295 Commits (924b7ecf8979eea84e2a793c8e029a8571d81518)

Author	SHA1	Message	Date
Harrison Chase	924b7ecf89	pass kwargs and bump (#770)	1 year ago
Samantha Whitmore	be7de427ca	Serialize all the chains! (#761) ... Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	1 year ago
Harrison Chase	e2a7fed890	Harrison/serialize from llm and tools (#760)	1 year ago
Harrison Chase	12dc7f26cc	load agents from hub (#759)	1 year ago
Harrison Chase	7129f23511	output parser serialization (#758)	1 year ago
Harrison Chase	f273c50d62	add loading chains from hub (#757)	1 year ago
Harrison Chase	1b89a438cf	(wip) Harrison/serialize agents (#725)	1 year ago
Harrison Chase	cc70565886	add prompt type (#730)	1 year ago
Francisco Ingham	374e510f94	Upper bound on number of iterations (#754) ... Some custom agents might continue to iterate until they find the correct answer, getting stuck on loops that generate request after request and are really expensive for the end user. Putting an upper bound for the number of iterations by default controls this and can be explicitly tweaked by the user if necessary. Co-authored-by: Francisco Ingham <>	1 year ago
Smit Shah	28efbb05bf	Add params to reduce K dynamically to reduce it below token limit (#739) ... Referring to #687, I implemented the functionality to reduce K if it exceeds the token limit. Edit: I should have ran make lint locally. Also, this only applies to `StuffDocumentChain`	1 year ago
Roy Williams	d2f882158f	Add type information for crawler.py (#738) ... Added type information to `crawler.py` to make it safer to use and understand.	1 year ago
Ankush Gola	57609845df	add tracing support to langchain (#741) ... * add implementations of `BaseCallbackHandler` to support tracing: `SharedTracer` which is thread-safe and `Tracer` which is not and is meant to be used locally. * Tracers persist runs to locally running `langchain-server` Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	1 year ago
Harrison Chase	7f76a1189c	bump version to 0.0.70 (#744)	1 year ago
Harrison Chase	2ba1128095	Harrison/backwards compat (#740)	1 year ago
Francisco Ingham	f9ddcb5705	Hotfix: distance_func and collection_name must not be in kwargs (#735) ... If `distance_func` and `collection_name` are in `kwargs` they are sent to the `QdrantClient` which results in an error being raised. Co-authored-by: Francisco Ingham <>	1 year ago
Amos Ng	fa6826e417	Fix sqlalchemy warnings when running tests (#733) ... This has been bugging me when running my own tests that call langchain methods :P	1 year ago
Harrison Chase	9194a8be89	add stop to stream (#729)	1 year ago
scadEfUr	e3df8ab6dc	move hyde into chains (#728) ... Co-authored-by: scadEfUr <>	1 year ago
Harrison Chase	0ffeabd14f	Harrison/serialize llm chain (#671)	1 year ago
Feynman Liang	2824f36401	Add namespace to Pinecone.from_index (#716) ... Resolves https://github.com/hwchase17/langchain/issues/718	1 year ago
Kacper Łukawski	d4f719c34b	Convert numpy arrays to lists in HuggingFaceEmbeddings (#714) ... `SentenceTransformer` returns a NumPy array, not a `List[List[float]]` or `List[float]` as specified in the interface of `Embeddings`. That PR makes it consistent with the interface.	1 year ago
Kacper Łukawski	97c3544a1e	Hotfix: Qdrant.from_text embeddings (#713) ... I'm providing a hotfix for Qdrant integration. Calculating a single embedding to obtain the vector size was great idea. However, that change introduced a bug trying to put only that single embedding into the database. It's fixed. Right now all the embeddings will be pushed to Qdrant.	1 year ago
Feynman Liang	3a38604f07	Fix typo (#705)	1 year ago
Harrison Chase	fc4ad2db0f	langchain hub docs (#704) ... Co-authored-by: scadEfUr <123224380+scadEfUr@users.noreply.github.com>	1 year ago
Scott Leibrand	34932dd211	remove legacy embedding model name (#703) ... Now that OpenAI has deprecated all embeddings models except text-embedding-ada-002, we should stop specifying a legacy embedding model in the example. This will also avoid confusion from people (like me) trying to specify model="text-embedding-ada-002" and having that erroneously expanded to text-search-text-embedding-ada-002-query-001	1 year ago
scadEfUr	4aba0abeaa	added common prompt load method (#699) ... Co-authored-by: scadEfUr	1 year ago
xloem	36b6b3cdf6	HuggingFacePipeline: Forward model_kwargs. (#696) ... Since the tokenizer and model are constructed manually, model_kwargs needs to be passed to their constructors. Additionally, the pipeline has a specific named parameter to pass these with, which can provide forward compatibility if they are used for something other than tokenizer or model construction.	1 year ago
