714 Commits (main)

 

All Branches   

Search

Author	SHA1	Message	Date
Harrison Chase	2584663e44	remove unused buffer (#919)	1 year ago
Harrison Chase	cc20b9425e	add reqs (#918)	1 year ago
Harrison Chase	cea380174f	fix docs custom prompt template (#917)	1 year ago
Harrison Chase	87fad8fc00	analyze document (#731) ... add analyze document chain, which does text splitting and then analysis	1 year ago
Harrison Chase	e2b834e427	Harrison/prompt template prefix (#888) ... Co-authored-by: Gabriel Simmons <simmons.gabe@gmail.com>	1 year ago
Harrison Chase	f95cedc443	Harrison/sql rows (#915) ... Co-authored-by: Jon Luo <20971593+jzluo@users.noreply.github.com>	1 year ago
Harrison Chase	ba5a2f06b9	Harrison/inference endpoint (#861) ... Co-authored-by: Eno Reyes <enoreyes@gmail.com>	1 year ago
Harrison Chase	2ec25ddd4c	add unstructured examples (#913)	1 year ago
Kevin Huo	31b054f69d	Add pinecone integration test (#911) ... Basic integration test for pinecone	1 year ago
Harrison Chase	93a091cfb8	Optionally return shell output on incorrect command (#894) (#899) ... This allows the LLM to correct its previous command by looking at the error message output to the shell. Additionally, this uses subprocess.run because that is now recommended over subprocess.check_output: https://docs.python.org/3/library/subprocess.html#using-the-subprocess-module Co-authored-by: Amos Ng <me@amos.ng>	1 year ago
James Briggs	3aa53b44dd	added i_end in batch extraction (#907) ... Fix for issue #906 Switches `[i : i + batch_size]` to `[i : i_end]` in Pinecone `from_texts` method	1 year ago
Harrison Chase	82c080c6e6	bump version to 0078 (#908)	1 year ago
Harrison Chase	71e662e88d	update docs (#905)	1 year ago
Harrison Chase	53d56d7650	Harrison/unstructured support (#903)	1 year ago
Harrison Chase	2a68be3e8d	chat vector db chain (#902)	1 year ago
James Briggs	8217a2f26c	Update pinecone init details in docs (#898) ... PR to fix outdated environment details in the docs, see issue #897 I added code comments as pointers to where users go to get API keys, and where they can find the relevant environment variable.	1 year ago
Bagatur	7658263bfb	Check type of LLM.generate `prompts` arg (#886) ... Was passing prompt in directly as string and getting nonsense outputs. Had to inspect source code to realize that first arg should be a list. Could be nice if there was an explicit error or warning, seems like this could be a common mistake.	1 year ago
Samantha Whitmore	32b11101d3	Get elements of ActionInput on newlines (#889) ... The re.DOTALL flag in Python's re (regular expression) module makes the . (dot) metacharacter match newline characters as well as any other character. Without re.DOTALL, the . metacharacter only matches any character except for a newline character. With re.DOTALL, the . metacharacter matches any character, including newline characters.	1 year ago
Harrison Chase	1614c5f5fd	fix flaky tests (#892)	1 year ago
Harrison Chase	a2b699dcd2	prompt template from string (#884)	1 year ago
Alex	7cc44b3bdb	Add to gallery (#882)	1 year ago
Harrison Chase	0b9f086d36	Harrison/docs splitter (#879)	1 year ago
Harrison Chase	bcfbc7a818	version 0077 (#878)	1 year ago
Ryan Walker	1dd0733515	Fix small typo in getting started docs (#876) ... Just noticed this little typo while reading the docs, thought I'd open a PR!	1 year ago
Zach Schillaci	4c79100b15	Correct prompt typo + update example for SQLDatabaseChain (#868) ... See https://github.com/hwchase17/langchain/issues/821	1 year ago
Harrison Chase	777aaff841	fix routing to tiktoken encoder (#866)	1 year ago
Harrison Chase	e9ef08862d	validate template (#865)	1 year ago
Harrison Chase	364b771743	sql return direct (#864)	1 year ago
Harrison Chase	483441d305	pass kwargs through to loading (#863)	1 year ago
Harrison Chase	8df6b68093	fix length based example selector (#862)	1 year ago
Harrison Chase	3f48eed5bd	Harrison/milvus (#856) ... Signed-off-by: Filip Haltmayer <filip.haltmayer@zilliz.com> Signed-off-by: Frank Liu <frank.liu@zilliz.com> Co-authored-by: Filip Haltmayer <81822489+filip-halt@users.noreply.github.com> Co-authored-by: Frank Liu <frank@frankzliu.com>	1 year ago
