splitter for Markdown files by header #5860)
• Log tracer errors (Log tracer errors #6066)
• Add embaas document extraction api endpoints (Add embaas document extraction api endpoints  #6048)
• improve tools (improve tools #6062)
• propogate kwargs fully (propogate kwargs fully #6076)
• Enable serialization for anthropic (Enable serialization for anthropic #6049)
• turn off repr (turn off repr #6078)
• Use Run object from SDK (Use Run object from SDK #6067)
• Fix for ModuleNotFoundError while running langchain-server. Issue langchain-server: ModuleNotFoundError: No module named 'langchain.cli' #5833 (Fix for ModuleNotFoundError while running langchain-server. Issue #5833 #6077)
• Add tests and update notebook for MarkdownHeaderTextSplitter (Add tests and update notebook for MarkdownHeaderTextSplitter #6069)
• support functions (support functions #6099)
• convert tools to openai (convert tools to openai #6100)
• Implement max_marginal_relevance_search in VectorStore of Pinecone (Implement max_marginal_relevance_search in VectorStore of Pinecone #6056)
• bump version to 199 (bump version to 199 #6102)
• Harrison/notebook functions (Harrison/notebook functions #6103)
• Add support for tags (Add support for tags #5898)
• support streaming for functions (support streaming for functions #6115)
• Return session name in runner response (Return session name in runner response #6112)
• add functions agent (add functions agent #6113)
• bump ver to 200 (bump ver to 200 #6130)
• Add Run Collector Callback (Add Run Collector Callback #6133)
• Update Name (Update Name #6136)
• Update readthedocs_documentation.ipynb (Update readthedocs_documentation.ipynb #6148)
• typo: 'following following' to 'following' (typo: 'following following' to 'following' #6163)
• Add docs for tags (Add docs for tags #6155)
• feat: Add support for the Solidity language ( feat: Add support for the Solidity language #6054)
• feat: add content_format param to ConfluenceLoader.load() (feat: add content_format param to ConfluenceLoader.load() #5922)
• count tokens for new OpenAI model versions (count tokens for new OpenAI model versions #6195)
• Fix typo pandocs to pandoc (Fix typo pandocs to pandoc #6203)
• Harrison/use functions agent (Harrison/use functions agent #6185)
• bump version to 201 (bump version to 201 #6233)
• Add Tags for LLMs (Add Tags for LLMs #6229)
• Feature/add acreom loader (Feature/add acreom loader #5780)
• Support chat history persistence in AutoGPT (Support chat history persistence in AutoGPT #5716)
• Improve Error Message for failed callback (Improve Error Message for failed callback #6247)
• Harrison/openai functions (Harrison/openai functions #6223)
• Harrison/openai functions (Harrison/openai functions #6261)
• Fix: change the chatgpt plugin retriever metadata format (Fix: change the chatgpt plugin retriever metadata format #5920)
• Update output format of MosaicML endpoint to be more flexible (Update output format of MosaicML endpoint to be more flexible #6060)
• ArxivAPIWrapper - doc_content_chars_max (ArxivAPIWrapper - doc_content_chars_max #6063)
• bump to 202 (bump to 202 #6262)
• Doc refactor (Dev2049/docs docusaurus #6300)
• rm ignore_vercel (rm ignore_vercel #6302)
• update api link (update api link #6303)
• update readme (update readme #6304)
• basic redirect (basic redirect #6309)
• more redirect (more redirect #6314)
• Update dev container (Update dev container #6189)
• Del linkcheck readme (Del linkcheck readme #6317)
• Fixes LLMRequestsChain not enforcing headers when making http requests #6282 (Fixes #6282 #6283)
• nit (nit #6305)
• Improve the performance of add_texts interface and upgrade the AwaDB from 0.3.2 to 0.3.3 (Improve the performance of add_texts interface and upgrade the AwaDB from 0.3.2 to 0.3.3 #6316)
• fix eval guide links (fix eval guide links #6319)
• Harrison/deeplake new features (Harrison/deeplake new features #6263)
• Better Entity Memory code documentation (Better Entity Memory code documentation #6318)
• Handle Managed Motorhead Data Key (Handle Managed Motorhead Data Key #6169)
• changed height in the nb example (changed height in the nb example #6327)