Harrison Chase	3a30e6daa8	Harrison/openai callback (#684)	1 year ago
Harrison Chase	aef82f5d59	fix whitespace for conversational agent (#690)	1 year ago
Harrison Chase	86dbdb118b	Harrison/serpapi extra tools (#691) ... Co-authored-by: Bruno Bornsztein <bruno.bornsztein@gmail.com>	1 year ago
Harrison Chase	cbc146720b	verbose flag (#683)	1 year ago
Harrison Chase	27cef0870d	bump version to 0.0.67 (#689)	1 year ago
Samantha Whitmore	77e3d58922	ConversationEntityMemory: Chain which uses an entity extraction & sum… (#678) ... …marization prompt to maintain a key-value store of memory information cc @devennavani Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	1 year ago
dham	e04b063ff4	add faiss local saving/loading (#676) ... - This uses the faiss built-in `write_index` and `load_index` to save and load faiss indexes locally - Also fixes #674 - The save/load functions also use the faiss library, so I refactored the dependency into a function	1 year ago
Harrison Chase	e45f7e40e8	Harrison/few shot yaml (#682) ... Co-authored-by: vintro <77507980+vintrocode@users.noreply.github.com>	1 year ago
Harrison Chase	a2eeaf3d43	strip whitespace (#680)	1 year ago
Harrison Chase	3d41af0aba	Harrison/load tools kwargs (#681) ... Co-authored-by: Bruno Bornsztein <bruno.bornsztein@gmail.com>	1 year ago
Harrison Chase	0b204d8c21	Harrison/quadrant (#665) ... Co-authored-by: Kacper Łukawski <kacperlukawski@users.noreply.github.com>	1 year ago
Harrison Chase	983b73f47c	add search kwargs (#664)	1 year ago
vertinski	65f3a341b0	Prompt fix for empty intermediate steps in summarization (#660) ... Adding quotation marks around {text} avoids generating empty or completely random responses from OpenAI davinci-003. Empty or completely unrelated intermediate responses in summarization messes up the final result or makes it very inaccurate. The error from OpenAI would be: "The model predicted a completion that begins with a stop sequence, resulting in no output. Consider adjusting your prompt or stop sequences." This fix corrects the prompting for summarization chain. This works on API too, the images are for demonstrative purposes. This approach can be applied to other similar prompts too. Examples: 1) Without quotation marks  2) With quotation marks 	1 year ago
iocuydi	69998b5fad	Add ids parameter for pinecone from_texts / add_texts (#659) ... Allow optionally specifying a list of ids for pinecone rather than having them randomly generated. This also permits editing the embedding/metadata of existing pinecone entries, by id.	1 year ago
Harrison Chase	54d7f1c933	fix caching (#658)	1 year ago
Harrison Chase	d0fdc6da11	Harrison/bing wrapper (#656) ... Co-authored-by: Enrico Shippole <henryshippole@gmail.com>	1 year ago
iocuydi	207e319a70	Add search_kwargs option for VectorDBQAWithSourcesChain (#657) ... Allows for passing additional vectorstore params like namespace, etc. to VectorDBQAWithSourcesChain Example: `chain = VectorDBQAWithSourcesChain.from_llm(OpenAI(temperature=0), vectorstore=store, search_kwargs={"namespace": namespace})`	1 year ago
Harrison Chase	052c361031	pinecone docstring (#654)	1 year ago
Harrison Chase	95720adff5	Add documentation for custom prompts for Agents (#631) (#640) ... - Added a comment interpreting regex for `ZeroShotAgent` - Added a note to the `Custom Agent` notebook Co-authored-by: Sam Ching <samuel@duolingo.com>	1 year ago
Harrison Chase	6be5f4e4c4	Harrison/sql db chain (#641) ... Co-authored-by: Bruno Bornsztein <bruno.bornsztein@gmail.com>	1 year ago
Harrison Chase	4d4cff0530	Harrison/cohere experimental (#638) ... Co-authored-by: inyourhead <44607279+xettrisomeman@users.noreply.github.com>	1 year ago
Sasmitha Manathunga	5c97f70bf1	Fix CohereError: embed is not an available endpoint on this model (#637) ... Running the Cohere embeddings example from the docs: ```python from langchain.embeddings import CohereEmbeddings embeddings = CohereEmbeddings(cohere_api_key= cohere_api_key) text = "This is a test document." query_result = embeddings.embed_query(text) doc_result = embeddings.embed_documents([text]) ``` I get the error: ```bash CohereError(message=res['message'], http_status=response.status_code, headers=response.headers) cohere.error.CohereError: embed is not an available endpoint on this model ``` This is because the `model` string is set to `medium` which is not currently available. From the Cohere docs: > Currently available models are small and large (default)	1 year ago
Francisco Ingham	b929fd9f59	Exclude reference to 'example' in api prompt (#629) ... Co-authored-by: lesscomfortable <pancho_ingham@hotmail.com>	1 year ago