Ankush Gola	933441cc52	Add retry to OpenAI llm (#849) ... add ability to retry when certain exceptions are raised by `openai.Completions.create` Test plan: ran all OpenAI integration tests.	1 year ago
kahkeng	4a8f5cdf4b	Add alternative token-based text splitter (#816) ... This does not involve a separator, and will naively chunk input text at the appropriate boundaries in token space. This is helpful if we have strict token length limits that we need to strictly follow the specified chunk size, and we can't use aggressive separators like spaces to guarantee the absence of long strings. CharacterTextSplitter will let these strings through without splitting them, which could cause overflow errors downstream. Splitting at arbitrary token boundaries is not ideal but is hopefully mitigated by having a decent overlap quantity. Also this results in chunks which has exact number of tokens desired, instead of sometimes overcounting if we concatenate shorter strings. Potentially also helps with #528.	1 year ago
Harrison Chase	523ad2e6bd	vercel deployments (#850)	1 year ago
Harrison Chase	fc0cfd7d1f	docs (#848)	1 year ago
Harrison Chase	4d32441b86	bump version to 0076 (#847)	1 year ago
Harrison Chase	23d5f64bda	Harrison/ngram example (#846) ... Co-authored-by: Sean Spriggens <ssprigge@syr.edu>	1 year ago
Harrison Chase	0de55048b7	return code for pal (#844)	1 year ago
Harrison Chase	d564308e0f	rfc: instruct embeddings (#811) ... Co-authored-by: seanaedmiston <seane999@gmail.com>	1 year ago
Nick Furlotte	576609e665	Update PAL to allow passing local and global context to PythonREPL (#774) ... Passing additional variables to the python environment can be useful for example if you want to generate code to analyze a dataset. I also added a tracker for the executed code - `code_history`.	1 year ago
Harrison Chase	3f952eb597	add from string method (#820)	1 year ago
Ikko Eltociear Ashimine	ba26a879e0	Fix typo in crawler.py (#842) ... seperator -> separator	1 year ago
Eli Mernit	bfabd1d5c0	Added new deployment template (#835) ... This PR introduces a new template for deploying LangChain apps as web endpoints. It includes template code, and links to a detailed code-walkthrough.	1 year ago
Jonas Ehrenstein	f3508228df	Minor fix for google search util: it's uncertain if "snippet" in results exists (#830) ... The results from Google search may not always contain a "snippet". Example: `{'kind': 'customsearch#result', 'title': 'FEMA Flood Map', 'htmlTitle': 'FEMA Flood Map', 'link': 'https://msc.fema.gov/portal/home', 'displayLink': 'msc.fema.gov', 'formattedUrl': 'https://msc.fema.gov/portal/home', 'htmlFormattedUrl': 'https://<b>msc</b>.fema.gov/portal/home'}` This will cause a KeyError at line 99 `snippets.append(result["snippet"])`.	1 year ago
Zach Schillaci	b4eb043b81	Minor fix to SQLDatabaseChain doc (#826)	1 year ago
Istora Mandiri	06438794e1	Fix typo in textsplitter docs (#825)	1 year ago
Raza Habib	9f8e05ffd4	Update __init__.py (#827) ... Remove duplicate APIChain	1 year ago
Harrison Chase	b0d560be56	add to gallery (#824)	1 year ago
Johanna Appel	ebea40ce86	Add 'truncate' parameter for CohereEmbeddings (#798) ... Currently, the 'truncate' parameter of the cohere API is not supported. This means that by default, if trying to generate and embedding that is too big, the call will just fail with an error (which is frustrating if using this embedding source e.g. with GPT-Index, because it's hard to handle it properly when generating a lot of embeddings). With the parameter, one can decide to either truncate the START or END of the text to fit the max token length and still generate an embedding without throwing the error. In this PR, I added this parameter to the class. _Arguably, there should be a better way to handle this error, e.g. by optionally calling a function or so that gets triggered when the token limit is reached and can split the document or some such. Especially in the use case with GPT-Index, its often hard to estimate the token counts for each document and I'd rather sort out the troublemakers or simply split them than interrupting the whole execution. Thoughts?_ --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	1 year ago
Harrison Chase	b9045f7e0d	bump version to 0075 (#819)	1 year ago