• fix links to prompt templates and example selectors (fix links to prompt templates and example selectors #6332)
• DocArray as a Retriever (DocArray as a Retriever #6031)
• make modelname_to_contextsize as a staticmethod (make modelname_to_contextsize as a staticmethod #6040)
• Improve AnalyticDB Vector Store implementation without affecting user (Improve AnalyticDB Vector Store implementation without affecting user  #6086)
• Add oobabooga/text-generation-webui support as a llm (Add oobabooga/text-generation-webui support as a llm #5997)
• Allow GoogleDrive to authenticate via application default credentials on Cloud Run/GCE etc without service key (Allow GoogleDrive to authenticate via application default credentials on Cloud Run/GCE etc without service key #6035)
• qdrant: search by vector (qdrant: search by vector #6043)
• Harrison/error zero tools (Harrison/error zero tools #6340)
• Harrison/faiss score (Harrison/faiss score #6341)
• Custom Anthropic API URL (Custom Anthropic API URL #6221)
• fix spelling
• Make lckwargs private (Make lckwargs private #6344)
• fix titles in documentation
• update web_base.py to have verify option (update web_base.py to have verify option #6107)
• Add new openai 0613 model costs (Add new openai 0613 model costs #6110)
• Add ignore vercel preview script (Add ignore vercel preview script #6320)
• Harrison/mmr support for opensearch (Harrison/mmr support for opensearch #6349)
• Update MD header text splitter notebook (Update MD header text splitter notebook #6339)
• Add self query retriever example with MD header splitting (Add self query retriever example with MD header splitting #6359)
• bump 203 (bump 203 #6372)
• Guardrails output parser: Pass LLM api for reasking (Guardrails output parser: Pass LLM api for reasking #6089)
• Harrison/gdrive enhancements (Harrison/gdrive enhancements #6375)
• Extend ArgillaCallbackHandler support (Extend ArgillaCallbackHandler support #6153)
• Add the ability to run the map_reduce chains process results step as async (Add the ability to run the map_reduce chains process results step as async  #6181)
• fix link of callbacks on modules page (fix link of callbacks on modules page #6323)
• Fixed PermissionError on windows (Fixed PermissionError on windows #6170)
• searx - docs
• Harrison/myscale self query (Harrison/myscale self query #6376)
• Harrison/metaphor search fix (Harrison/metaphor search fix #6387)
• Harrison/zep mem (Harrison/zep mem #6388)
• Fix class promotion (Fix class promotion #6187)
• Harrison/functions docs improvements (Harrison/functions docs improvements #6389)
• Add option to save/load graph cypher QA (Add option to save/load graph cypher QA #6219)
• Fix output final text for HuggingFaceTextGenInference when streaming (Fix output final text for HuggingFaceTextGenInference when streaming #6211)
• OpenAI functions dont work with async streaming... OpenAI functions dont work with async streaming... #6225 (OpenAI functions dont work with async streaming... #6225 #6226)
• searx_search: updated tools and doc (searx_search: updated tools and doc #6276)
• Fix integration tests for Faiss vector store (Fix integration tests for Faiss vector store #6281)
• [hotfix] Deep Lake fails on newer version due to hardcode ([hotfix] Deep Lake fails on newer version due to hardcode #6383)
• Fix latest clickhouse vector schema change (Fix latest clickhouse vector schema change  #6385)
• Fix typo in the CAI critique prompt (Fix typo in the CAI critique prompt #6123)
• Correct AzureSearch Vector Store not applying search_kwargs when searching (Correct AzureSearch Vector Store not applying search_kwargs when searching #6132)
• Fixed an unhandled error that was raised when DynamoDB did not have any chat history. (Fixed an unhandled error that was raised when DynamoDB did not have any chat history. #6141)
• Fix LLM types so that they can be loaded from config dicts (Fix LLM types so that they can be loaded from config dicts #6235)
• add max_context_size property in BaseOpenAI (add max_context_size property in BaseOpenAI #6239)
• Add markdown to specify important arguments (Add markdown to specify important arguments #6246)
• Update web_base.ipynb for guiding purposes (Update web_base.ipynb for guiding purposes #6248)
• Iterate through filtered file types instead of all listed files (Iterate through filtered file types instead of all listed files #6258)
• Fixes typo in Vectara.similarity_search (Fixes typo in Vectara.similarity_search #6277)
• • Fix pass system_message argument in new feature openai_functions_agent (- Fix pass system_message argument in new feature openai_functions_agent #6297)
• Added gpt-3.5-turbo 0613 16k and 16k-0613 pricing (Added gpt-3.5-turbo 0613 16k and 16k-0613 pricing #6287)
• rm pandas from arize (rm pandas from arize #6392)
• Harrison/typesense fix (Harrison/typesense fix #6391)
• Harrison/chroma fix (Harrison/chroma fix #6390)
• Update web_base.py _fetch() method For SiteMapLoader (Update web_base.py _fetch() method For SiteMapLoader #6256)
• support memory for functions (support memory for functions #6165)
• fix prod docs build (fix prod docs build #6402)
• Docs nit (nit #6350)
• changes to llm chain (changes to llm chain #6328)
• Harrison/refactor functions (Harrison/refactor functions #6408)
• bump version to 205 (bump version to 205 #6410)
• Include placeholder value for all secrets, not just kwargs (Include placeholder value for all secrets, not just kwargs #6421)
• remove mongo
• expose docs chains (expose docs chains #6453)
• Run eval in eval mode (Run eval in eval mode #6447)
• Update arize_callback.py (Update arize_callback.py #6433)
• Add Trajectory Eval RunEvaluator (Add Trajectory Eval RunEvaluator #6449)
• fix anthropic chat model mutating input list (fix anthropic chat model mutating input list #6457)
• Remove extra word in the introduction documentation (Remove extra word in the introduction documentation #6450)
• Add example for question answering over documents with OpenAI Function Agent (Add example for question answering over documents with OpenAI Function Agent #6448)
• Add _similarity_search_with_relevance_scores in Pinecone (Add _similarity_search_with_relevance_scores in Pinecone #6446)
• Update web_base.ipynb (Update web_base.ipynb #6430)
• Remove backticks without clear purpose from docs (Remove backticks without clear purpose from docs #6442)
• Fix Custom LLM Agent example (Fix Custom LLM Agent example #6429)
• Update introduction.mdx (Update introduction.mdx #6425)
• docs retrievers fixes (docs retrievers fixes #6299)
• Fixed a link typo /-/route -> /-/routes. and change endpoint format (Fixed a link typo /-/route -> /-/routes. and change endpoint format #6186)
• Incorrect argument count handling (Incorrect argument count handling #5543)
• Harrison/functions in retrieval (Harrison/functions in retrieval #6463)
• Fix for ChatPromptTemplate with partial variables is giving validation error #6431 - chatprompt template with partial variables giing validation error (Fix for #6431 - chatprompt template with partial variables throws validation error #6456)
• Update SinglStoreDB vectorstore (Update SinglStoreDB vectorstore #6423)
• Fix broken links in autonomous agents docs (Fix broken links in autonomous agents docs #6398)
• Fix the issue where ANTHROPIC_API_URL set in environment is not takin… (Fix the issue where ANTHROPIC_API_URL set in environment is not takin… #6400)
• Improve error message (Improve error message #6275)
• Harrison/unstructured page number (Harrison/unstructured page number #6464)
• feat: use latest duckduckgo_search API to call (feat: use latest duckduckgo_search API to call #6409)
• fix: llm caching for replicate (fix: llm caching for replicate #6396)
• Update serpapi.py Support baidu list type answer_box (Update serpapi.py Support baidu list type answer_box #6386)
• fix neo4j schema query (fix neo4j schema query #6381)
• bump version to 206 (bump version to 206 #6465)
• add FunctionMessage support to _convert_dict_to_message() in OpenAI chat model (add FunctionMessage support to _convert_dict_to_message() in OpenAI chat model #6382)
• fix openai qa chain (fix openai qa chain #6487)
• Add Alibaba Cloud OpenSearch as a new vector store (Add Alibaba Cloud OpenSearch as a new vector store #6154)
• release 207 (release 207 #6488)
• fix: change ddg to DDGS (fix: change ddg to DDGS #6480)
• improve documentation on base chain (improve documentation on base chain #6468)
• Vector store support for Cassandra (Vector store support for Cassandra #6426)
• Update notebook for MD header splitter and create new cookbook (Update notebook for MD header splitter and create new cookbook #6399)
• docs/fix links (docs/fix links #6498)
• Fix link (Fix link #6501)
• Documentation Fix: Correct the example code output in the prompt templates doc (Documentation Fix: Correct the example code output in the prompt templates doc #6496)
• Fixed: 'readible' -> readable (Fixed: 'readible' -> readable #6492)
• Make streamlit import optional (Make streamlit import optional #6510)
• Fix typo in docstring of format_tool_to_openai_function (Fix typo in docstring of format_tool_to_openai_function #6479)
• typo(llamacpp.ipynb): 'condiser' -> 'consider' (typo(llamacpp.ipynb): 'condiser' -> 'consider' #6474)
• Export trajectory eval fn (Export trajectory eval fn #6509)
• Update index.mdx (Update index.mdx #6326)
• Add KuzuQAChain (Add KuzuQAChain #6454)
• Be able to use Codey models on Vertex AI (Be able to use Codey models on Vertex AI #6354)
• Add async support for HuggingFaceTextGenInference (Add async support for HuggingFaceTextGenInference #6507)
• Feat: Add a prompt template parameter to qa with structure chains (Feat: Add a prompt template parameter to qa with structure chains #6495)
• Integrate Rockset as Vectorstore (Integrate Rockset as Vectorstore #6216)
• Fix issue with non-list To header in GmailSendMessage Tool (Fix issue with non-list To header in GmailSendMessage Tool #6242)
• Update model token mappings/cost to include 0613 models (Update model token mappings/cost to include 0613 models #6122)
• Infino integration for simplified logs, metrics & search across LLM data & token usage (Infino integration for simplified logs, metrics & search across LLM data & token usage #6218)
• Harrison/multi tool (Harrison/multi tool #6518)
• bump to ver 208 (bump to ver 208 #6540)
• Relax string input mapper check (Relax string input mapper check #6544)
• [Feature][VectorStore] Support StarRocks as vector db ([Feature][VectorStore] Support StarRocks as vector db #6119)
• Minor Grammar Fixes in Docs and Comments (Minor Grammar Fixes in Docs and Comments #6536)
• Remove unintended double negation in docstring (Remove unintended double negation in docstring #6541)
• update pr tmpl (update pr tmpl #6552)
• feat: faiss filter from list (feat: faiss filter from list #6537)
• Wait for all futures (Wait for all futures #6554)
• Fix whatsappchatloader - enable parsing new datetime format on WhatsApp chat (Fix whatsappchatloader - enable parsing new datetime format on WhatsApp chat #6555)
• Remove duplicate databricks entries in ecosystem integrations (Remove duplicate databricks entries in ecosystem integrations #6569)
• Change Data Loader Namespace (Change Data Loader Namespace #6568)
• Detailed using the Twilio tool to send messages with 3rd party apps incl. WhatsApp (Detailed using the Twilio tool to send messages with 3rd party apps incl. WhatsApp #6562)
• add motherduck docs (add motherduck docs #6572)
• Upgrade the version of AwaDB and add some new interfaces (Upgrade the version of AwaDB and add some new interfaces #6565)
• feat: interfaces for async embeddings, implement async openai (feat: interfaces for async embeddings, implement async openai #6563)
• Add OpenLLM wrapper(Dev2049/openllm #6578)
• Add AzureML endpoint LLM wrapper (Dev2049/azure endpoint #6580)
• Add missing word in comment (Add missing word in comment #6587)
• Clarifai integration (Clarifai integration #5954)
• bump 209 (bump 209 #6593)
• Fix callback forwarding in async plan method for OpenAI function agent (Fix callback forwarding in async plan method for OpenAI function agent #6584)
• MD header text splitter returns Documents (MD header text splitter returns Documents #6571)
• add mongo (HOLD) (add mongo (HOLD) #6437)
• Allow callback handlers to opt into being run inline (Allow callback handlers to opt into being run inline #6424)
• StreamlitCallbackHandler (StreamlitCallbackHandler #6315)
• added redis method to delete entries by keys (added redis method to delete entries by keys #6222)
• Loader for OpenCityData and minor cleanups to Pandas, Airtable loaders (Loader for OpenCityData and minor cleanups to Pandas, Airtable loaders #6301)
• Add tags in agent initialization (Add tags in agent initialization #6559)
• Session to project (Session to project #6249)
• fix: remove callbacks arg from Tool and StructuredTool inferred schema (fix: remove callbacks arg from Tool and StructuredTool inferred schema #6483)
• bump 210 (bump 210 #6656)
• Openapi to openai (Dev2049/openapi to openai #6658)
• bump 211 (bump 211 #6660)
• openapi_openai docstring (openapi_openai docstring #6661)
• Create merge loader that combines documents from a set of loaders (Create merge loader that combines documents from a set of loaders #6659)
• Add delete and ensure add_texts performs upsert (w/ ID optional) (Add delete and ensure add_texts performs upsert (w/ ID optional) #6126)
• Recursive URL loader (Recursive URL loader #6455)
• ChatVertexAI broken - Fix error with sending context in params (ChatVertexAI broken - Fix error with sending context in params #6652)
• Dev2049/bump 212 (Dev2049/bump 212 #6665)
• fix(docs): broken link for OpenLLM (fix(docs): broken link for OpenLLM #6622)
• Fix grammar mistake in base.py in planners (Fix grammar mistake in base.py in planners #6611)
• Fix ray-project/Aviary integration (Fix ray-project/Aviary integration #6607)
• Fix Typo (Fix Typo #6595)
• Fix typo in myscale_self_query.ipynb (Fix typo in myscale_self_query.ipynb #6601)
• fix minor typo in vector_db_qa.mdx (fix minor typo in vector_db_qa.mdx #6604)
• Kendra retriever api (Kendra retriever api #6616)
• PowerBI: catch outdated token (PowerBI: catch outdated token #6634)
• update chroma notebook (update chroma notebook #6664)
• openapi -> openai nit (openapi -> openai nit #6667)
• adds doc_content_chars_max argument to WikipediaLoader (adds doc_content_chars_max argument to WikipediaLoader #6645)
• chroma nb close img tag (chroma nb close img tag #6669)
• Changed generate_prompt.py (Changed generate_prompt.py #6644)
• added docstrings where they missed (docstrings: top-level 1 #6626)
• Wiki loader lint (Dev2049/wiki lint #6670)
• Just corrected a small inconsistency on a doc page (Just corrected a small inconsistency on a doc page #6603)
• Fix openapi parameter parsing (Fix openapi parameter parsing #6676)
• Amazon API Gateway hosted LLM (Amazon API Gateway hosted LLM #6673)
• Session deletion method in motorhead memory (Session deletion method in motorhead memory #6609)
• Harrison/optional ids opensearch (Harrison/optional ids opensearch #6684)
• Add caching to BaseChatModel (issue Add caching support to BaseChatModel #1644) ( Add caching to BaseChatModel (issue #1644) #5089)
• bump to version 213 (bump to version 213 #6688)
• Make bs4 a local import in recursive_url_loader.py (Make bs4 a local import in recursive_url_loader.py #6693)
• bump v214 (bump v214 #6694)
• split up batch llm calls into separate runs (split up batch llm calls into separate runs #5804)
• bump version to 215 (bump version to 215 #6719)
• Fix Multi Functions Agent Tracing (Fix Multi Functions Agent Tracing #6702)
• fix chroma _similarity_search_with_relevance_scores missing kwargs … (fix chroma _similarity_search_with_relevance_scores missing kwargs … #6708)
• Fix Typo in LangChain MyScale Integration Doc (Fix Typo in LangChain MyScale Integration Doc #6705)
• updated sql_database.py for returning sorted table names. (updated sql_database.py for returning sorted table names. #6692)
• Fix WhatsAppChatLoader : Enable parsing additional formats (Fix WhatsAppChatLoader : Enable parsing additional formats #6663)
• feat: added tqdm progress bar to UnstructuredURLLoader (feat: added tqdm progress bar to UnstructuredURLLoader #6600)
• feat: Add UnstructuredRSTLoader (feat: Add UnstructuredRSTLoader #6594)
• beautifulsoup get_text kwargs in WebBaseLoader (beautifulsoup get_text kwargs in WebBaseLoader #6591)
• Added a MHTML document loader (Added a MHTML document loader #6311)
• correct docs site links
• zep api_key auth

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

1 Ignored Deployment

Name	Status	Preview	Comments	Updated (UTC)
langchain	⬜️ Ignored (Inspect)			Jun 25, 2023 11:02pm